正在加载视频...

视频加载失败

返回首页

Grok Build CLI just got an update with v0.2.113! 🚀 Changelog v0.2.113 Features: • MCP servers can now be enabled or disabled directly from the CLI with `grok mcp enable ` and `grok mcp disable `. • Full plan markdown can now be copied to the clipboard with `y`...

GrokInsider's profile picture

Puck

5,385 subscribers

94,737 次观看 • 1 个月前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Grok Build CLI just got an update with v0.2.100! 🚀 Changelog v0.2.100 Features: • Session picker now discovers and resumes recent Claude Code, Codex, and Cursor sessions. • Welcome screen now offers a one-click resume nudge for recent Claude, Codex, or Cursor sessions. Bug Fixes: • Web fetch tool preserves full truncated page content as readable artifacts instead of discarding it. • Multiline mode now correctly sends the top queued message on empty Enter when a turn is running. • Queued commands no longer disappear or delay when pressing Enter twice quickly during a running turn. • Minimal mode text is now readable on dark terminals with proper contrast and highlighted user prompts. • Grok no longer crashes when printing resume hints after the terminal pane has closed. • Long-running turns with multiple waits now show updated status markers in the transcript instead of appearing stuck. • Claude and Cursor hooks are now correctly disabled at session start when disabled in config.
0:53

Grok Build CLI just got an update with v0.2.100! 🚀 Changelog v0.2.100 Features: • Session picker now discovers and resumes recent Claude Code, Codex, and Cursor sessions. • Welcome screen now offers a one-click resume nudge for recent Claude, Codex, or Cursor sessions. Bug Fixes: • Web fetch tool preserves full truncated page content as readable artifacts instead of discarding it. • Multiline mode now correctly sends the top queued message on empty Enter when a turn is running. • Queued commands no longer disappear or delay when pressing Enter twice quickly during a running turn. • Minimal mode text is now readable on dark terminals with proper contrast and highlighted user prompts. • Grok no longer crashes when printing resume hints after the terminal pane has closed. • Long-running turns with multiple waits now show updated status markers in the transcript instead of appearing stuck. • Claude and Cursor hooks are now correctly disabled at session start when disabled in config.

Grok News

44,121 次观看 • 2 个月前

Grok Build CLI just got an update with v1.0.5! 🚀 Changelog v1.0.5 Features: • GROK_CONFIG and GROK_CONFIG_PATH environment variables now let launchers override selected config settings without editing config.toml. • Worktrees under ~/.grok/worktrees are now automatically reclaimed when safe, with strong safeguards that never delete a user's last copy. • Hook policy blocks now correctly report "Turn blocked by a hook" instead of "Turn cancelled by user." • Image and video generation now limits how many calls the model can request in one step to avoid overload. • Arabic and Persian text can now be reordered correctly in the terminal UI. Turn on in /settings. • Reasoning effort can now be supplied when an ACP client opens or resumes a session. • Session titles now refresh early in the conversation and stay stable; /resume shows a recap and last-turn summary when available. • GROK_FORCE_LOGIN_TEAM_ID environment variable now lets launchers restrict interactive login to one or more teams. • Preparing spinner now shows readable labels such as "Writing file…" and "Writing edit…" for common tools. Bug Fixes: • Tool calls (shell, grep, list_dir) no longer fail for the rest of a session if /dev/null is removed. • Agent skill discovery now resolves the user's home directory correctly on Windows. • MCP tool calls now show clearer spinner text instead of the raw wire name while arguments are still arriving. • grok inspect no longer crashes when its output is piped into a command that closes the pipe early. • Minimal mode no longer truncates a still-streaming assistant reply when thinking blocks are interleaved.
0:59

Grok Build CLI just got an update with v1.0.5! 🚀 Changelog v1.0.5 Features: • GROK_CONFIG and GROK_CONFIG_PATH environment variables now let launchers override selected config settings without editing config.toml. • Worktrees under ~/.grok/worktrees are now automatically reclaimed when safe, with strong safeguards that never delete a user's last copy. • Hook policy blocks now correctly report "Turn blocked by a hook" instead of "Turn cancelled by user." • Image and video generation now limits how many calls the model can request in one step to avoid overload. • Arabic and Persian text can now be reordered correctly in the terminal UI. Turn on in /settings. • Reasoning effort can now be supplied when an ACP client opens or resumes a session. • Session titles now refresh early in the conversation and stay stable; /resume shows a recap and last-turn summary when available. • GROK_FORCE_LOGIN_TEAM_ID environment variable now lets launchers restrict interactive login to one or more teams. • Preparing spinner now shows readable labels such as "Writing file…" and "Writing edit…" for common tools. Bug Fixes: • Tool calls (shell, grep, list_dir) no longer fail for the rest of a session if /dev/null is removed. • Agent skill discovery now resolves the user's home directory correctly on Windows. • MCP tool calls now show clearer spinner text instead of the raw wire name while arguments are still arriving. • grok inspect no longer crashes when its output is piped into a command that closes the pipe early. • Minimal mode no longer truncates a still-streaming assistant reply when thinking blocks are interleaved.

Puck

31,441 次观看 • 1 个月前

Introducing my newest app, TethrX, made with Grok 4.5 to access Grok Build on your phone. TethrX connects to Grok Build running on your own computer, so you can start a task from anywhere, follow Grok's reasoning as it works, approve every command before it runs, and review the code it writes. Your code never leaves your machine. The public TestFlight is now open, and a demonstration is below. You pair your phone by scanning a QR code, either on your local network or from anywhere through Tailscale. From there TethrX streams Grok's reasoning, tool calls, command output and file changes as they happen, and asks your approval before anything runs. Plan mode lets you read the plan before the work begins. When a task finishes you can review exactly what changed. TethrX lists the modified files in your project, shows a diff for each one, and lets you commit or discard the work without leaving your phone. The app supports slash commands, including /compact and any skills you have installed, along with voice dictation, queued messages and reusable prompts. Sessions can be searched and organised into folders, and you can pair several computers and switch between them. Siri can start a task or tell you what Grok is doing without opening the app, a home screen widget shows whether Grok is working, and a Live Activity tracks progress on your lock screen and Dynamic Island. Every session reports its context window, token usage and cost, the app can be locked behind Face ID, and your computer is kept awake for as long as a task is running. TethrX requires Grok Build installed and signed in on your computer, together with Node.js 20 or newer. A single command starts the bridge: npx tethrx-bridge TethrX is open source under the Apache License 2.0. Both the iOS client and the local bridge are available here: Grok 4.5 helped a lot, thanks to SpaceXAI for making Grok 4.5 exceptional.
0:27

Introducing my newest app, TethrX, made with Grok 4.5 to access Grok Build on your phone. TethrX connects to Grok Build running on your own computer, so you can start a task from anywhere, follow Grok's reasoning as it works, approve every command before it runs, and review the code it writes. Your code never leaves your machine. The public TestFlight is now open, and a demonstration is below. You pair your phone by scanning a QR code, either on your local network or from anywhere through Tailscale. From there TethrX streams Grok's reasoning, tool calls, command output and file changes as they happen, and asks your approval before anything runs. Plan mode lets you read the plan before the work begins. When a task finishes you can review exactly what changed. TethrX lists the modified files in your project, shows a diff for each one, and lets you commit or discard the work without leaving your phone. The app supports slash commands, including /compact and any skills you have installed, along with voice dictation, queued messages and reusable prompts. Sessions can be searched and organised into folders, and you can pair several computers and switch between them. Siri can start a task or tell you what Grok is doing without opening the app, a home screen widget shows whether Grok is working, and a Live Activity tracks progress on your lock screen and Dynamic Island. Every session reports its context window, token usage and cost, the app can be locked behind Face ID, and your computer is kept awake for as long as a task is running. TethrX requires Grok Build installed and signed in on your computer, together with Node.js 20 or newer. A single command starts the bridge: npx tethrx-bridge TethrX is open source under the Apache License 2.0. Both the iOS client and the local bridge are available here: Grok 4.5 helped a lot, thanks to SpaceXAI for making Grok 4.5 exceptional.

Myrhe𝕩

13,099 次观看 • 1 个月前

long time no posting, here's some of the stuff we released in helium recently: - customizable keyboard shortcuts on all platforms - automatic updates on windows - frameless mode (previously zen mode), with floating sidebar, is now out of beta and included in settings by default - improved fingerprint noising: fixed the canvas noising algorithm and added protections against analysis attacks (thank you Cynthia 🐈 for your report, research, and assistance) - tab URL copying, one or multiple, formatted as a list with line breaks - manual tab hibernation, with an option to hibernate all tabs except for selected/active ones - an option to close tabs to the left (or above, in vertical layout) - redesigned toast notifications, now anchored to the active web page, and no longer blinding in dark mode - toast notification about newly opened background tabs in frameless mode (can be disabled in settings) - redesigned the infobar, it no longer looks out of place - improved QR code generation, now it's actually useful - downloads bubble is now shown instead of the full page whenever applicable - kagi search now supports reverse image search from image context menu - frameless mode animations are now smoother - better color contrast in light and dark modes - a lot of bug fixes and other minor improvements all of these changes are present in the latest version of helium. if you're using helium on windows, please update to the latest version, so your browser can be updated automatically from now on!
0:45

long time no posting, here's some of the stuff we released in helium recently: - customizable keyboard shortcuts on all platforms - automatic updates on windows - frameless mode (previously zen mode), with floating sidebar, is now out of beta and included in settings by default - improved fingerprint noising: fixed the canvas noising algorithm and added protections against analysis attacks (thank you Cynthia 🐈 for your report, research, and assistance) - tab URL copying, one or multiple, formatted as a list with line breaks - manual tab hibernation, with an option to hibernate all tabs except for selected/active ones - an option to close tabs to the left (or above, in vertical layout) - redesigned toast notifications, now anchored to the active web page, and no longer blinding in dark mode - toast notification about newly opened background tabs in frameless mode (can be disabled in settings) - redesigned the infobar, it no longer looks out of place - improved QR code generation, now it's actually useful - downloads bubble is now shown instead of the full page whenever applicable - kagi search now supports reverse image search from image context menu - frameless mode animations are now smoother - better color contrast in light and dark modes - a lot of bug fixes and other minor improvements all of these changes are present in the latest version of helium. if you're using helium on windows, please update to the latest version, so your browser can be updated automatically from now on!

Helium

177,589 次观看 • 3 个月前

Look ma new Codex Updates! 0.119.0 and 0.120.0 are here. And with it, a HUGE number of quality of life updates and bug fixes! > Hooks now render in a dedicated live area above the composer. They only persist when they have output, so your terminal stays clean. If you're running PreToolUse or PostToolUse hooks, this is a huge readability win. > Hooks are now available again on Windows > CTRL+O copies the last agent output. Small but clutch when you're pulling a code block into another file or chat. > New statusline option: context usage as a graphical bar instead of a percentage. Easier to glance at mid-session when you're trying to gauge how much runway you have left. > Zellij support is here with no scrollback bugs. If you've been stuck on tmux just because Codex was broken in Zellij, you're free now (shout out Felipe Coury 🦀) > Memory extensions just landed. The consolidation agent can now discover plugin folders under memories_extensions/ and read their instructions.md to learn how to interpret new memory sources. Drop a folder in, give it guidance, and the agent picks it up automatically during summarization. No core code changes needed. This is the first real extension point for Codex's memory system, and it opens the door for third-party memory plugins. > Did you know, you can /rename a thread? But what's really cool about that is, after you rename it, you can resume it with the same name, no more UUIDs. codex resume mynewapp or directly from the TUI: /resume mynewapp > Multi agents v2 got an update to tool descriptions More reliable multi agent environments and inter agent communication > You can now enable TUI notifications whether Codex is in focus or not. Modify this in your config: [tui] notification_condition = "always" > MAJOR overhaul to Codex MCP functionality: 1. Codex Tool Search now works with custom MCP servers, so tools can be searched and deferred instead of all being exposed up front. 2. Custom MCP servers can now trigger elicitations, meaning they can stop and ask for user approval or input mid-flow. 3. MCP tool results now preserve richer metadata, which improves app/UI handoff behavior. 4. Codex can now read MCP resources directly, letting apps return resource URIs that the client can actually open. 5. File params for Codex Apps are smoother: local file paths can be uploaded and remapped automatically. 6. Plugin cache refresh and fallback sync behavior are more reliable, especially for custom and curated plugins. > Composer and chat behavior smoother overall, resize bugs remain though. > Realtime v2 got several significant improvements as well. > You're still reading? What a legend. 🫶 npm i -g @openai/codex to update
0:36

Look ma new Codex Updates! 0.119.0 and 0.120.0 are here. And with it, a HUGE number of quality of life updates and bug fixes! > Hooks now render in a dedicated live area above the composer. They only persist when they have output, so your terminal stays clean. If you're running PreToolUse or PostToolUse hooks, this is a huge readability win. > Hooks are now available again on Windows > CTRL+O copies the last agent output. Small but clutch when you're pulling a code block into another file or chat. > New statusline option: context usage as a graphical bar instead of a percentage. Easier to glance at mid-session when you're trying to gauge how much runway you have left. > Zellij support is here with no scrollback bugs. If you've been stuck on tmux just because Codex was broken in Zellij, you're free now (shout out Felipe Coury 🦀) > Memory extensions just landed. The consolidation agent can now discover plugin folders under memories_extensions/ and read their instructions.md to learn how to interpret new memory sources. Drop a folder in, give it guidance, and the agent picks it up automatically during summarization. No core code changes needed. This is the first real extension point for Codex's memory system, and it opens the door for third-party memory plugins. > Did you know, you can /rename a thread? But what's really cool about that is, after you rename it, you can resume it with the same name, no more UUIDs. codex resume mynewapp or directly from the TUI: /resume mynewapp > Multi agents v2 got an update to tool descriptions More reliable multi agent environments and inter agent communication > You can now enable TUI notifications whether Codex is in focus or not. Modify this in your config: [tui] notification_condition = "always" > MAJOR overhaul to Codex MCP functionality: 1. Codex Tool Search now works with custom MCP servers, so tools can be searched and deferred instead of all being exposed up front. 2. Custom MCP servers can now trigger elicitations, meaning they can stop and ask for user approval or input mid-flow. 3. MCP tool results now preserve richer metadata, which improves app/UI handoff behavior. 4. Codex can now read MCP resources directly, letting apps return resource URIs that the client can actually open. 5. File params for Codex Apps are smoother: local file paths can be uploaded and remapped automatically. 6. Plugin cache refresh and fallback sync behavior are more reliable, especially for custom and curated plugins. > Composer and chat behavior smoother overall, resize bugs remain though. > Realtime v2 got several significant improvements as well. > You're still reading? What a legend. 🫶 npm i -g @openai/codex to update

am.will

742,455 次观看 • 5 个月前

Keet Mobile 4.0.0 Changelog 🍐 Features - Keet 4.0.0 introduces a new engine which improves performance, app scalability and sets the ground for a new set of features development. Improvements - Faster room loading with optimised icons and image-preview caching. - Media previews respect maximum image size to save bandwidth. - Added a system-update banner to keep you informed of important upgrades. - Cleaner room creation flow and refined DM request handling. - Down arrow and room avatar colours match desktop application. - Bottom tab bar is now hidden until onboarding is complete. - Clearer username error messages and progress indicators on slow networks. - Better feedback form now includes your username automatically - Call experience tweaks: hangs up cleanly; DM ring logic improved; Android auto-end in background. - Introduced hang-up icon for when call ends in rooms. - Device naming screen now auto focuses the input field. - Updated confirm device screen. - Software version list now shows Hyperdiscovery and lists WebRTC as keet-webrtc. - Refreshed onboarding pages and UI text updates. - Improved audio record UX and many Fixes - Fixed avatar rendering issues. - Removed grey bars at the top of several pages. - Stopped the tooltip from appearing when the username is already set. - Aligned the error-log message-field layout. - Resolved cursor and emoji picker jumps when switching between emoji and keyboard input. - Corrected chat text input width. - Restored fullscreen video previews. - Fixed image loading status indicators. - Adjusted code block spacing for messages sent from mobile. - Prevented locked recordings from following you when leaving a room. - Fixed a crash when opening a room on Android. - Stopped unnecessary FlatList re-renders. - Center aligned preview images. - Resolved chat UI breakage after double tapping the emoji picker icon. - Corrected contentFit on image messages. - Ensured pinned messages remain visible during a call. - Fixed speaker tooltip content overflow. - Calls: fixed orientation breaks, crash when app is killed, call-ring answer now opens the screen. - Resolved unrecoverable error when sharing a file from Google Files. - Eliminated flicker when searching usernames. - Disabled button presses while a tooltip is visible. - Fixed Discover Communities being cut off on small devices. - Disabled bottom tab presses when no identity is set. - Corrected tooltip orientation on tablets. Keet Desktop 4.0.0 Changelog Features - Keet 4.0.0 introduces a new engine which improves performance, app scalability and sets the ground for a new set of features development Improvements - Introduced system-banner UI for updates and notices. - Added a 'Quit' button to uncaught error screens. - Displayed an app loader before the app initialises. - Added a toast notification and an informative banner when sending a DM request. - Consistent avatars between DM rooms and member views. - Added support to medium sized file previews in chat. - Smoother last message rendering in the room list. - Added a chat loader on start up when no cache is available. - Clearer version display in the software section and added hyper db version to the list. - Updated texts for system and migration banners. - Refactored DM request actions and block member logic. Fixes - Prevented image preview blinking while loading. - Fixed crash when removing an avatar file from a deleted message. - Onboarding status is now remembered after a restart. - Eliminated room menu blinking via useDeferredValue. - Prevented Rive animation from disappearing when switching monitors. - Stopped creation of duplicate DM rooms for the same member. - Resolved broken file preview when a file lacked a name. - Restored missing styles on error pages. - Prevented error pages from appearing behind the loader. - Corrected emoji rendering on macOS. - Repaired chat voice message playback. - Fixed useRoomConfig imports. - Corrected file item height in room info. And more
5:57

Keet Mobile 4.0.0 Changelog 🍐 Features - Keet 4.0.0 introduces a new engine which improves performance, app scalability and sets the ground for a new set of features development. Improvements - Faster room loading with optimised icons and image-preview caching. - Media previews respect maximum image size to save bandwidth. - Added a system-update banner to keep you informed of important upgrades. - Cleaner room creation flow and refined DM request handling. - Down arrow and room avatar colours match desktop application. - Bottom tab bar is now hidden until onboarding is complete. - Clearer username error messages and progress indicators on slow networks. - Better feedback form now includes your username automatically - Call experience tweaks: hangs up cleanly; DM ring logic improved; Android auto-end in background. - Introduced hang-up icon for when call ends in rooms. - Device naming screen now auto focuses the input field. - Updated confirm device screen. - Software version list now shows Hyperdiscovery and lists WebRTC as keet-webrtc. - Refreshed onboarding pages and UI text updates. - Improved audio record UX and many Fixes - Fixed avatar rendering issues. - Removed grey bars at the top of several pages. - Stopped the tooltip from appearing when the username is already set. - Aligned the error-log message-field layout. - Resolved cursor and emoji picker jumps when switching between emoji and keyboard input. - Corrected chat text input width. - Restored fullscreen video previews. - Fixed image loading status indicators. - Adjusted code block spacing for messages sent from mobile. - Prevented locked recordings from following you when leaving a room. - Fixed a crash when opening a room on Android. - Stopped unnecessary FlatList re-renders. - Center aligned preview images. - Resolved chat UI breakage after double tapping the emoji picker icon. - Corrected contentFit on image messages. - Ensured pinned messages remain visible during a call. - Fixed speaker tooltip content overflow. - Calls: fixed orientation breaks, crash when app is killed, call-ring answer now opens the screen. - Resolved unrecoverable error when sharing a file from Google Files. - Eliminated flicker when searching usernames. - Disabled button presses while a tooltip is visible. - Fixed Discover Communities being cut off on small devices. - Disabled bottom tab presses when no identity is set. - Corrected tooltip orientation on tablets. Keet Desktop 4.0.0 Changelog Features - Keet 4.0.0 introduces a new engine which improves performance, app scalability and sets the ground for a new set of features development Improvements - Introduced system-banner UI for updates and notices. - Added a 'Quit' button to uncaught error screens. - Displayed an app loader before the app initialises. - Added a toast notification and an informative banner when sending a DM request. - Consistent avatars between DM rooms and member views. - Added support to medium sized file previews in chat. - Smoother last message rendering in the room list. - Added a chat loader on start up when no cache is available. - Clearer version display in the software section and added hyper db version to the list. - Updated texts for system and migration banners. - Refactored DM request actions and block member logic. Fixes - Prevented image preview blinking while loading. - Fixed crash when removing an avatar file from a deleted message. - Onboarding status is now remembered after a restart. - Eliminated room menu blinking via useDeferredValue. - Prevented Rive animation from disappearing when switching monitors. - Stopped creation of duplicate DM rooms for the same member. - Resolved broken file preview when a file lacked a name. - Restored missing styles on error pages. - Prevented error pages from appearing behind the loader. - Corrected emoji rendering on macOS. - Repaired chat voice message playback. - Fixed useRoomConfig imports. - Corrected file item height in room info. And more

Keet

25,883 次观看 • 1 年前

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.
2:14

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.

Aaron Levie

24,728 次观看 • 5 个月前

BREAKING: SpaceXAI has added a new guide called “Grok Bot 101” It explains how to create a personal AI teammate in just 10 to 15 minutes, teach it real workflows, connect apps, and build teams of specialized bots that continue working in the cloud even after you close your laptop. Here is the full guide in simple terms: • What is Grok Bot Grok Bot is an AI agent with its own persistent computer in the cloud. It has a desktop, files, terminal, browser, and apps. It can browse the web, use software, write and run code, and complete tasks just like someone using a computer. You can access the same computer from your phone or desktop. When needed, Grok Bot can hand control back to you for a CAPTCHA, 2FA, or secure login. • Creating a bot Give the bot a name, title, and detailed instructions. You can explain the workflow through chat or record yourself completing the task. Once trained, the bot can repeat that workflow whenever needed. It can also use MCP servers, plugins, skills, and connected services such as Gmail, Google Calendar, Google Drive, and Slack. • Three ways to use Grok Bot Send it a message in chat. Create schedules or triggers, such as monitoring a Slack thread or GitHub PR. Allow bots to message and activate other bots. • Permissions and safety You can write rules in normal language explaining what the bot can and cannot do. A separate review agent checks proposed actions and can allow them, block them, or ask you for approval. Allow and block lists provide additional control, while the work runs inside an isolated environment. One important detail: if you log into a website with one bot, other bots using that shared cloud computer can also access it. • Multi-bot teams You can create specialist bots for different jobs and let them work together. One bot can ask another for help, several bots can work inside a group chat, and a scheduled routine can move a task through multiple specialists until the work is finished. • Personal CRM The author created a bot that turned the 800 to 900 people he follows on X into a private Notion CRM containing public profile information. It helps him find and reconnect with people when traveling. • Arnold, the fitness bot He replaced a complicated fitness app with a Grok Bot strength-training coach named Arnold. The bot uses MCP servers, plugins, and skills while requiring less maintenance. Its behavior can be updated simply by chatting with it. • Building software Grok Bot gathers information from Slack, Notion, GitHub, documentation, and other sources. It then creates a clean prompt and sends it to a specialized Cursor cloud agent that builds the software. Grok Bot handles the planning and coordination, while the coding agent handles the actual build. • Searching company knowledge Grok Bot can search across codebases, Slack conversations, Notion pages, GitHub, and internal documents to answer product or company questions. This helps people find information faster and reduces the need to interrupt coworkers. • The biggest takeaway Instead of repeatedly building scripts or complicated apps, you can describe a workflow to Grok Bot, improve it through chat, reuse it, and let it continue working in the cloud. Grok Bot is not just another chatbot. It is a real AI teammate with a computer that can use tools, coordinate specialists, and get actual work done. The future of work is becoming incredibly exciting.
0:23

BREAKING: SpaceXAI has added a new guide called “Grok Bot 101” It explains how to create a personal AI teammate in just 10 to 15 minutes, teach it real workflows, connect apps, and build teams of specialized bots that continue working in the cloud even after you close your laptop. Here is the full guide in simple terms: • What is Grok Bot Grok Bot is an AI agent with its own persistent computer in the cloud. It has a desktop, files, terminal, browser, and apps. It can browse the web, use software, write and run code, and complete tasks just like someone using a computer. You can access the same computer from your phone or desktop. When needed, Grok Bot can hand control back to you for a CAPTCHA, 2FA, or secure login. • Creating a bot Give the bot a name, title, and detailed instructions. You can explain the workflow through chat or record yourself completing the task. Once trained, the bot can repeat that workflow whenever needed. It can also use MCP servers, plugins, skills, and connected services such as Gmail, Google Calendar, Google Drive, and Slack. • Three ways to use Grok Bot Send it a message in chat. Create schedules or triggers, such as monitoring a Slack thread or GitHub PR. Allow bots to message and activate other bots. • Permissions and safety You can write rules in normal language explaining what the bot can and cannot do. A separate review agent checks proposed actions and can allow them, block them, or ask you for approval. Allow and block lists provide additional control, while the work runs inside an isolated environment. One important detail: if you log into a website with one bot, other bots using that shared cloud computer can also access it. • Multi-bot teams You can create specialist bots for different jobs and let them work together. One bot can ask another for help, several bots can work inside a group chat, and a scheduled routine can move a task through multiple specialists until the work is finished. • Personal CRM The author created a bot that turned the 800 to 900 people he follows on X into a private Notion CRM containing public profile information. It helps him find and reconnect with people when traveling. • Arnold, the fitness bot He replaced a complicated fitness app with a Grok Bot strength-training coach named Arnold. The bot uses MCP servers, plugins, and skills while requiring less maintenance. Its behavior can be updated simply by chatting with it. • Building software Grok Bot gathers information from Slack, Notion, GitHub, documentation, and other sources. It then creates a clean prompt and sends it to a specialized Cursor cloud agent that builds the software. Grok Bot handles the planning and coordination, while the coding agent handles the actual build. • Searching company knowledge Grok Bot can search across codebases, Slack conversations, Notion pages, GitHub, and internal documents to answer product or company questions. This helps people find information faster and reduces the need to interrupt coworkers. • The biggest takeaway Instead of repeatedly building scripts or complicated apps, you can describe a workflow to Grok Bot, improve it through chat, reuse it, and let it continue working in the cloud. Grok Bot is not just another chatbot. It is a real AI teammate with a computer that can use tools, coordinate specialists, and get actual work done. The future of work is becoming incredibly exciting.

DogeDesigner

126,412 次观看 • 4 天前

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.
0:43

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Aaron Levie

17,543 次观看 • 5 个月前

🛠️ Patch Notes - Early Access Patch 2 We are incredibly excited to be releasing our largest patch yet, marking the One Month Anniversary of our Steam Early Access Launch! Patch 2 is chock full of highly requested features such as Weapon Tryout, the ability to Respec, DLSS / FSR Upscaling and Controller Remapping. Lots of Balancing and Quality of Life improvements, Audio, Animation, and Visual Effect polish as well as a multitude of bug fixes are also included! Between DLSS and FSR, numerous CPU, GPU performance improvements, and memory optimization we are confident that your experience of playing No Rest For The Wicked will be significantly smoother across a wide range of hardware. For NVIDIA users, we are excited to mention that there’s a new Game Ready Driver for No Rest for the Wicked! Be sure to check out our Patch 2 Highlight Video and the full patch notes below. ⚔️ Performance: • Performance Mode now lowers texture resolution, reducing crashes on lower-end machines • Numerous Significant CPU optimizations • Fixed performance degradation that might occur on some gamepads • Fixed numerous memory leaks • Reduced instantiation spikes for numerous objects • Disabled detail meshes on generic humanoids faces when not needed • Reduced latency, overhead and improved stability of GPU Culling • Optimized texture resolution and memory budgets for Steam Deck • Optimized Art content in Ship Prologue and its cinematics • Removed unused weapon assets to free up memory • Removed leftover developer tools to free up memory • Optimized CPU spikes of a variety of common content loading operations • Added texture streaming for character portraits during dialogue interactions to save memory • Fixed some persistent log spam being generated by potatoes in Nameless Pass • Cleaned up numerous NPC prefabs, reducing memory footprint and instantiation costs • Optimized Ambient Occlusion Rendering • Extended GPU culling usage for more cases • Configured and optimized pooling for more prefab instantiations reducing CPU spikes ⚔️ Gameplay Systems: • Added new Respec System! ⚬ Players can now Respec by examining the statue in the Cerim Crucible Atrium ⚬ Respec allows players to take back Attribute Points that have been allocated at the cost of 1 Fallen Ember per Attribute Point returned ⚬ Players can then allocate returned Attribute Points for no cost at the Respec screen or in the existing Stats screen ⚔️ Quality of Life: • All weapons can now be equipped regardless of their Attribute Requirements to allow players to try out weapons they acquire ⚬ Weapons that the player does not meet the requirements for will deal less damage through negative scaling on the Attributes that are below the weapon’s Attribute Requirements • Inventory Items can now be docked to compare them ⚬ Press F (Keyboard) or Y (Controller) to dock items and hover other items to compare • Brought back the Misc category to the Inventory ⚬ Housing items, Runes, Fallen Embers and other miscellaneous items will now be sorted into this category and free up space from other categories • Vendor screens are now sorted by item type so that items are more organized for purchase • Improved Stamina player HUD brightness for better visibility, and readability of stamina debt • Added side notifications for when Danos Sacrament Upgrades are completed • Added Floor Indicators under the Clock HUD to show the Cerim Crucible floors • Improved visibility of LB/RB button icons for Equipment HUD on Steam Deck ⚔️ Settings: • Added support for Upscaling with DLSS 3.7 and FSR 2.2 • Added custom key rebinding options for Controller • Added support for Mouse Buttons 4,5 and F1-F12 Keys for custom Keyboard bindings • Default Keyboard layout set to Mouse+WASD • Added support for worldspace Player HUD (Stamina wheel, NPC name tags, etc) brightness to UI Brightness setting ⚔️ Content Additions: • Added a new set of enchantments • All Throw runes can now be added to Spears ⚔️ Loot: • Added Pig Sticker Blueprint to Fillmore's Level 1 Shop • Added Assegai Blueprint to Whittacker's Level 1 Shop ⚔️ Balance: • Nerfed Throw runes ⚬ Reduced Poise Damage on all Throw runes ⚬ Reduced Damage on Ice Throw Rune • Nerfed Focus Regeneration enchant curve so that it no longer generates too much Focus too quickly • Focus Regeneration enchantment no longer drops with Gloves and now only drops with Helmets • This includes enchanting items at Eleanor • Falling Sky and Woodland Protector’s initial item levels were set too high and have been lowered to the intended levels ⚔️ Weapons: • Updated animation for backstabbing with Staves, Spears, Greatswords and Great Hammers • Updated visual effects for Piercing type weapon attacks (such as Spear or Rapier) ⚔️ Enemies and Bosses: • Polished Darak boss fight ⚬ Improved behavior to prevent him standing idle after attacking ⚬ Improved behavior when fighting ranged builds • Added Bite Attack to Plague Rat • Added Back Attack to Risen Axe Bruiser • Added escape logic to Risen Fire Bomber • Added Elemental Affix visual effects to Nith Brute, Nith Screamer and Shackled Brute • Adding cloth simulation to Boarskin Bruiser • Polished rigging on Plagued Boomer • Reduced camera shake intensity on Risen Hammer Bruiser, Boarskin Bruiser and Riven Twins • Smaller enemies can now smash breakable objects (barrels, crates, etc.) ⚔️ NPCs: • Changed the name of the worried woman in the Sacrament Town Square to Nell • Polishing dialog for Druo, Lucian and Everwyn • Updated the dialog for NPCs at the Cerim Gate in Nameless Pass • Added eavesdrop to Sleeping Guard Gerard in Sacrament ⚔️ Areas: • Improved collision, faders and set dressing in Prologue Ship, Orban Glades, Mariner’s Keep, Nameless Pass, Sacrament, Multiple Sacrament Interiors, Cerim Crucible, Cerim Cave, Riven Twins Boss Arena and Potion Seller Cave • Polished lighting for the ship in Prologue, Sacrament and Cerim Crucible • Updated foliage in various locations • Added physics and wind simulation to Spruce trees ⚔️ Cinematics: • Polished animations for characters in the Inquisition Arrival cinematic • Improved lighting, character rim lighting and volumetrics for the Prologue Ship Crash Outro and Inquisition Arrival cinematics • Removed a background character who was blocking part of the view in the Inquisition Arrival cinematic • Fixed cloth and camera pops in the Inquisition Arrival cinematic ⚔️ Audio: • Environment update for Sacrament: ⚬ Added Ambience Emitters for certain Residential and Vendor buildings like the Cook, Tavern, Woodcrafter and Enchantress ⚬ Updated zone beds and oneshots for unique parts of town (Cemetery, Poor Area,Training Grounds, Dasha Sanctuary) ⚬ The church near the cemetery now has bells ringing to service playing at certain times of day, followed by churchgoers praying and chanting from behind the doors. ⚬ Updated ambience for Sacrament Town Square to feel busier during the day ⚬ Updated environment audio for the Cerim Gate zone in Mountain Pass • Increased audio buffer to help alleviate audio crackle artifacts • Increased available audio resources to help prevent sounds from dropping out during long play sessions • Updated audio for Cerim Vision cinematic • Updated audio mix for Barrel and Crate destruction • Saluting Guards in Sacrament now have sound • Added Weapon-specific Impacts on parrying and blocking actions • Added ladder sliding sound effects for Kickdown Ladders • Added sound effects for going down Ladders • Added new sound effects for Plague-Enchanted weapons • Polished audio for Bounties enemies • Fixed missing sounds for Plagued Mutant Soldier • Fixed rain sounds appearing in Sacrament Interiors • Fixed enchantment-specific weapon whooshes cutting a bit too early • Fixed NPCs not making footstep sounds when walking around • Fixed environment states sometimes not resetting when returning to the main menu ⚔️ VFX: • Blood effects are now juicier and used more often! • Improved blood visual effects attachment to characters bodies from attacking and getting hit • Increased intensity of shiny item drop VFX ⚔️ Bounties and Challenges: • Updated Crustacean Conundrum bounty to spawn 14 Crabs while still only requiring 8 Crabs be killed to complete ⚔️ Localization: • Added and updated localized text in many places across multiple languages • Added localization support for new Controller Remapping screen and for various missing localized elements • Fixed incorrect font on the Activities screen ⚔️ Bug Fixes: • Fixed various enchantments on unique weapons and rings that weren’t working properly • Fixed Rested Bonuses for sleeping in beds • Fixed Key Items respawning after pick up • Fixed navigation in Nameless Pass which was preventing certain enemies and the Riven Twins boss from patrolling and moving to the player • Fixed Echo Knight falling off the arena and blocking progress • Fixed Cerim Armor missing upgrades at Filmore • Fixed Risen Pavise, Eye of the Beholder and Wooden Howler Shields not showing their proper models • Fixed SHIFT key not being recognized in the Main Menu • Fixed certain environment textures overriding certain armor textures • Fixed certain armor having missing or incorrect cloth simulation • Fixed rigging on certain armor • Fixed The Wallow boss attacks not having sound effects • Fixed Falling Sky Blueprint not giving the Unique version of the weapon when crafting • Fixed an issue where completed but not yet turned in bounty/challenge rewards were being automatically given to the player at reset • Fixed wall cannons not firing in Cerim Crucible • Fixed XP UI not showing “Max Level” after reaching the level cap • Fixed Level and XP UI being present without a Character selected in the Main Menu • Fixed “Long Area Name” appearing on the map where map is unavailable (such as Cerim Crucible) • Fixed being able to skip through locked doors in The Shallows • Fixed players getting stuck at the end of the entrance corridor in the Echo Knight Arena • Fixed Enchant Item Challenge counting enchanted items that are picked up • Fixed mortuary guard popping in on screen during Spoken and Unspoken quest • Fixed extra Elsa map marker during the Spoken and Unspoken quest • Fixed Giles and Petra standing instead of sitting on the chairs in Caroline’s Inn • Fixed Arrows not hitting Plagued Wolf • Fixed Wolf and Plagued Wolf target point • Fixed Tanth Knight getting stuck during patrolling in Mariner’s Keep at Endgame state • Fixed Darak leaving his shield in Orban Glades when he escapes • Fixed chest opening VFX in Performance and Balanced quality presets • Fixed Wolf having a dance party after death • Fixed Chest floating in the air in Mariner’s Keep • Fixed incorrect texture on the Crafting Table • Fixed 4096x2160 resolution appearing as 256x135 aspect ratio, instead displays as 1.9:1 • Fixed overblown bonfire lighting at The Shallows • Removed rogue rim light at The Shallows • Removed lighting debug shortcut See the full patch notes here -
1:30

🛠️ Patch Notes - Early Access Patch 2 We are incredibly excited to be releasing our largest patch yet, marking the One Month Anniversary of our Steam Early Access Launch! Patch 2 is chock full of highly requested features such as Weapon Tryout, the ability to Respec, DLSS / FSR Upscaling and Controller Remapping. Lots of Balancing and Quality of Life improvements, Audio, Animation, and Visual Effect polish as well as a multitude of bug fixes are also included! Between DLSS and FSR, numerous CPU, GPU performance improvements, and memory optimization we are confident that your experience of playing No Rest For The Wicked will be significantly smoother across a wide range of hardware. For NVIDIA users, we are excited to mention that there’s a new Game Ready Driver for No Rest for the Wicked! Be sure to check out our Patch 2 Highlight Video and the full patch notes below. ⚔️ Performance: • Performance Mode now lowers texture resolution, reducing crashes on lower-end machines • Numerous Significant CPU optimizations • Fixed performance degradation that might occur on some gamepads • Fixed numerous memory leaks • Reduced instantiation spikes for numerous objects • Disabled detail meshes on generic humanoids faces when not needed • Reduced latency, overhead and improved stability of GPU Culling • Optimized texture resolution and memory budgets for Steam Deck • Optimized Art content in Ship Prologue and its cinematics • Removed unused weapon assets to free up memory • Removed leftover developer tools to free up memory • Optimized CPU spikes of a variety of common content loading operations • Added texture streaming for character portraits during dialogue interactions to save memory • Fixed some persistent log spam being generated by potatoes in Nameless Pass • Cleaned up numerous NPC prefabs, reducing memory footprint and instantiation costs • Optimized Ambient Occlusion Rendering • Extended GPU culling usage for more cases • Configured and optimized pooling for more prefab instantiations reducing CPU spikes ⚔️ Gameplay Systems: • Added new Respec System! ⚬ Players can now Respec by examining the statue in the Cerim Crucible Atrium ⚬ Respec allows players to take back Attribute Points that have been allocated at the cost of 1 Fallen Ember per Attribute Point returned ⚬ Players can then allocate returned Attribute Points for no cost at the Respec screen or in the existing Stats screen ⚔️ Quality of Life: • All weapons can now be equipped regardless of their Attribute Requirements to allow players to try out weapons they acquire ⚬ Weapons that the player does not meet the requirements for will deal less damage through negative scaling on the Attributes that are below the weapon’s Attribute Requirements • Inventory Items can now be docked to compare them ⚬ Press F (Keyboard) or Y (Controller) to dock items and hover other items to compare • Brought back the Misc category to the Inventory ⚬ Housing items, Runes, Fallen Embers and other miscellaneous items will now be sorted into this category and free up space from other categories • Vendor screens are now sorted by item type so that items are more organized for purchase • Improved Stamina player HUD brightness for better visibility, and readability of stamina debt • Added side notifications for when Danos Sacrament Upgrades are completed • Added Floor Indicators under the Clock HUD to show the Cerim Crucible floors • Improved visibility of LB/RB button icons for Equipment HUD on Steam Deck ⚔️ Settings: • Added support for Upscaling with DLSS 3.7 and FSR 2.2 • Added custom key rebinding options for Controller • Added support for Mouse Buttons 4,5 and F1-F12 Keys for custom Keyboard bindings • Default Keyboard layout set to Mouse+WASD • Added support for worldspace Player HUD (Stamina wheel, NPC name tags, etc) brightness to UI Brightness setting ⚔️ Content Additions: • Added a new set of enchantments • All Throw runes can now be added to Spears ⚔️ Loot: • Added Pig Sticker Blueprint to Fillmore's Level 1 Shop • Added Assegai Blueprint to Whittacker's Level 1 Shop ⚔️ Balance: • Nerfed Throw runes ⚬ Reduced Poise Damage on all Throw runes ⚬ Reduced Damage on Ice Throw Rune • Nerfed Focus Regeneration enchant curve so that it no longer generates too much Focus too quickly • Focus Regeneration enchantment no longer drops with Gloves and now only drops with Helmets • This includes enchanting items at Eleanor • Falling Sky and Woodland Protector’s initial item levels were set too high and have been lowered to the intended levels ⚔️ Weapons: • Updated animation for backstabbing with Staves, Spears, Greatswords and Great Hammers • Updated visual effects for Piercing type weapon attacks (such as Spear or Rapier) ⚔️ Enemies and Bosses: • Polished Darak boss fight ⚬ Improved behavior to prevent him standing idle after attacking ⚬ Improved behavior when fighting ranged builds • Added Bite Attack to Plague Rat • Added Back Attack to Risen Axe Bruiser • Added escape logic to Risen Fire Bomber • Added Elemental Affix visual effects to Nith Brute, Nith Screamer and Shackled Brute • Adding cloth simulation to Boarskin Bruiser • Polished rigging on Plagued Boomer • Reduced camera shake intensity on Risen Hammer Bruiser, Boarskin Bruiser and Riven Twins • Smaller enemies can now smash breakable objects (barrels, crates, etc.) ⚔️ NPCs: • Changed the name of the worried woman in the Sacrament Town Square to Nell • Polishing dialog for Druo, Lucian and Everwyn • Updated the dialog for NPCs at the Cerim Gate in Nameless Pass • Added eavesdrop to Sleeping Guard Gerard in Sacrament ⚔️ Areas: • Improved collision, faders and set dressing in Prologue Ship, Orban Glades, Mariner’s Keep, Nameless Pass, Sacrament, Multiple Sacrament Interiors, Cerim Crucible, Cerim Cave, Riven Twins Boss Arena and Potion Seller Cave • Polished lighting for the ship in Prologue, Sacrament and Cerim Crucible • Updated foliage in various locations • Added physics and wind simulation to Spruce trees ⚔️ Cinematics: • Polished animations for characters in the Inquisition Arrival cinematic • Improved lighting, character rim lighting and volumetrics for the Prologue Ship Crash Outro and Inquisition Arrival cinematics • Removed a background character who was blocking part of the view in the Inquisition Arrival cinematic • Fixed cloth and camera pops in the Inquisition Arrival cinematic ⚔️ Audio: • Environment update for Sacrament: ⚬ Added Ambience Emitters for certain Residential and Vendor buildings like the Cook, Tavern, Woodcrafter and Enchantress ⚬ Updated zone beds and oneshots for unique parts of town (Cemetery, Poor Area,Training Grounds, Dasha Sanctuary) ⚬ The church near the cemetery now has bells ringing to service playing at certain times of day, followed by churchgoers praying and chanting from behind the doors. ⚬ Updated ambience for Sacrament Town Square to feel busier during the day ⚬ Updated environment audio for the Cerim Gate zone in Mountain Pass • Increased audio buffer to help alleviate audio crackle artifacts • Increased available audio resources to help prevent sounds from dropping out during long play sessions • Updated audio for Cerim Vision cinematic • Updated audio mix for Barrel and Crate destruction • Saluting Guards in Sacrament now have sound • Added Weapon-specific Impacts on parrying and blocking actions • Added ladder sliding sound effects for Kickdown Ladders • Added sound effects for going down Ladders • Added new sound effects for Plague-Enchanted weapons • Polished audio for Bounties enemies • Fixed missing sounds for Plagued Mutant Soldier • Fixed rain sounds appearing in Sacrament Interiors • Fixed enchantment-specific weapon whooshes cutting a bit too early • Fixed NPCs not making footstep sounds when walking around • Fixed environment states sometimes not resetting when returning to the main menu ⚔️ VFX: • Blood effects are now juicier and used more often! • Improved blood visual effects attachment to characters bodies from attacking and getting hit • Increased intensity of shiny item drop VFX ⚔️ Bounties and Challenges: • Updated Crustacean Conundrum bounty to spawn 14 Crabs while still only requiring 8 Crabs be killed to complete ⚔️ Localization: • Added and updated localized text in many places across multiple languages • Added localization support for new Controller Remapping screen and for various missing localized elements • Fixed incorrect font on the Activities screen ⚔️ Bug Fixes: • Fixed various enchantments on unique weapons and rings that weren’t working properly • Fixed Rested Bonuses for sleeping in beds • Fixed Key Items respawning after pick up • Fixed navigation in Nameless Pass which was preventing certain enemies and the Riven Twins boss from patrolling and moving to the player • Fixed Echo Knight falling off the arena and blocking progress • Fixed Cerim Armor missing upgrades at Filmore • Fixed Risen Pavise, Eye of the Beholder and Wooden Howler Shields not showing their proper models • Fixed SHIFT key not being recognized in the Main Menu • Fixed certain environment textures overriding certain armor textures • Fixed certain armor having missing or incorrect cloth simulation • Fixed rigging on certain armor • Fixed The Wallow boss attacks not having sound effects • Fixed Falling Sky Blueprint not giving the Unique version of the weapon when crafting • Fixed an issue where completed but not yet turned in bounty/challenge rewards were being automatically given to the player at reset • Fixed wall cannons not firing in Cerim Crucible • Fixed XP UI not showing “Max Level” after reaching the level cap • Fixed Level and XP UI being present without a Character selected in the Main Menu • Fixed “Long Area Name” appearing on the map where map is unavailable (such as Cerim Crucible) • Fixed being able to skip through locked doors in The Shallows • Fixed players getting stuck at the end of the entrance corridor in the Echo Knight Arena • Fixed Enchant Item Challenge counting enchanted items that are picked up • Fixed mortuary guard popping in on screen during Spoken and Unspoken quest • Fixed extra Elsa map marker during the Spoken and Unspoken quest • Fixed Giles and Petra standing instead of sitting on the chairs in Caroline’s Inn • Fixed Arrows not hitting Plagued Wolf • Fixed Wolf and Plagued Wolf target point • Fixed Tanth Knight getting stuck during patrolling in Mariner’s Keep at Endgame state • Fixed Darak leaving his shield in Orban Glades when he escapes • Fixed chest opening VFX in Performance and Balanced quality presets • Fixed Wolf having a dance party after death • Fixed Chest floating in the air in Mariner’s Keep • Fixed incorrect texture on the Crafting Table • Fixed 4096x2160 resolution appearing as 256x135 aspect ratio, instead displays as 1.9:1 • Fixed overblown bonfire lighting at The Shallows • Removed rogue rim light at The Shallows • Removed lighting debug shortcut See the full patch notes here -

No Rest for the Wicked

184,300 次观看 • 2 年前

Crimson Desert Update 1.04 is HUGE, adding difficulty settings and more. • Difficulty options added • New pets - birds, 5 new cats, and more • Added new Storage Chests that allow materials and ingredients to be used directly from storage • New weapons, quests, and armor for all 3 playable characters • Improved the rendering quality of distant objects and textures • Can now name your pets and horses • Pets can now equip accessories for a wider variety of roles • Abyss Gears, insects, fish, and animals now stack in inventory • Can now select between different house layouts • Improved housing controls and UI • Observing a skill you already have now rewards an Abyss Artifact • Added a new item that allows cats to stay on your shoulder for a longer time • New weapons for all three playable characters • New Baltheon armor for Kliff • New pet gear shop added to Pororin • Added more ores and wells across Pywell • Nerfed the amount of attack and defense gained from anvils and grindstones • Greymane camp NPCs now sell items at a 10% discount • Can now 'Lock' items to prevent accidental selling or deletion • New control presets for controller and KBM • Added a feature where, when the interaction key is pressed, the corresponding action is performed immediately • Can now switch the controls for Dodge Roll and Evasion • Improved aiming controls • Can now open the map directly on controller by holding down the Touch Pad or View button • Adjusted the overall balance of bosses - bosses are no longer immune while performing powerful attacks and the frequency at which they escape or counterattack has been adjusted • Increased damage taken from elemental status effects • Force Palm Pulse can now be charged up to 3 stages • Improved the overall speed of 'Examine' • Improved the speed of pushing or rotating objects during puzzles • Improved follow-up attacks so they connect more quickly even when the initial attack is blocked • Blinding Flash can now be used anywhere and auto-targets whatever target you're facing • Added a Weapon Throw ability while dual-wielding • Improved Force Palm attack speed • Inventory now has 5 category tabs • Inventory groups will now show relevant icons • Added a Filter/Search to the map • Reaching max trust with a shop will allow you to see their current stock directly from the map • Minimap now shows north, south, east, west • Shops now show how many of that item you own • Improved the visual quality of characters at long distances • Improved hair lighting in shaded areas, errors and flickering • Camera distance is now maintained when adjusting visual range • Can now disable Chromatic Aberration • Added Colorblind and Photosensitive accessibility modes Update is out now on Steam, PS5, and Xbox with other platforms coming soon.
0:33

Crimson Desert Update 1.04 is HUGE, adding difficulty settings and more. • Difficulty options added • New pets - birds, 5 new cats, and more • Added new Storage Chests that allow materials and ingredients to be used directly from storage • New weapons, quests, and armor for all 3 playable characters • Improved the rendering quality of distant objects and textures • Can now name your pets and horses • Pets can now equip accessories for a wider variety of roles • Abyss Gears, insects, fish, and animals now stack in inventory • Can now select between different house layouts • Improved housing controls and UI • Observing a skill you already have now rewards an Abyss Artifact • Added a new item that allows cats to stay on your shoulder for a longer time • New weapons for all three playable characters • New Baltheon armor for Kliff • New pet gear shop added to Pororin • Added more ores and wells across Pywell • Nerfed the amount of attack and defense gained from anvils and grindstones • Greymane camp NPCs now sell items at a 10% discount • Can now 'Lock' items to prevent accidental selling or deletion • New control presets for controller and KBM • Added a feature where, when the interaction key is pressed, the corresponding action is performed immediately • Can now switch the controls for Dodge Roll and Evasion • Improved aiming controls • Can now open the map directly on controller by holding down the Touch Pad or View button • Adjusted the overall balance of bosses - bosses are no longer immune while performing powerful attacks and the frequency at which they escape or counterattack has been adjusted • Increased damage taken from elemental status effects • Force Palm Pulse can now be charged up to 3 stages • Improved the overall speed of 'Examine' • Improved the speed of pushing or rotating objects during puzzles • Improved follow-up attacks so they connect more quickly even when the initial attack is blocked • Blinding Flash can now be used anywhere and auto-targets whatever target you're facing • Added a Weapon Throw ability while dual-wielding • Improved Force Palm attack speed • Inventory now has 5 category tabs • Inventory groups will now show relevant icons • Added a Filter/Search to the map • Reaching max trust with a shop will allow you to see their current stock directly from the map • Minimap now shows north, south, east, west • Shops now show how many of that item you own • Improved the visual quality of characters at long distances • Improved hair lighting in shaded areas, errors and flickering • Camera distance is now maintained when adjusting visual range • Can now disable Chromatic Aberration • Added Colorblind and Photosensitive accessibility modes Update is out now on Steam, PS5, and Xbox with other platforms coming soon.

KAMI

535,500 次观看 • 4 个月前

Obsidian 1.8.3 is now available to all for desktop and mobile! - Web viewer. New core plugin lets you open external links within Obsidian on desktop. This makes it easier to read linked content without leaving the app and improves multitasking for web research. The plugin can be enabled manually in settings. - Improved iCloud sync. Obsidian no longer waits to confirm that configuration files have synced. - New mobile onboarding. This guided flow helps new mobile users create and sync a vault. - New "Download attachments for current file" command. Downloads all externally embedded images and replaces the external links with internal embeds. A few notable improvements: - When modifying a numbered list, the numbers are now updated automatically. - Pressing Enter in a multi-line list item now continues the list properly. - New "Insert footnote" command. Footnote autocomplete now provides a fallback to create a new footnote if no match is found. - Tags view now includes search. - File Explorer now includes an option to automatically reveal the active file. - Outline now has an "Auto-scroll to current section" option. - Sync now has a new view option, "Hide my changes," which hides your own file changes in a shared Obsidian sync vault. - Recently used commands now appear at the top of the command palette. - "Search current file" search bar now displays the total number of results. - "Insert template" command now sorts templates by file path and displays folder names. - , , and tags with relative src paths are now rendered in Live Preview and Reading mode. - Graph view no longer considers Canvas files as attachments. See the changelog for dozens more improvements and bug fixes.
0:41

Obsidian 1.8.3 is now available to all for desktop and mobile! - Web viewer. New core plugin lets you open external links within Obsidian on desktop. This makes it easier to read linked content without leaving the app and improves multitasking for web research. The plugin can be enabled manually in settings. - Improved iCloud sync. Obsidian no longer waits to confirm that configuration files have synced. - New mobile onboarding. This guided flow helps new mobile users create and sync a vault. - New "Download attachments for current file" command. Downloads all externally embedded images and replaces the external links with internal embeds. A few notable improvements: - When modifying a numbered list, the numbers are now updated automatically. - Pressing Enter in a multi-line list item now continues the list properly. - New "Insert footnote" command. Footnote autocomplete now provides a fallback to create a new footnote if no match is found. - Tags view now includes search. - File Explorer now includes an option to automatically reveal the active file. - Outline now has an "Auto-scroll to current section" option. - Sync now has a new view option, "Hide my changes," which hides your own file changes in a shared Obsidian sync vault. - Recently used commands now appear at the top of the command palette. - "Search current file" search bar now displays the total number of results. - "Insert template" command now sorts templates by file path and displays folder names. - , , and tags with relative src paths are now rendered in Live Preview and Reading mode. - Graph view no longer considers Canvas files as attachments. See the changelog for dozens more improvements and bug fixes.

Obsidian

118,904 次观看 • 1 年前

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!
0:53

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Akshay 🚀

87,048 次观看 • 4 个月前

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.
1:15

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.

Rohan Paul

33,431 次观看 • 6 个月前

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.
1:18

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,540 次观看 • 3 个月前

The Visual Studio Code insiders version that just shipped and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.
0:24

The Visual Studio Code insiders version that just shipped and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.

Oren Melamed

29,555 次观看 • 8 个月前

This Chinese guy created agents in Claude Code for MCP servers and single-handedly serves 6 marketing agencies a month from one iPhone, earning $5,000 from each. Inside he runs a pipeline of 7 agents on Claude Sonnet 4.6 that every Monday pulls a scan of the tech stack from a selected agency, develops an MCP server for its ad accounts, and over the course of a week brings it to production code ready to connect to Claude Desktop. No DevOps, no senior developer, no project manager. Just a Mac Mini in a work corner, an iPhone in the pocket, and a single API key. And traditional dev shops keep 5 people on project rates for the same contract, while his entire P&L is tokens, dirt-cheap hosting on Cloudflare, and Calendly. 7 agents run under a shared orchestrator-router and burn about 5 million tokens a day, which in the API bill comes out to $540 a month. The Mac Mini itself sits at home and keeps the entire orchestrator running 24/7, and from the iPhone the owner connects to it through a secure remote terminal and sees the output of any session right on the smartphone screen, wherever he happens to be. His starting system prompt looks like this: "you run a solo shop for custom MCP servers for marketing agencies. you hand out read-only tasks to 6 sub-agents and own all commits and shipping yourself. sub-agents: // Hunter (finds marketing agencies of 15 to 60 people that have no MCP access to Google Ads, Meta Ads, TikTok Ads, and HubSpot) // Mapper (pulls their tech stack, identifies 3 to 5 integration pains, and simultaneously writes the technical spec for the server: which tools, resources, and prompts to export through MCP, which auth flow and rate limit) // Coder (generates an MCP server in Python through the MCP SDK, deploys 8 to 15 tools for ad accounts and CRM) // Validator (connects the server to Claude Desktop, runs real client API keys in a sandbox, and checks for compliance with the MCP spec) // Shipper (writes a README, integration guide, deployment manual, packages the server, and hosts it on Cloudflare Workers or pushes to the GitHub of the client) // Mobile (always online on the iPhone, books demo calls in Calendly, picks up hot fixes, and confirms contracts through a secure remote terminal to the Mac Mini). only 1 owner agent works on 1 contract, no overlaps. you pull the owner out of observation mode only when a deal goes above $7,500 or the test coverage of the server drops below 85%." This prompt gives the system an understanding of its role and the limits of intervention from the very first line. It knows it is supposed to find agencies on its own. It knows it is supposed to bring every MCP server to production on its own. It knows it connects the live owner only on large deals or when the tests do not converge. → The pipeline runs without breaks, day or night → Hunter goes through about 130 marketing agencies on LinkedIn and Clutch per day → Mapper rolls out 4 audit reports with the tech stack and a final spec for each → Coder writes 1 to 2 MCP servers per week in Python with 8 to 15 tools → Validator validates every server through Claude Desktop with real client API keys → Shipper rolls out the full documentation package and pushes the finished product to Cloudflare Workers or the GitHub of the client And only when a contract breaks $7,500 or test coverage drops below 85% does the orchestrator pull the owner from whatever he is doing. And when the owner at that moment is behind the wheel or at a meeting in a coworking space, the Mobile agent in his iPhone picks up 1 contract in progress: confirms a meeting with the agency CMO in Calendly, opens a live demo of the MCP server through a secure terminal to the Mac Mini, and writes the test result to the shared state. The owner just swipes "approve" and in 15 minutes joins the Zoom demo. The fresh system log from last Wednesday looks like this: "hunter report: 132 agencies checked on LinkedIn and Clutch, 19 without MCP integrations, 8 with active requests for AI tooling in job posts, 4 with an open Q4 budget. passing to mapper." "coder: MCP server for Northwave Performance Marketing built in Python, 11 tools for Google Ads, Meta Ads, and GA4, 320 lines of code. exported to /Users/dev/mcp-shop/clients/northwave/server.py. validator connecting to Claude Desktop." "validator: 11 tools passed validation through Claude Desktop, test coverage 92%, average latency 380 ms. passing to shipper." "eval flag: contract with Pacific Reach Agency at $8,200 exceeds the approved limit of $7,500. sending for manual review." In his work setup there is no cloud server, no external team, and not even a separate office. At home sits a Mac Mini with a sandbox at /Users/dev/mcp-shop, on top runs an MCP router with a single API key to Claude, and the same key is forwarded to a secure terminal on the iPhone. Out of everything I have seen this year, this is the cleanest solo shop for custom MCP servers for marketing agencies: $540 a month on the API, about $30,000 into the account, and between them 7 system prompts, 1 Mac Mini in a work corner, and 1 iPhone that never leaves the pocket.
0:33

This Chinese guy created agents in Claude Code for MCP servers and single-handedly serves 6 marketing agencies a month from one iPhone, earning $5,000 from each. Inside he runs a pipeline of 7 agents on Claude Sonnet 4.6 that every Monday pulls a scan of the tech stack from a selected agency, develops an MCP server for its ad accounts, and over the course of a week brings it to production code ready to connect to Claude Desktop. No DevOps, no senior developer, no project manager. Just a Mac Mini in a work corner, an iPhone in the pocket, and a single API key. And traditional dev shops keep 5 people on project rates for the same contract, while his entire P&L is tokens, dirt-cheap hosting on Cloudflare, and Calendly. 7 agents run under a shared orchestrator-router and burn about 5 million tokens a day, which in the API bill comes out to $540 a month. The Mac Mini itself sits at home and keeps the entire orchestrator running 24/7, and from the iPhone the owner connects to it through a secure remote terminal and sees the output of any session right on the smartphone screen, wherever he happens to be. His starting system prompt looks like this: "you run a solo shop for custom MCP servers for marketing agencies. you hand out read-only tasks to 6 sub-agents and own all commits and shipping yourself. sub-agents: // Hunter (finds marketing agencies of 15 to 60 people that have no MCP access to Google Ads, Meta Ads, TikTok Ads, and HubSpot) // Mapper (pulls their tech stack, identifies 3 to 5 integration pains, and simultaneously writes the technical spec for the server: which tools, resources, and prompts to export through MCP, which auth flow and rate limit) // Coder (generates an MCP server in Python through the MCP SDK, deploys 8 to 15 tools for ad accounts and CRM) // Validator (connects the server to Claude Desktop, runs real client API keys in a sandbox, and checks for compliance with the MCP spec) // Shipper (writes a README, integration guide, deployment manual, packages the server, and hosts it on Cloudflare Workers or pushes to the GitHub of the client) // Mobile (always online on the iPhone, books demo calls in Calendly, picks up hot fixes, and confirms contracts through a secure remote terminal to the Mac Mini). only 1 owner agent works on 1 contract, no overlaps. you pull the owner out of observation mode only when a deal goes above $7,500 or the test coverage of the server drops below 85%." This prompt gives the system an understanding of its role and the limits of intervention from the very first line. It knows it is supposed to find agencies on its own. It knows it is supposed to bring every MCP server to production on its own. It knows it connects the live owner only on large deals or when the tests do not converge. → The pipeline runs without breaks, day or night → Hunter goes through about 130 marketing agencies on LinkedIn and Clutch per day → Mapper rolls out 4 audit reports with the tech stack and a final spec for each → Coder writes 1 to 2 MCP servers per week in Python with 8 to 15 tools → Validator validates every server through Claude Desktop with real client API keys → Shipper rolls out the full documentation package and pushes the finished product to Cloudflare Workers or the GitHub of the client And only when a contract breaks $7,500 or test coverage drops below 85% does the orchestrator pull the owner from whatever he is doing. And when the owner at that moment is behind the wheel or at a meeting in a coworking space, the Mobile agent in his iPhone picks up 1 contract in progress: confirms a meeting with the agency CMO in Calendly, opens a live demo of the MCP server through a secure terminal to the Mac Mini, and writes the test result to the shared state. The owner just swipes "approve" and in 15 minutes joins the Zoom demo. The fresh system log from last Wednesday looks like this: "hunter report: 132 agencies checked on LinkedIn and Clutch, 19 without MCP integrations, 8 with active requests for AI tooling in job posts, 4 with an open Q4 budget. passing to mapper." "coder: MCP server for Northwave Performance Marketing built in Python, 11 tools for Google Ads, Meta Ads, and GA4, 320 lines of code. exported to /Users/dev/mcp-shop/clients/northwave/server.py. validator connecting to Claude Desktop." "validator: 11 tools passed validation through Claude Desktop, test coverage 92%, average latency 380 ms. passing to shipper." "eval flag: contract with Pacific Reach Agency at $8,200 exceeds the approved limit of $7,500. sending for manual review." In his work setup there is no cloud server, no external team, and not even a separate office. At home sits a Mac Mini with a sandbox at /Users/dev/mcp-shop, on top runs an MCP router with a single API key to Claude, and the same key is forwarded to a secure terminal on the iPhone. Out of everything I have seen this year, this is the cleanest solo shop for custom MCP servers for marketing agencies: $540 a month on the API, about $30,000 into the account, and between them 7 system prompts, 1 Mac Mini in a work corner, and 1 iPhone that never leaves the pocket.

Blaze

55,926 次观看 • 4 个月前

A little look behind the scenes: Many of you asked how I handle switching from SwiftData & CloudKit to Firebase and a different way of sharing entries with your friends. Previously, there was no need to create an account and the app just used the user's iCloud ID in the background to "sign up". Why did I do this? SwiftData is really nice to use but after working with it for over a year now, it feels still quite unstable, buggy and errors are super hard to track. Same goes for CloudKit and the CloudKit sharing that I implemented. For a growing app, in my opinion, it's just not feasible to use because errors happen regularly, you don't really know if the data is stored (and shared) correctly and the documentation on CK is just bad. I have big plans for this app (reacting to your friends' entries, Apple Health integration, tagging multiple friends in entries etc.) and all of it is now much simpler - and faster to build. The Migration part When an existing user starts the app, a little migration sheet with a couple of steps opens which can't be dismissed. The goal is that the user maintains all entries and can use the app like before :) Steps: 1) Create an Account using Apple Sign In and Firebase Auth 2) Migrate your user profile (profile picture etc.) and all your friends from SwiftData to Firestore. Here I basically iterate over all the data that is there, run a custom conversion for all the fields (some things need to be stored differently) and save them. Profile Images are now saved in Firebase Storage 3) Migrate all entries to Firestore the same way. Images and Voice Notes are now saved in Firebase Storage (that might take a bit of time, video is sped up) 4) After that, migration is basically done and the user can use the app like before. In the settings, the user can now log out or delete the account, things that weren't possible before. If for any reason the migration has to be done again, this can be triggered from the settings as well. How do I decide if a user needs to migrate? Previously, I saved the user's profile in SwiftData under a specific key (simplified). If the app finds something under this key, user is prompted for a migration. New users don't have to run through the migration. They simply start fresh with the Apple Sign in in the onboarding like seen in the referenced post. How does sharing entries now work? For sharing, I create deeplinks using branch . io now. These links basically work like every other Invite Link you've received or created. The friend opens the link, can accept your invitation and now both of you are connected as buddies. Previously using CloudKit Sharing, this process took two steps - each user had to share a link to give access to their entries. The process now is much simpler and better understand for the user. Developing the migration Tbh I thought this would be way quicker. In the end it was > 100 commits since I had to basically change every screen in the app. Working with SwiftData is quite different to how things work with Firebase (and most other frameworks), so every interaction where data was involved had to be reworked. Now the app runs on a combination of Firestore, Cloud Functions and Firebase Storage. In terms of memory, the app feels notably faster and only needs around 1/4 of the memory bandwidth it needed before. Let's see if it will be worth it! All in all super happy with the new flexibility for the app and not being limited by the technology anymore 👀
0:44

A little look behind the scenes: Many of you asked how I handle switching from SwiftData & CloudKit to Firebase and a different way of sharing entries with your friends. Previously, there was no need to create an account and the app just used the user's iCloud ID in the background to "sign up". Why did I do this? SwiftData is really nice to use but after working with it for over a year now, it feels still quite unstable, buggy and errors are super hard to track. Same goes for CloudKit and the CloudKit sharing that I implemented. For a growing app, in my opinion, it's just not feasible to use because errors happen regularly, you don't really know if the data is stored (and shared) correctly and the documentation on CK is just bad. I have big plans for this app (reacting to your friends' entries, Apple Health integration, tagging multiple friends in entries etc.) and all of it is now much simpler - and faster to build. The Migration part When an existing user starts the app, a little migration sheet with a couple of steps opens which can't be dismissed. The goal is that the user maintains all entries and can use the app like before :) Steps: 1) Create an Account using Apple Sign In and Firebase Auth 2) Migrate your user profile (profile picture etc.) and all your friends from SwiftData to Firestore. Here I basically iterate over all the data that is there, run a custom conversion for all the fields (some things need to be stored differently) and save them. Profile Images are now saved in Firebase Storage 3) Migrate all entries to Firestore the same way. Images and Voice Notes are now saved in Firebase Storage (that might take a bit of time, video is sped up) 4) After that, migration is basically done and the user can use the app like before. In the settings, the user can now log out or delete the account, things that weren't possible before. If for any reason the migration has to be done again, this can be triggered from the settings as well. How do I decide if a user needs to migrate? Previously, I saved the user's profile in SwiftData under a specific key (simplified). If the app finds something under this key, user is prompted for a migration. New users don't have to run through the migration. They simply start fresh with the Apple Sign in in the onboarding like seen in the referenced post. How does sharing entries now work? For sharing, I create deeplinks using branch . io now. These links basically work like every other Invite Link you've received or created. The friend opens the link, can accept your invitation and now both of you are connected as buddies. Previously using CloudKit Sharing, this process took two steps - each user had to share a link to give access to their entries. The process now is much simpler and better understand for the user. Developing the migration Tbh I thought this would be way quicker. In the end it was > 100 commits since I had to basically change every screen in the app. Working with SwiftData is quite different to how things work with Firebase (and most other frameworks), so every interaction where data was involved had to be reworked. Now the app runs on a combination of Firestore, Cloud Functions and Firebase Storage. In terms of memory, the app feels notably faster and only needs around 1/4 of the memory bandwidth it needed before. Let's see if it will be worth it! All in all super happy with the new flexibility for the app and not being limited by the technology anymore 👀

Fabian Gruß

26,781 次观看 • 1 年前

142 people downloaded my Hermes Bots mobile app 43 of you sent feedback. I implemented all of it. I respect Nous Research and I don't want to get in any conflict. With that said... The app has a new name and icon: Herald, Companion for Hermes Agent. Still my unofficial app, now a lot closer to what you asked for. Here’s what changed 👇 Setup is much easier Run npx herald-setup on your computer. It configures Hermes, Tailscale, and a password. Scan the QR code and connect. You can also enter a Tailscale name, IP, or domain. Herald handles port and HTTPS detection. Pairing the same machine again updates it instead of creating duplicates, and the app handles signing back in after authentication errors. All your Bots in one place Connect multiple computers and see their Bots in one roster. Search across Bots, groups, and machines, with indicators showing who’s awake, working, or offline. Start a session in Telegram, your terminal, or Hermes Desktop and continue from your phone. Bots on different machines can join the same group, and the Kanban board now has activity badges. Photos, video, and audio inside the conversation Attach photos and they stay in the thread as thumbnails, even after you reopen the chat. An SVG your Bot drew, an MP3 it recorded, or a video it rendered now appears inline instead of as a file path. Tap to view full screen, share, or play directly in the chat. Media comes from your own Hermes and is cached on your phone. A much better chat experience Select and copy messages, copy code blocks with one tap, and preview HTML or SVG without leaving the conversation. Voice notes and dictation run through your own Hermes. On Android, long code blocks no longer trap your scrolling, and the keyboard no longer covers the message box. Make it yours Choose an accent color for your send button and your own message bubbles: graphite, slate, blue, green, purple, orange, or the original black and white. Dark mode stays the default, with light mode available too. Every iOS menu now uses a native pull down, and plugin switches reflect what’s actually running on your computer. Android is here 🎉 The roster loads even when Hermes is slow, and screens recover from errors instead of crashing the app. Push notifications are also wired up for both iOS and Android. Three days ago, this was an app I built for myself. Your feedback is helping turn it into something useful for everyone. Thank you for testing it and telling me what needed fixing ❤️ I’m now starting the store submission process for iOS and Android
1:34

142 people downloaded my Hermes Bots mobile app 43 of you sent feedback. I implemented all of it. I respect Nous Research and I don't want to get in any conflict. With that said... The app has a new name and icon: Herald, Companion for Hermes Agent. Still my unofficial app, now a lot closer to what you asked for. Here’s what changed 👇 Setup is much easier Run npx herald-setup on your computer. It configures Hermes, Tailscale, and a password. Scan the QR code and connect. You can also enter a Tailscale name, IP, or domain. Herald handles port and HTTPS detection. Pairing the same machine again updates it instead of creating duplicates, and the app handles signing back in after authentication errors. All your Bots in one place Connect multiple computers and see their Bots in one roster. Search across Bots, groups, and machines, with indicators showing who’s awake, working, or offline. Start a session in Telegram, your terminal, or Hermes Desktop and continue from your phone. Bots on different machines can join the same group, and the Kanban board now has activity badges. Photos, video, and audio inside the conversation Attach photos and they stay in the thread as thumbnails, even after you reopen the chat. An SVG your Bot drew, an MP3 it recorded, or a video it rendered now appears inline instead of as a file path. Tap to view full screen, share, or play directly in the chat. Media comes from your own Hermes and is cached on your phone. A much better chat experience Select and copy messages, copy code blocks with one tap, and preview HTML or SVG without leaving the conversation. Voice notes and dictation run through your own Hermes. On Android, long code blocks no longer trap your scrolling, and the keyboard no longer covers the message box. Make it yours Choose an accent color for your send button and your own message bubbles: graphite, slate, blue, green, purple, orange, or the original black and white. Dark mode stays the default, with light mode available too. Every iOS menu now uses a native pull down, and plugin switches reflect what’s actually running on your computer. Android is here 🎉 The roster loads even when Hermes is slow, and screens recover from errors instead of crashing the app. Push notifications are also wired up for both iOS and Android. Three days ago, this was an app I built for myself. Your feedback is helping turn it into something useful for everyone. Thank you for testing it and telling me what needed fixing ❤️ I’m now starting the store submission process for iOS and Android

Luke The Dev

60,585 次观看 • 7 天前

It is done! Grok has literally built something that no one else has but anyone studying space weather would want! I will be releasing it today to the world on my website for free , and as open source for anyone to tweak, add or change things as they see fit! First we managed to resurrect the old Japanese NICT magnetosphere monitoring page, getting all the original data... then, added in the SOLAR-1 Data, and the data from the BOM Australia on the Magnetopause (shell around earth that bounces around). The magnetic field lines of the magnetoSPHERE coming from the ACE and Solar-1 data, and the bouncing shell of the magnetopause from the BOM, then we added in the Schumann resonance, to give each magnetic field line from the ACE and Solar-1 data an oscillating glow that lights up according to the current Hz of the Schumann. There is an option to turn on charged particles, which will then reflect off of , or be pulled in towards (or stay neutral) to the magnetic field of both the ACE + Solar-1 field LINES and the outer shell magnetopause from the BOM!!!! This is huge! When Bz goes green one way the particles turn RED and are reflected off of Earths magnetic field like a force field.. and when Bz goes Red, the particles turn GREEN and are accepted in to Earths fields! When neutral positive you see light blue and when neutral negative the particles are grey. Simply put, you can now look at this and know just by the particle color and their direction whether Earth was accepting or denying particle absorption!!!! Nowhere in the world has anyone put anything like this together into one model. Now we have it! All of these are toggleable on and off, so each one can be viewed on or off at any time. Also added multiple types of lighting and graphics controls , so that the user can control the amount of lighting, glow, thickness of the field lines when displayed, and the amount of the flashes per second using the Schumann hz filter, as well as the amount of brightness of each flash. Can go anywhere from 7hz up to 40+hz just like the actual Schumann resolance. You can also turn on "manual control" so that you can simulate "what would happen if" solar wind went up high or if the hz rate of the Schumann were to spike what it would look like magnetically on the spherical display of the magnetic field. Finally a record option was built in to allow for recording of movies in the program, which I have uploaded here now. Not the highest quality yet, but I figure people will use screen capture programs instead of this if they're making movies (this is fine for public use as is now imo). Also added in color controls for the background (default set to black) and for the magnetic field lines which default to Red and Blue just like the old NICT Japanese site which got shut down years ago.
2:41

It is done! Grok has literally built something that no one else has but anyone studying space weather would want! I will be releasing it today to the world on my website for free , and as open source for anyone to tweak, add or change things as they see fit! First we managed to resurrect the old Japanese NICT magnetosphere monitoring page, getting all the original data... then, added in the SOLAR-1 Data, and the data from the BOM Australia on the Magnetopause (shell around earth that bounces around). The magnetic field lines of the magnetoSPHERE coming from the ACE and Solar-1 data, and the bouncing shell of the magnetopause from the BOM, then we added in the Schumann resonance, to give each magnetic field line from the ACE and Solar-1 data an oscillating glow that lights up according to the current Hz of the Schumann. There is an option to turn on charged particles, which will then reflect off of , or be pulled in towards (or stay neutral) to the magnetic field of both the ACE + Solar-1 field LINES and the outer shell magnetopause from the BOM!!!! This is huge! When Bz goes green one way the particles turn RED and are reflected off of Earths magnetic field like a force field.. and when Bz goes Red, the particles turn GREEN and are accepted in to Earths fields! When neutral positive you see light blue and when neutral negative the particles are grey. Simply put, you can now look at this and know just by the particle color and their direction whether Earth was accepting or denying particle absorption!!!! Nowhere in the world has anyone put anything like this together into one model. Now we have it! All of these are toggleable on and off, so each one can be viewed on or off at any time. Also added multiple types of lighting and graphics controls , so that the user can control the amount of lighting, glow, thickness of the field lines when displayed, and the amount of the flashes per second using the Schumann hz filter, as well as the amount of brightness of each flash. Can go anywhere from 7hz up to 40+hz just like the actual Schumann resolance. You can also turn on "manual control" so that you can simulate "what would happen if" solar wind went up high or if the hz rate of the Schumann were to spike what it would look like magnetically on the spherical display of the magnetic field. Finally a record option was built in to allow for recording of movies in the program, which I have uploaded here now. Not the highest quality yet, but I figure people will use screen capture programs instead of this if they're making movies (this is fine for public use as is now imo). Also added in color controls for the background (default set to black) and for the magnetic field lines which default to Red and Blue just like the old NICT Japanese site which got shut down years ago.

Dutchsinse

14,548 次观看 • 27 天前