Codex CLI Update: Let there be Search Whatup nerds,... back so soon looking or yet ANOTHER update?! I got you. Update 0.121.0 is here! > You can now search through previous user prompts with CTRL+R. Just trigger search and enter your search string, you can easily arrow through all matches. See video below! > 🥔 Support for Spud! Is not here yet. Sorry. Maybe tomorrow. 🫢 > v0.121.0 adds custom marketplace installs in Codex: you can run codex marketplace add to register marketplaces from GitHub shorthand, git URLs, or local directories. Codex validates the marketplace layout and stores it in your user config so it shows up consistently in plugin discovery. > Improved memory features, including a new /memories TUI menu with use/generate toggles, a reset-all-memories action, app-server support for setting thread memory mode and clearing memories, and cleanup of stale memory-extension resources. Note: Not working on Linux for me. /memories command unavailable. > Codex MCP got further upgrades with direct app tool calls, cleaner namespacing, and safe optional parallel execution for faster workflows > Codex realtime got better controls (text/audio + clear “done” signals), easier history syncing, and safer file handling. > Hardened devcontainer setup plus smarter macOS socket allowlists for safer local runtime access. > Dozens of other bug fixes, see repo below. Toodles! ✌️show more

Released SuperCmd 1.0.8 🚀 biggest udpate so far! 📅... First Class Support for Calendar, Meeting reminders, with join meeting notifications before meeting 📔 You can now Sync SuperCmd Notes with Obsidian, with custom folder for notes ✨ Improved AI chat & Quick AI experience 📞 Search Contacts command 🧩 Custom Extension Support ⌨️ Auto switch Keyboard Layout Key updates 💫 > Notes: Hotkey and alias support for each note > Custom save location for screenshots > Custom search scopes (paths) for App indexing > Alt + Tab can now show apps from all spaces > Master switches for every module / command (screenshot, terminal, extensions, system settings, system commands, window mgmt) > Better support for Pinyin layout > Window Management: Window Gap support, New commands Minizmie, Zoom, Two Thirds > Text (OCR) search in screenshot history > Option to select primary action in clipboard (copy, paste to active app) > Here is the corrected text: > Exhaustive set of options for Dictation models via Open Router > Esc key support for hotkeys > Option to choose what happens when screenshot is taken (open editor / copy to clipboard) > DMG is now 22 -> 15mb > Bunch of enhacments and Bug fixes complete changelog: If you are looking to repalce Raycast with native alternative, try out SuperCmd. 50mb on disk, ~150mb memory usageshow more

HTML Artifacts are a big part of how I... work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:show more

CCleaner used to be the default way to keep... a Windows machine fast. Then it got bought, stuffed with ads and bundled crapware, and in 2017 one release was compromised and shipped malware to over 2 million people. Millions still install it every month because nothing else has really replaced it. So, a team called AdventDev just built a free, open-source replacement. It's called Kudu. Open the app and you get one dashboard for the whole machine. > System cleaner for temp files, logs, caches, and crash dumps. > Browser cleaner across every major browser. > Gaming cleaner for launcher and shader caches. > Registry cleaner for broken and orphaned entries. > Startup manager that shows the actual boot impact of each program. > Disk analyzer with an interactive treemap, so you can see where 40GB quietly disappeared to. > Debloater that rips Windows bloatware out. > Program uninstaller that also removes the leftovers other uninstallers leave behind. Then it does the parts CCleaner never did. A malware scanner with signature matching, heuristic analysis, and Windows Defender integration. A privacy shield that lets you flip 30+ Windows privacy settings from one screen: telemetry, ad ID, Cortana, tracking. Secure delete that overwrites files with random data before removing them, so nothing can recover them later. There's a real-time performance monitor with per-core CPU, memory, disk, network, and S.M.A.R.T. drive health. A one-click restore point before every clean, so you can roll back. Scheduled scans. A CLI mode for people who don't want a GUI. Support for 30 languages. Native app for Windows, macOS, and Linux. Intel and Apple Silicon builds. No ads, no upsells, no telemetry, no account. The cleaning rules are plain JSON files, so if your favorite app isn't covered yet, you can add support for it without writing a line of code. MIT license. 100% Open Source. Repo:show more

Boom! Grok Tasks Make It One Of The Most... POWERFUL Real-Time AI Systems In The World. — My How to Use Grok Tasks With Hidden Tools For Powerful Daily Output. Grok Tasks are customizable AI workflows that integrate a variety of tools to streamline daily activities, from research and analysis to creative planning and problem-solving. I have been using them for quite sometime and because of the vital heartbeat of news and first person data on X, it is the most powerful AI platform available. By combining Tasks with tools like web searches, X platform interactions, code execution, and media viewers, you can build efficient, automated processes. These tasks work by prompting Grok with a clear description of what you want to achieve, and Grok will intelligently call the necessary tools in sequence or parallel to deliver results. Here's a step-by-step guide to creating and using Grok Tasks: Step 1: Define Your Task Start by clearly outlining the daily activity or goal. Consider what inputs you have (e.g., a URL, a query, or an attachment) and what output you need (e.g., a summary, calculation, or visual analysis). Break it down into subtasks to identify tool needs. For example, if your task involves researching current events, note that you'll need search and browsing capabilities. Step 2: Review Available Tools Familiarize yourself with the tools Grok can access. Here's a quick overview: - Code Execution: Run Python code for calculations, data processing, or simulations using libraries like numpy, pandas, or sympy. - Browse Page: Fetch and summarize content from any website URL with custom instructions. - Web Search: Perform general internet searches, returning results with optional operators like site:. - Web Search With Snippets: Get quick, detailed excerpts from search results for fact-checking. - X Keyword Search: Advanced search for X posts using operators like from:, since:, or filter:. - X Semantic Search: Find semantically related X posts based on a query, with filters for dates or users. - X User Search: Locate X users by name or handle. - X Thread Fetch: Retrieve a full X post thread, including context like replies and parents. - View Image: Analyze an image from a URL or conversation ID. - View X Video: Extract frames and subtitles from an X-hosted video. - Search PDF Attachment: Query a PDF file for relevant pages using keyword or regex modes. - Browse PDF Attachment: View specific pages of a PDF with text and screenshots. Select tools that align with your task. Aim for a mix to handle data gathering, processing, and visualization. Step 3: Craft Your Prompt Write a detailed prompt to Grok describing the task. Include: - The overall goal. - Specific steps or subtasks. - References to tools if you want to guide the process (e.g., "Use web_search to find sources, then code_execution to analyze data"). - Any constraints, like dates or limits. Example prompt: "Create a Grok Task for my morning routine: Search recent X posts about tech news using x_keyword_search, fetch a key thread with x_thread_fetch, and summarize with browse_page on linked articles." Step 4: Submit and Interact Send your prompt to Grok. It will process the task by calling tools as needed, often in parallel for efficiency. Review the output and refine with follow-up prompts if required (e.g., "Expand on that using view_image for visuals"). Iterate to fine-tune the workflow for reuse. Step 5: Save and Reuse Once refined, note the prompt as a template for future use. You can adapt it for similar tasks, making Grok Tasks a habitual part of your day. Finding Grok Tasks To discover existing Grok Tasks or inspiration for new ones, use X searches with tools like x_keyword_search or x_semantic_search (e.g., query: "Grok Tasks examples" with mode: Latest). Browse community-shared threads via x_thread_fetch, or web_search for tutorials on xAI features. Prompt Grok directly: "Show me popular Grok Tasks for productivity." 1 of 3show more

Stateless History Node is almost like a regular Ethereum... node, but it doesn't store state and it doesn't have EVM execution. It's used only for syncing events and thus - is faster and gives you FREE INDEXING. You don't have to pay 6 figures for RPC anymore! Just spin up a Stateless History Node, plug rindexer or Ponder there, and enjoy free (AND FAST!!) indexing! This node is syncing >1000 blocks per second at my local pc (less than 6hrs for the whole Ethereum), and it should use less than 200GB - which means you can host it on a MacMini, Hetzner or whatever. You can futhermore filter that by using block ranges or bloom filters, etc - I haven't developed this yet. What you see is a proof of concept. It works via native devp2p 'eth' protocol, but with EIP4444 and The Prune we would have to also support era1 archives and Portal Network. But so far it works - there are plenty of peers serving historical receipts, and they serve them FAST! If you run Stateless History Node you can also serve the blocks and receipts - so that could help to preserve archival data too. For now there is no data validation yet (and even no data storage - that's a very early PoC), but we can verify validity of chain by simultaneously running a lightweight CL node (or not lightweight if you're extremely paranoid). And then support verifying the hashes of receipts and blocks with their parents, maintaining full integrity and zero trust. It's also written in rust, btw. So, I guess, at least for Ethereum Mainnet the era of RPC's pumping moneybags is over - there's finally a local, trustless and free indexing alternative available. Too sad this won't work for Optimism / Base , cause despite introducing P2P after Bedrock - they haven't enabled receipts transfer in the protocol (or at least I couldn't find one). Arbitrum is even sadder - I don't believe there is a P2P layer at all - you just have to run your own node, hold state and execute blocks to get events. There is hope - Paradigm recently released Ress - stateless execution, but it requires nodes to support Witness preparation & exchange - but this could work for L2s - cause the main blocker for local RPCs rn is huge state (VPS with TB storage cost a lot), and the second blocker is EVM forks makes it hard to hold a node - it needs to be maintained, upgraded, etc. Ress at least solves the state part. But anyways, I will try to continue working on this and release some MVP version with RPC endpoint and data storage soon - follow the updates!show more

I went a little overboard with Codex last week... and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.show more

Introducing fx, a tiny, open, native coding agent from... Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑show more

Introducing a new tool called "SideChannel". A secure alternative... to OpenClaw. Utilizes signal for communication and has Claude integration. I built SideChannel, an open-source Signal bot that connects Claude AI to your entire development workflow. End-to-end encrypted. From your pocket. The real power is autonomous development. Send one message like "Build a REST API with auth, pagination, and tests" and SideChannel will: - Generate a full PRD with stories and atomic tasks. - Dispatch up to 10 parallel workers (each running Claude). - Independently verify every task with a separate Claude context. - Run quality gates to catch regressions - Auto-fix failures. - Send you progress updates via Signal as work completes. Every piece of code is reviewed by a separate AI context using a fail-closed security model. If it detects security issues, backdoors, or logic errors — the code gets rejected automatically. No rubber stamps. It also has memory that actually works. Conversations are stored with vector embeddings for semantic search. Claude remembers your project conventions, past decisions, and what's been tried before. It gets smarter about your codebase over time. Other things I'm proud of: - Plugin framework for extending with custom commands. - Multi-project support with per-user scoping. - Rate limiting, path validation, phone allowlist. - Git checkpoints before every task, atomic commits after. - Stale task recovery, circular dependency detection. - Works on Linux and macOS, one-command install. It also integrates into OpenAI or Grok (optional) for more Generative AI response for simple things like "Whats the weather in New York City right now?".show more

today was the first time i was genuinely impressed... with what AI can do i recently decided to buy a whole FPV drone setup knowing basically nothing about the hardware side of it there's a pretty steep learning curve even just to set everything up properly: radios, RF protocols, flight controllers, ESCs, firmware, batteries, goggles, betaflight configs etc as someone that spends essentially 12h a day prompting agents to build software, it's actually pretty rare that i interact with AI on something where i have zero idea what's going on under the hood, and i never really used it for debugging a bunch of physical devices that all have to talk to each other i had codex + voice mode open for basically the entire setup. told it everything i bought, sent it some pics and then just started talking to it >what order do i set all this up in >how do i change this setting on the radio >which of these cables do i use >the drone is flashing pink wat mean >can you make this thing less insane to fly in my apartment and it was surprisingly seamless it would go find the manual for whatever specific thing i was holding, tell me exactly which buttons to press, what port to plug something into, what i should see if it worked etc then when i got to configuring the actual drone i had codex running on the computer it was plugged into, so it could inspect the config, back everything up, change settings, send usb reboot signals and check what happened the insane thing about voice mode is that youre literally hands on with the hardware and just telling codex what it should do, i literally never touched a thing on the computer besides starting voice mode if something doesn't work you tell it what happened and keep going a few hours of this and i had the radio, goggles, charger, batteries, drone firmware and betaflight all set up and had actually flown the thing the part that stuck with me is that i also understood what most of it was doing by the end, every time there was a term or tech i didnt understand id just ask to explain there is something absolutely magical about having proper real time personalized assistance, being able to dump a pile of unfamiliar hardware on your desk and have something figure out exactly what you own and walk through it with you in real time you become the missing physical link pressing the buttons i think spending all day using coding agents has actually made me pretty numb to AI progress. every new model is a bit better at some benchmark or can oneshot some task that the previous one couldn't and you just kinda adjust to it this felt different mostly because i had no existing knowledge to fall back on for the first time the jarvis comparison didn't feel cringe ai for coding and general computer tasks is cool and all but this feels a lot closer to the endgame anyone should be able to just ask any question about whats going on in their life and have realtime support i wonder if more hardware products will actually start exposing some sort of MCP or interface for agents to plug into thinking for example of how elevators in china are increasingly built with interfaces that let delivery robots call them directly instead of having to physically press a button we might actually start seeing hardware design shift from being purely human-interface-first to also being agent-interface-first buttons, screens and menus exist because humans need some way to tell machines what to do. agents don't necessarily need any of that if the hardware exposes an interface directly very curious which side closes the physical world gap first: humanoid robots that can operate hardware designed for humans, or hardware adapting so agents can operate it directlyshow more

BREAKING: SpaceXAI has released another major new update for... Grok Build (v1.0.19) This update improves background task handling, adds transparent terminal themes, worktree support for headless sessions, and better session/dashboard controls. It also fixes UI freezes, crashes, feedback issues, clickable URLs, and makes the first prompt after login faster. Breaking Changes • Scheduled /loop tasks always run in the background; they no longer inject turns into your conversation. Features • New terminal theme option makes backgrounds transparent so the terminal's own colors show through. • MCP servers blocked by organization policy now show clear messages and are refused before any config change. • Session resume now tells the model what loops, subagents, and workflows were still running. • Dashboard now shows newly dispatched sessions immediately instead of waiting for the store. • Headless sessions (grok -p) now support the --worktree flag to run in a separate git worktree. • Dashboard now says 'Open session' instead of 'Add session' for the session picker button. • Multi-line bash commands now render with proper wrapping and highlighting when opening the block viewer. • /usage now works from the dashboard and shows account allowance when no session is active. Bug Fixes • Fixed mid-turn UI freezes when the terminal stops reading output. • Fixed crashes that occurred when the terminal pane was closed while grok was exiting. • MCP server list in minimal mode now correctly shows policy-blocked servers. • URLs that wrap across multiple lines inside quotes or lists are now fully clickable. • The welcome screen composer now grows taller when you paste multi-line text. • Enterprise policy files are no longer deleted on startup when your team login is stored at a custom GROK_AUTH_PATH. • /feedback now drops unsupported images with a notice (matching the modal) and never loses your report text on save errors. • Feedback drafts keep their paragraph breaks when updated, and the modal no longer switches tabs unexpectedly. • Turn summary lines no longer lose their spacing after background tasks finish. • Thinking blocks no longer stay expanded after switching between fullscreen and minimal modes. Performance • First prompt after login is faster when MCP servers are configured; they connect in the background. Download Grok Build: Update to the latest Alpha release: grok update --alpha Update to the latest Stable release: grok updateshow more

your AI agent can watch any video now -... paste a URL and it sees every frame, hears every word, all for free 🤯 bradautomates/claude-video gives Claude the ability to watch YouTube, Loom, TikTok, local files - anything yt-dlp supports what people actually use it for: → analyze a competitor launch - what hook, what visuals, what structure → debug from a screen recording - Claude reads the exact frame where it breaks → summarize a 49-min talk in 30 seconds with frame-accurate timestamps → strip the hype from product videos - "what's actually new, skip the pitch" the mechanism: yt-dlp pulls free captions first (zero cost). ffmpeg extracts frames at scene-aware intervals - not uniform sampling, so you don't waste tokens on 12 identical frames of the same slide. Claude reads every frame as an image with timestamp markers. Groq Whisper only kicks in when a video has no caption track how to set up (3 min): > claude code: /plugin marketplace add bradautomates/claude-video then /plugin install watch@claude-video > or npx skills add bradautomates/claude-video -g for codex, cursor, gemini cli > dependencies auto-install on macOS via brew two caveats: free captions cover most but not all videos. past 10 min use --start/--end for focused sections or the token-burner mode for full coverage your buddy still watches every tutorial at 2x speed taking manual notes. you paste a URL and your agent extracts the substance in seconds for $0show more

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.show more

Another WTF moment. A developer just open-sourced a coding... agent harness that boots 245x faster than Claude Code. It's called jcode. You launch it and the first frame renders in 14 milliseconds. Claude Code takes 3,436. One active session uses 27.8 MB of RAM. Claude Code uses 386.6. Run ten sessions in parallel and jcode holds at 117 MB while OpenCode swells to 3.2 GB. Each agent has a semantic memory graph instead of a scratchpad. Every turn gets embedded as a vector. The graph is queried on every turn for related memories, and a sideagent verifies the hits before injecting them into context. Consolidation runs in the background to check for stale or conflicting facts. No manual /remember calls. No token burn on lookup tools. The provider list is 30+ deep. Claude, ChatGPT, Gemini, GitHub Copilot, Azure, OpenRouter, DeepSeek, Groq, Mistral, Perplexity, Fireworks, Ollama, LM Studio, and any OpenAI-compatible endpoint you point it at. Ran out of tokens on your first ChatGPT Pro sub? /account swaps to the second. Then there's Swarm. Spawn two agents in the same repo and the server manages them. When agent A edits a file agent B has been reading, agent B gets pinged and can check the diff. Agents can DM each other, broadcast to the room, or spawn their own worker teams for parallel tasks. Groups, channels, and completion statuses are handled automatically. The UI has live side panels that render mermaid diagrams inline. To make it fast, the author wrote a Rust mermaid renderer 1800x faster than the JavaScript one, then wrote a custom terminal called Handterm because no existing terminal could do smooth partial-line scrolling. Self-dev mode is where it gets wild. Tell your agent to enter self-dev and it starts editing jcode's own source code, rebuilds the binary, reloads it live, and keeps working across your existing sessions. You can also resume broken sessions from Claude Code, Codex, OpenCode, or pi directly inside jcode. Anthropic's cache goes cold at the 5-minute mark and you're staring down a big cache miss on your next turn? The UI warns you before you spend the tokens. Written in Rust. MIT licensed. Runs on macOS, Windows, Linux, and Termux. Sitting at 11.2k stars with a native iOS app coming.show more

BREAKING: SpaceXAI has released another major new update for... Grok Build (v1.0.22) This update is focused on smoother workflows, better safety and improved reliability. It adds stronger desktop and MCP integration, clearer file-edit previews, a redesigned dashboard and better subagent support. It also fixes problems with sessions, skills, authentication and background commands while making sessions faster to open and resume. Features Built-in agent tools now take precedence over user MCP servers when tool names collide. Desktop app tools are now available through a dedicated first-party MCP server. Remote control pickers can now group servers by device using announced device identity. edit_file diffs now show real file line numbers instead of starting at line 1. Permission prompts for file edits now auto-expand the diff row so you can see the change before approving. Sending a message to a finished subagent now continues that same subagent instead of failing. Background subagent completion messages now show the actual output instead of just a pointer to run the tool. Dashboard now shows a unified header with a location picker and an actions row for creating agents or resuming previous sessions. New grok-workspaced daemon mode lets a long-lived process expose folders to the Computer Hub, separate from the Desktop-supervised sidecar. Bug Fixes MCP connectors now correctly show when they need re-authentication, even if no tools are listed. Extensions modal shortcuts now work when the tab bar is focused, and invalid actions on headers show helpful messages. The Send now button and shortcuts now work correctly when an automatic background turn is running. Resumed sessions now show the exact text you typed for mid-turn follow-ups instead of the wrapped system message. The /skills command now updates the model with newly installed skills, even when written from another NFS client. Auto mode no longer instantly runs destructive git checkout -- commands; they now go through the model for safety. Fixed a crash that could occur when restoring pasted content after certain skill injections or rewinds. Subagents and workflows now respect the same bash timeout and auto-background settings configured for the parent session. Fixed model backend selection so an explicit chat_completions setting in config.toml is no longer overwritten by same-slug siblings. Slash command advertisements no longer spam repeatedly when your current directory is your home folder. Foreground shell commands no longer produce spurious background-task reminders or incorrect kill results. Queued follow-up buttons now appear in the order [Send now][edit][Cancel]. /compact instructions in the pager are now passed to the compaction backend. Bare /compact is unchanged. /goal, and resume after pressing Esc, now correctly starts the goal planner instead of failing with “Planning failed.” run_terminal_cmd now correctly tells the model that foreground commands are backgrounded after approximately 15 seconds instead of the 120-second timeout value. Skill announcements no longer repeat the same list of available skills multiple times in a session. Monitor events in multi-session processes now correctly wake idle sessions instead of being buffered until the next prompt. Performance Opening or resuming sessions no longer pauses the interface while reading MCP configuration files. Download Grok Build: Update to the latest Alpha release: grok update --alpha Update to the latest Stable release: grok updateshow more

After a few more hours, I think I've figured... out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.show more

Congratulations to our winner for the Solo Leveling PC... jedi_master_snorlax 🎉 Also, please be kind to winners, we only have 1 PC to go around for all of you 🥹🙏 How are winners picked for giveaways??⬇️ Since we’ve got a lot of new people in here, let me explain how winners are picked. We use a site called Rafflly (I’ll link it below if you want to check it out and use it for your own giveaways), We pay $50 a month for a subscription since we have so many entries, and that lets us handle all the volume fairly and smoothly, we had 334,264 enter this time around. I’ve also included a video that shows how we link all the accounts together and run a multi network giveaway to pick one lucky person. It’s the best way to keep things fair! After it picks someone we confirm 1 that they are real and 2 they followed all the rules. And just to clear things up, our giveaways are definitely real. Josh and I run them ourselves and we cover the shipping costs out of pocket. The companies we partner with aren’t paying for the shipping or paying us to run them, we do it because we want to give back to the community. It’s a win win, you get free stuff, we get a little exposure, and the brands do too and nothing gets sent to a landfill 👌 Also, big thank you to everyone who entered the Solo Leveling giveaway! Right now, the Hatsune Miku giveaway is live, you’ve got 6 days left to enter 💙✨ And on the 13th, our 3rd giveaway will go live, the all white Cougar PC 🤍🔥 see you then! 💜 Thank you again for all the love and support, it genuinely makes all these giveaways possible!show more

A good technical LLM interview question: Your RAG chatbot... is working as expected locally. You deploy it behind a load balancer with 3 replicas. Users report that it forgets what they just asked, and answers get worse with each restart. Why did this happen? (answer below) A local setup has one process that owns everything. - The vector index is a variable in memory. - Conversation history is a Python list. - The documents are on local disk. You never treat any of them as infrastructure, because restarting rebuilds all three in seconds and there is only ever one copy. The setup does not carry over to production directly. The vector index might disappear on restart, so the app re-embeds everything on boot and serves empty results until it finishes. Conversation history may belong to one replica, so a follow-up routed elsewhere has no memory of the previous turn. Documents could be on whichever container ingested them, so the three replicas hold three different corpora. None of this is evident with one user and one process. So the actual work in shipping RAG is not just the retrieval logic, but also storing the vector index, the conversation history, and the documents outside the app, where every replica reads and writes the same copy. Which comes down to three requirements: > The vector store needs persistence and has to be reachable from every replica. pgvector inside Postgres keeps embeddings next to the rest of the data instead of adding another system to operate. > Conversation state has to be checkpointed outside the app. LangGraph writes its state to Postgres, so any replica can pick up a thread mid-conversation. > Docs need shared object storage, so ingestion happens once instead of once per replica. If you get those three right, the retrieval logic you wrote in the notebook works unchanged. To learn how all of it is wired together, Akamai's GitHub has a working reference implementation. - rag-langgraph-k8s-quickstart is an airline policy Q&A assistant built with FastAPI, LangChain, and LangGraph. Terraform provisions the LKE cluster, a Postgres instance with pgvector for embeddings, a second Postgres for LangGraph checkpointing, and an object storage bucket for the policy documents, in one apply. - akamai-workshop-ai-inference covers the next step, running the model yourself instead of calling an API, with prefill and decode, KV cache tradeoffs, and continuous batching under real concurrency. Both are available on Akamai's new Developer Hub, alongside their tutorials and code samples. It also links to Edge Case, their Discord, where four developer advocates architect and deploy a production app live every other Wednesday. If you create a new Akamai Cloud account, you can also get $300 in credits for joining. Join here: That said, this post assumes the retrieval logic was right to begin with, and that is doing a lot of work. Most RAG systems fail earlier, at the point where a chunk gets treated as a self-contained unit of meaning. I wrote about the two skills that fix that gap, and why the chunk is usually the wrong thing to embed. Read it below. Thanks to Akamai Cloud for partnering today!show more

While working on a new video with solutions to... the previous one, I found ChatGPT's new UI struggles even more with concurrent updates: entries lose state and stick around for too long (see video). If this was a LiveView app, we would be getting so much flak.😅 --- I believe part of the problem here is having separate mutate and fetch requests on every deletion. The first fetch is cancelled when the second one comes up, causing items to stick around for longer. Many said yesterday that you could do the mutation and fetch as a single request, but that leads to other problems, such zombie entries. For example, imagine you delete link1 and link2 within a brief period of time. There is no guarantee the deletion order in the database will match the order the client receives the response, so you may end up with this: 1. (client) request to delete link1 sent 2. (client) request to delete link2 sent 3. (server) deletes link1 and loads a new list (includes link2) 4. (server) deletes link2 and loads a new list (no link1 or link2) 5. (client) receives link2 response 6. (client) receives link1 response So if you choose to use the latest response (link1), you brought link2 back to life. If you say you will use the response from the last request, events 3-4 can be swapped, and now you bring link1 back to life. Another way to solve this is by basically not allowing concurrent requests at all but that can affect the user experience drastically in other ways. Next week I should publish a video explaining how LiveView tackles this. Stay tuned!show more

Introducing Pods Hyperspace Pods lets a small group of... people - a family, a startup, a few friends, to pool their laptops and desktops into one AI cluster. Everyone installs the CLI, someone creates a pod, shares an invite link, and the machines form a mesh. Models like Qwen 3.5 32B or GLM-5 Turbo that need more memory than any single laptop has get automatically sharded across the group's devices - layers split proportionally, inference pipelined through the ring. From the outside it looks like one OpenAI-compatible API endpoint with a pk_* key that drops straight into your AI tools and products. No configuration beyond pasting the key and changing the base URL. A team of five paying for cloud AI burns $500–2,000 a month on API calls. The same team's existing machines can serve Qwen 3.5 (competitive on SWE-bench) and GLM-5 Turbo (#1 on BrowseComp for tool-calling and web research) for free - the hardware is already on their desks. When a query genuinely needs a frontier model nobody has locally, the pod falls back to cloud at wholesale rates from a shared treasury. But for the daily work - code reviews, refactors, research, drafting - local models handle it and nobody gets billed. And when it is idle, you can rent out your pod on the compute marketplace, with fine-grained permissions for access management. There's no central server involved in inference. Prompts go from your machine to your pod members' machines and back: all of this enabled by the fully peer-to-peer Hyperspace network. Pod state - who's a member, which API keys are valid, how much treasury is left - is replicated across members with consensus, so the whole thing works on a local network. Members behind home routers don't need port forwarding either. The practical setup for most pods is three models covering different jobs: Qwen 3.5 32B for code and reasoning, GLM-5 Turbo for browsing and research, Gemma 4 for fast lightweight tasks. All running on hardware you already own. Pods ship today in Hyperspace v5.19. Model sharding, API keys, treasury, and Raft coordinator are all live. What Makes This Different - No middleman. Your prompts travel from your IDE to your pod members' hardware and back. There is no server in between reading your data. - No vendor lock-in. Pod membership, API keys, and treasury are replicated across your own machines using Raft consensus. If the internet goes down, your local network keeps working. There is no database in someone else's cloud that your pod depends on. - Automatic sharding. You don't configure layer ranges or calculate VRAM budgets. Tell the pod which model you want. It figures out how to split it across whatever hardware is online. - Real NAT traversal. Your friend behind a home router with a dynamic IP? Works. No VPN, no Tailscale, no port forwarding. The nodes handle it. - Free when local. This is the part that matters most. Cloud AI bills scale with usage. Pod inference on local hardware scales with nothing. The marginal cost of your 10,000th prompt is the electricity your laptop was already using. Coming soon: - Pod federation: pods form alliances with other pods. - Marketplace: pods with spare capacity can sell inference to other pods.show more

A friend of mine just recently got his first... gun, a striker fired Glock 19. He is terrified to leave a round chambered. To anyone reading this who has this same fear, I want to alleviate your concerns. I'm going to explain why there is nothing to be afraid of. First and foremost, I fully understand your concern. It's not irrational. And you're not stupid for being nervous about a bullet being aimed at your leg with the striker cocked back under spring tension about an 1/8 of an inch from the primer. I get it. I shared this concern when I was new to carrying. But your fear is due to a lack of understanding of the internal safety features of a modern striker fired handgun. On a properly maintained modern striker fired pistol the striker CANNOT hit the primer on the chambered round without the trigger being pulled. Can't. Not shouldn't. Can't. (If you have any good Sig P320 jokes, this is the proper place to share them) There is a block that the striker will hit and stop if it is released without the trigger being depressed. It works just like a lock and key. There is a channel in the blocker that the striker can pass through if it is in the fire position. It only goes into the fire position if the trigger is pulled which pushes the blocker into the fire position. A spring keeps the blocker firmly in the block position until then. The blocker is a solid piece of steel that won't break. And if your gun is securely in a hard sided Kydex holster nothing can move the trigger unless it is unholstered. Many guns like Glocks have a trigger safety that prevents the trigger from moving due to force of dropping. Your finger has to be on the trigger safety to move it. So the gun cannot fire unless you pull the trigger. And it's easy for you to test this safety feature to see how it works! See the video below. You can try to push the striker forward by moving that piece at the back of the slide forward. That piece is the back of the striker. Push it forward and it will stop. The tip won't come out through the breach. You see it trying to come through but it gets stuck. Now push that little button in. That is the actual blocker. When you push it in you will now be able to move the striker forward through the breach and see how it will strike the primer. You can test this easily every time you disassemble your pistol to verify it is still working. You can break this safety feature by removing the blocker or losing the spring. But if it's there it will work. (You would be the first person in firearms history who has ever lost a spring. Literally the first one. It has never happened before. 😐) But it doesn't come out as part of regular maintenance. You have to disassemble the firing assembly to get it out. That won't happen by accident. And if you do that on purpose you should do this blocker test when you reassemble it to make sure the safety feature is working. My video shows a Glock slide. All Glocks will look like this. Other brands may put the blocker in a different spot or it may be a slightly different shape. But they all (mostly) have the same design. If you test yours as demonstrated and it works like mine does, your gun WILL NOT fire without pulling the trigger. (If you just thought of another P320 joke, this is another good place to toss that out there)show more