正在加载视频...

视频加载失败

返回首页

Meet Quest 1.0 ！ - Built-in Agent Skills with elevated design taste - Parallel execution: local + remote, multiple tasks at once - From 0→1 to 1→∞, MVP to refactors - Walk away while it builds. Check results when ready 👇 Watch our PM adds two features. No code written.

qoder_ai_ide's profile picture

Qoder

8,239 subscribers

1,982,600 次观看 • 6 个月前 •via X (Twitter)

教育科学技术
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

Cursor for Design? This Claude Code UI workflow is insane And many vibe coders not aware of it: 1. Claude Code can assign parallel tasks to sub agents 2. Integrate with git worktree to create sandbox env This means you can get Claude Code generate 10 design at the same time, fork & iterate 🔁 Design is an explorative process, by leveraging sub agent + parallel task capabilities, many interesting product UX can be built; Also turned this workflow into an open-source IDE extension here:
16:38

Cursor for Design? This Claude Code UI workflow is insane And many vibe coders not aware of it: 1. Claude Code can assign parallel tasks to sub agents 2. Integrate with git worktree to create sandbox env This means you can get Claude Code generate 10 design at the same time, fork & iterate 🔁 Design is an explorative process, by leveraging sub agent + parallel task capabilities, many interesting product UX can be built; Also turned this workflow into an open-source IDE extension here:

Jason Zhou

40,635 次观看 • 1 年前

NOT KNOWING HOW TO CODE IS OFFICIALLY A BAD EXCUSE. This 18-year-old just built an app with 0 technical knowledge. Absolutely no coding skills. Just: – a sharp idea – fast execution – AI as leverage Result? $17K+ MRR. If he can go from idea > app store in 1 month, what's stopping you?
0:51

NOT KNOWING HOW TO CODE IS OFFICIALLY A BAD EXCUSE. This 18-year-old just built an app with 0 technical knowledge. Absolutely no coding skills. Just: – a sharp idea – fast execution – AI as leverage Result? $17K+ MRR. If he can go from idea > app store in 1 month, what's stopping you?

Starter Story

36,586 次观看 • 5 个月前

“When I was with my boyfriend, he never sent me up to 500k at once. But this lady transferred 1 million in a single transaction. That was when I realized it was time to walk away from that relationship.” — Woman shares her experience dat!ng another woman.👀🤔
4:39

Sensitive content

“When I was with my boyfriend, he never sent me up to 500k at once. But this lady transferred 1 million in a single transaction. That was when I realized it was time to walk away from that relationship.” — Woman shares her experience dat!ng another woman.👀🤔

Dami’ Adenuga

123,128 次观看 • 5 个月前

WATCH GRASS GROW- LIVE EVENT ON APRIL 1 @ 8 PM BST / 3PM EST MAP CODE: 0158-8116-3594 The spiritual successor to our biggest release from last year, WATCH PAINT DRY! With UEFN's insane advancements in technology, we were able to allow players to watch paint dry AND watch grass grow at the same time! This is an ACTUAL event. Something DOES happen when the clock hits 0. #UEFN
0:26

WATCH GRASS GROW- LIVE EVENT ON APRIL 1 @ 8 PM BST / 3PM EST MAP CODE: 0158-8116-3594 The spiritual successor to our biggest release from last year, WATCH PAINT DRY! With UEFN's insane advancements in technology, we were able to allow players to watch paint dry AND watch grass grow at the same time! This is an ACTUAL event. Something DOES happen when the clock hits 0. #UEFN

Genesis Studios

118,722 次观看 • 4 个月前

HERMES AGENT SUPPORTS 7 TYPES OF AI AGENTS. EACH ONE TAKES LESS THAN 90 SECONDS TO SET UP. MOST PEOPLE ONLY BUILD THE FIRST ONE. HERE ARE ALL SEVEN AND WHEN TO USE EACH. 1. BASIC AGENT WITH TOOLS your agent with access to terminal, browser, file system, web search, and calendar. it plans and executes tasks on its own. this is what you get on day one. "find flights to Lisbon under $400" "check my calendar and flag conflicts" "search the web for competitor pricing" set in Desktop app / Dashboard: Tools → enable what you need. when to use: single tasks that need tool access. 2. AGENT WITH MCP SERVERS connect your agent to external services. Notion, Google Drive, GitHub, Slack, databases, APIs, any MCP-compatible service. the agent doesn't scrape these services. it interacts through structured APIs. reads your Notion pages. creates GitHub issues. queries your database. sends Slack messages. set in Desktop app / Dashboard: MCP → Add Server. when to use: your workflow lives across multiple platforms. 3. SEQUENTIAL AGENTS (pipeline) one agent finishes. passes output to the next. assembly line for AI. agent 1: scans inbox for leads. agent 2: qualifies leads against criteria. agent 3: drafts outreach emails. in Hermes: cron jobs with wakeAgent gates. agent 1 writes output to a file. agent 2 wakes only when that file has new data. agent 3 wakes when agent 2 is done. each agent = a separate profile with its own model. when to use: multi-step workflows where each step depends on the previous one finishing. 4. PARALLEL EXECUTION AGENTS multiple agents working at the same time. results merge when all finish. "research these 5 competitors in parallel" in Hermes: delegate_task with batch mode. up to 3 sub-agents running in parallel by default. each gets its own clean context. only summaries return to the parent. delegation: model: "deepseek/deepseek-v4" children run cheap. parent synthesizes. when to use: independent tasks that don't depend on each other. research, data gathering, analysis. 5. AGENTS WITH ROUTERS conditions that send tasks down different paths based on the input. "if sales email → SDR profile. if support ticket → support profile. if calendar invite → EA profile." in Hermes: Kanban decompose. the decomposer reads profile descriptions and routes each task to the best-fit agent. or: Chief of Staff profile that triages and assigns to other profiles. when to use: incoming work that needs different specialists based on type. 6. HUMAN IN THE LOOP the agent does the work. asks for your approval before executing. "I drafted this email. approve before I send?" "this command will delete 3 files. proceed?" in Hermes: approvals.mode: manual (default). every dangerous action needs your confirmation. 60-second timeout. fails closed. or smart mode: LLM assesses risk. safe actions auto-approved. dangerous ones ask you. uncertain ones escalate. when to use: tasks where a mistake has real consequences. emails, deployments, financial transactions, public posts. 7. DYNAMIC SUB-AGENT SPAWNING your main agent realizes it needs help and spawns specialized sub-agents on the fly. "build this feature" → parent delegates: → sub-agent 1: research the API docs → sub-agent 2: write the code → sub-agent 3: write the tests in Hermes: delegate_task with role: orchestrator. raise max_spawn_depth for nested delegation. delegation: max_spawn_depth: 2 orchestrator_enabled: true depth 2 with concurrency 3 = up to 9 parallel workers. each level multiplies the spend. raise depth only when you need multi-level trees. when to use: complex tasks where the agent discovers what help it needs during execution. THE PROGRESSION: start with 1 (tools) and 6 (approvals). add 2 (MCP) when you need external services. add 4 (parallel) when tasks take too long one at a time. add 3 (sequential) when you build multi-step pipelines. add 5 (routing) when you run multiple profiles. add 7 (dynamic) when single-agent reasoning falls short. seven types. each under 90 seconds to configure. the value compounds as you stack them. comment AGENTS and I'll send you 3 ready-to-build agent setups that combine these types into real workflows.
1:15

HERMES AGENT SUPPORTS 7 TYPES OF AI AGENTS. EACH ONE TAKES LESS THAN 90 SECONDS TO SET UP. MOST PEOPLE ONLY BUILD THE FIRST ONE. HERE ARE ALL SEVEN AND WHEN TO USE EACH. 1. BASIC AGENT WITH TOOLS your agent with access to terminal, browser, file system, web search, and calendar. it plans and executes tasks on its own. this is what you get on day one. "find flights to Lisbon under $400" "check my calendar and flag conflicts" "search the web for competitor pricing" set in Desktop app / Dashboard: Tools → enable what you need. when to use: single tasks that need tool access. 2. AGENT WITH MCP SERVERS connect your agent to external services. Notion, Google Drive, GitHub, Slack, databases, APIs, any MCP-compatible service. the agent doesn't scrape these services. it interacts through structured APIs. reads your Notion pages. creates GitHub issues. queries your database. sends Slack messages. set in Desktop app / Dashboard: MCP → Add Server. when to use: your workflow lives across multiple platforms. 3. SEQUENTIAL AGENTS (pipeline) one agent finishes. passes output to the next. assembly line for AI. agent 1: scans inbox for leads. agent 2: qualifies leads against criteria. agent 3: drafts outreach emails. in Hermes: cron jobs with wakeAgent gates. agent 1 writes output to a file. agent 2 wakes only when that file has new data. agent 3 wakes when agent 2 is done. each agent = a separate profile with its own model. when to use: multi-step workflows where each step depends on the previous one finishing. 4. PARALLEL EXECUTION AGENTS multiple agents working at the same time. results merge when all finish. "research these 5 competitors in parallel" in Hermes: delegate_task with batch mode. up to 3 sub-agents running in parallel by default. each gets its own clean context. only summaries return to the parent. delegation: model: "deepseek/deepseek-v4" children run cheap. parent synthesizes. when to use: independent tasks that don't depend on each other. research, data gathering, analysis. 5. AGENTS WITH ROUTERS conditions that send tasks down different paths based on the input. "if sales email → SDR profile. if support ticket → support profile. if calendar invite → EA profile." in Hermes: Kanban decompose. the decomposer reads profile descriptions and routes each task to the best-fit agent. or: Chief of Staff profile that triages and assigns to other profiles. when to use: incoming work that needs different specialists based on type. 6. HUMAN IN THE LOOP the agent does the work. asks for your approval before executing. "I drafted this email. approve before I send?" "this command will delete 3 files. proceed?" in Hermes: approvals.mode: manual (default). every dangerous action needs your confirmation. 60-second timeout. fails closed. or smart mode: LLM assesses risk. safe actions auto-approved. dangerous ones ask you. uncertain ones escalate. when to use: tasks where a mistake has real consequences. emails, deployments, financial transactions, public posts. 7. DYNAMIC SUB-AGENT SPAWNING your main agent realizes it needs help and spawns specialized sub-agents on the fly. "build this feature" → parent delegates: → sub-agent 1: research the API docs → sub-agent 2: write the code → sub-agent 3: write the tests in Hermes: delegate_task with role: orchestrator. raise max_spawn_depth for nested delegation. delegation: max_spawn_depth: 2 orchestrator_enabled: true depth 2 with concurrency 3 = up to 9 parallel workers. each level multiplies the spend. raise depth only when you need multi-level trees. when to use: complex tasks where the agent discovers what help it needs during execution. THE PROGRESSION: start with 1 (tools) and 6 (approvals). add 2 (MCP) when you need external services. add 4 (parallel) when tasks take too long one at a time. add 3 (sequential) when you build multi-step pipelines. add 5 (routing) when you run multiple profiles. add 7 (dynamic) when single-agent reasoning falls short. seven types. each under 90 seconds to configure. the value compounds as you stack them. comment AGENTS and I'll send you 3 ready-to-build agent setups that combine these types into real workflows.

YanXbt

17,312 次观看 • 29 天前

This guy literally broke down everything to build a 21 agent dev team in Claude Code: 0:00 - Why one prompt = AI slop 1:55 - Claude Code as your full startup 2:43 - The 21-agent team 4:57 - Inside the system analyst agent 5:52 - Live demo: 0 → TestFlight 8:42 - Define a "good" system analyst first 11:53 - The system analyst workflow 12:17 - Why Confluence + Jira + MCPs matter 15:30 - Classic PM skills > vibe coding 19:15 - The scaffolding that kills spaghetti code 22:10 - Setting up agents inside Claude Code 26:19 - The longest dictation prompt this podcast has seen 35:29 - Why dictation beats typing for AI specs 47:30 - Brand guidelines in Figma Make 55:59 - Idea → prompt → design → app 1:06:27 - Claude Code builds the Figma screens 1:23:59 - Frontend tickets appear in Jira (with Figma links) 1:48:49 - The hockey rules AI app goes live 1:53:56 - Full recap: Claude, Confluence, Figma, Jira, Simulator, TestFlight 2:03:17 - Should PMs get AI PM certificates? 2:08:15 - How to build a PM portfolio that lands FAANG offers 2:13:25 - How to get started this week
2:15:18

This guy literally broke down everything to build a 21 agent dev team in Claude Code: 0:00 - Why one prompt = AI slop 1:55 - Claude Code as your full startup 2:43 - The 21-agent team 4:57 - Inside the system analyst agent 5:52 - Live demo: 0 → TestFlight 8:42 - Define a "good" system analyst first 11:53 - The system analyst workflow 12:17 - Why Confluence + Jira + MCPs matter 15:30 - Classic PM skills > vibe coding 19:15 - The scaffolding that kills spaghetti code 22:10 - Setting up agents inside Claude Code 26:19 - The longest dictation prompt this podcast has seen 35:29 - Why dictation beats typing for AI specs 47:30 - Brand guidelines in Figma Make 55:59 - Idea → prompt → design → app 1:06:27 - Claude Code builds the Figma screens 1:23:59 - Frontend tickets appear in Jira (with Figma links) 1:48:49 - The hockey rules AI app goes live 1:53:56 - Full recap: Claude, Confluence, Figma, Jira, Simulator, TestFlight 2:03:17 - Should PMs get AI PM certificates? 2:08:15 - How to build a PM portfolio that lands FAANG offers 2:13:25 - How to get started this week

Aakash Gupta

178,026 次观看 • 3 个月前

Sensational limbs from Fulham. No win at Stamford Bridge for 45 years and they’ve gone there on Boxing Day and come from 1-0 down on 82 minutes to win it with a 95th minute goal in front of the away end. What a way to end the run of results.
0:41

Sensational limbs from Fulham. No win at Stamford Bridge for 45 years and they’ve gone there on Boxing Day and come from 1-0 down on 82 minutes to win it with a 95th minute goal in front of the away end. What a way to end the run of results.

HLTCO

809,807 次观看 • 1 年前

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!
44:33

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!

Dan Shipper 📧

145,487 次观看 • 1 年前

Testing Replit ⠕ Agent 4 and its actually cracked Been a power user of Replit for like a year now and this new update makes it feel like a whole new platform Just updated my portfolio and it was like 5x simpler to do now than before - Agent Tasks on left lets you do hella things at once - Shell still runs Claude like its a terminal - Design section has built in previews + prompts to give you UI remix options - Skills are built into Agent prompting - iOS apps have options to go straight to the App Store I know two people IRL who built 2-3 apps with Replit from ZERO AI experience IMO Replit is still the easiest to use platform (especially for beginners) for anything videcoding related
0:21

Testing Replit ⠕ Agent 4 and its actually cracked Been a power user of Replit for like a year now and this new update makes it feel like a whole new platform Just updated my portfolio and it was like 5x simpler to do now than before - Agent Tasks on left lets you do hella things at once - Shell still runs Claude like its a terminal - Design section has built in previews + prompts to give you UI remix options - Skills are built into Agent prompting - iOS apps have options to go straight to the App Store I know two people IRL who built 2-3 apps with Replit from ZERO AI experience IMO Replit is still the easiest to use platform (especially for beginners) for anything videcoding related

ashen

30,418 次观看 • 5 个月前

🎨 Introducing Genspark Design The next-gen AI for design and creation, powered by Claude Opus 4.7. From rough idea to professional design, no design background needed. - One tool for everything you design. UI prototypes, videos, HTML animations, posters — all in one place and production-ready. - Stay on-brand with your own design system. Upload your Figma files or save your designs, reuse them across every project, and share them with your team. - Ship it, don't just mock it. Turn any app or website design into working code with one click, built on Genspark Code. Start building at our launch price 👉
1:23

🎨 Introducing Genspark Design The next-gen AI for design and creation, powered by Claude Opus 4.7. From rough idea to professional design, no design background needed. - One tool for everything you design. UI prototypes, videos, HTML animations, posters — all in one place and production-ready. - Stay on-brand with your own design system. Upload your Figma files or save your designs, reuse them across every project, and share them with your team. - Ship it, don't just mock it. Turn any app or website design into working code with one click, built on Genspark Code. Start building at our launch price 👉

Genspark

179,614 次观看 • 1 个月前

I got early access to Replits Agent 4. it makes building so much fun. in an hour I... > found a local business with no website. > built them a site that looks like it came from an agency. > had multiple agents working on new features at the same time. > made a custom pitch deck > and a custom mobile app for the business, just for the fun of it. incredible.
17:20

I got early access to Replits Agent 4. it makes building so much fun. in an hour I... > found a local business with no website. > built them a site that looks like it came from an agency. > had multiple agents working on new features at the same time. > made a custom pitch deck > and a custom mobile app for the business, just for the fun of it. incredible.

Nic Conley

47,549 次观看 • 5 个月前

Cursor pays engineers $1,100,000 a year to run teams of AI agents that ship code while they sleep. [The CEO of Cursor explained in 9 minutes how they ship at 100x speed using team of agents] ↓ Save this before everyone copies the playbook 1. Engineers no longer babysit one assistant. They manage dozens of agent colleagues working in parallel, each on its own remote machine 2. Validation contract before code, not after. Humans only at scoping and review. 3. The agent team handles the full loop : planning, coding, testing, shipping PRs with each agent specialised for a role. Watch the guide. Then read the guide below by Khairallah AL-Awady
9:37

Cursor pays engineers $1,100,000 a year to run teams of AI agents that ship code while they sleep. [The CEO of Cursor explained in 9 minutes how they ship at 100x speed using team of agents] ↓ Save this before everyone copies the playbook 1. Engineers no longer babysit one assistant. They manage dozens of agent colleagues working in parallel, each on its own remote machine 2. Validation contract before code, not after. Humans only at scoping and review. 3. The agent team handles the full loop : planning, coding, testing, shipping PRs with each agent specialised for a role. Watch the guide. Then read the guide below by Khairallah AL-Awady

Avid

636,555 次观看 • 3 个月前

Want to win a trip Into The Millennium to meet us at Sphere?! We’re teaming up with Fandiem to give away a VIP trip for two to see us at our ‘Into The Millennium’ Sphere Residency this August 17 in Las Vegas, NV! Trip includes 2 VIP tickets to our show, meet & take a photo with us, roundtrip airfare and hotel accommodations, and more! Donate for a chance to win, all while supporting the incredible Make-A-Wish America at close Friday, August 1, 2025 11:59 pm PT.
0:40

Want to win a trip Into The Millennium to meet us at Sphere?! We’re teaming up with Fandiem to give away a VIP trip for two to see us at our ‘Into The Millennium’ Sphere Residency this August 17 in Las Vegas, NV! Trip includes 2 VIP tickets to our show, meet & take a photo with us, roundtrip airfare and hotel accommodations, and more! Donate for a chance to win, all while supporting the incredible Make-A-Wish America at close Friday, August 1, 2025 11:59 pm PT.

Backstreet Boys

17,701 次观看 • 1 年前

Google Labs just updated Stitch and it's insane: → Voice-activated design (talk and it builds) → AI agent that critiques your UI and writes PRDs → Instant multi-device prototyping → Exportable design systems via markdown → Manages multiple ideas in parallel I've designed and built dozens of apps throughout the years – a formerly tedious process that's now available to anyone. No, this doesn't kill designers. But the bottlenecks are collapsing. It's a beautiful time to build. This video is not sponsored, but I did receive early access to test Stitch from my friends at Google Labs which was much appreciated 🙏
1:37

Google Labs just updated Stitch and it's insane: → Voice-activated design (talk and it builds) → AI agent that critiques your UI and writes PRDs → Instant multi-device prototyping → Exportable design systems via markdown → Manages multiple ideas in parallel I've designed and built dozens of apps throughout the years – a formerly tedious process that's now available to anyone. No, this doesn't kill designers. But the bottlenecks are collapsing. It's a beautiful time to build. This video is not sponsored, but I did receive early access to test Stitch from my friends at Google Labs which was much appreciated 🙏

Roberto Nickson

30,412 次观看 • 4 个月前

New course: Nvidia's NeMo Agent Toolkit: Making Agents Reliable, taught by Brian McBrayer 🐬 from NVIDIA. Many teams struggle to turn agent demos into reliable systems that are ready for production. This short course teaches you to harden agentic workflows into reliable systems using Nvidia's open-source NeMo Agent Toolkit (NAT). Whether you built your agent in raw Python or using a framework like LangGraph, or CrewAI, NAT provides building blocks for observability, evaluation, and deployment that turn proofs-of-concept into production-ready systems. NAT makes it easy to troubleshoot and optimize agent performance with execution traces, systematic evaluations, and CI/CD integration. Skills you'll gain: - Build configuration-driven agent workflows with REST APIs and minimal code - Add observability with tracing to visualize agent reasoning and debug performance bottlenecks - Create systematic evaluations using gold-standard datasets to measure and improve agent reliability - Deploy multi-agent systems with authentication, rate limiting, and professional web interfaces - Orchestrate agents from different frameworks to collaborate on complex tasks Join and learn how to turn agent demos into reliable systems!
2:01

New course: Nvidia's NeMo Agent Toolkit: Making Agents Reliable, taught by Brian McBrayer 🐬 from NVIDIA. Many teams struggle to turn agent demos into reliable systems that are ready for production. This short course teaches you to harden agentic workflows into reliable systems using Nvidia's open-source NeMo Agent Toolkit (NAT). Whether you built your agent in raw Python or using a framework like LangGraph, or CrewAI, NAT provides building blocks for observability, evaluation, and deployment that turn proofs-of-concept into production-ready systems. NAT makes it easy to troubleshoot and optimize agent performance with execution traces, systematic evaluations, and CI/CD integration. Skills you'll gain: - Build configuration-driven agent workflows with REST APIs and minimal code - Add observability with tracing to visualize agent reasoning and debug performance bottlenecks - Create systematic evaluations using gold-standard datasets to measure and improve agent reliability - Deploy multi-agent systems with authentication, rate limiting, and professional web interfaces - Orchestrate agents from different frameworks to collaborate on complex tasks Join and learn how to turn agent demos into reliable systems!

Andrew Ng

64,033 次观看 • 7 个月前

HERMES AGENT BUILT A SKILL THAT AUTOMATED AN 8-HOUR WORKFLOW INTO 80 MINUTES. THE AGENT BUILT IT FROM ITS OWN COMPLETED SESSIONS. one user ran their customer pipeline through Hermes repeatedly: meetings → recordings → product requirements → technical specs → development → delivery. after enough runs, Hermes identified the pattern and created a skill that handles the full pipeline: → takes meeting recordings → extracts requirements automatically → runs research on the extracted data → generates product requirement documents → generates technical specifications → delegates the build to a coding agent → sends a link to the finished product what Hermes skills contain: → when to use (trigger conditions) → step-by-step procedure → known pitfalls to avoid → verification steps (how to confirm it worked) stored as markdown in ~/.hermes/skills/. readable, editable, permanent. agents with 20+ self-created skills finish similar future tasks ~40% faster. month 1 you explain everything. month 3 the agent runs your core workflows from the skills it built along the way. full breakdown of Hermes as a Personal AI OS in the article 👇
0:56

HERMES AGENT BUILT A SKILL THAT AUTOMATED AN 8-HOUR WORKFLOW INTO 80 MINUTES. THE AGENT BUILT IT FROM ITS OWN COMPLETED SESSIONS. one user ran their customer pipeline through Hermes repeatedly: meetings → recordings → product requirements → technical specs → development → delivery. after enough runs, Hermes identified the pattern and created a skill that handles the full pipeline: → takes meeting recordings → extracts requirements automatically → runs research on the extracted data → generates product requirement documents → generates technical specifications → delegates the build to a coding agent → sends a link to the finished product what Hermes skills contain: → when to use (trigger conditions) → step-by-step procedure → known pitfalls to avoid → verification steps (how to confirm it worked) stored as markdown in ~/.hermes/skills/. readable, editable, permanent. agents with 20+ self-created skills finish similar future tasks ~40% faster. month 1 you explain everything. month 3 the agent runs your core workflows from the skills it built along the way. full breakdown of Hermes as a Personal AI OS in the article 👇

YanXbt

29,819 次观看 • 2 个月前

Excited to share our latest progress on DYNA-1 pre-training! 🤖 The base model now can perform diverse, dexterous tasks (laundry folding, package sorting, …) without any post-training, even in unseen environments. This powerful base also allows extremely efficient fine-tuning to ~100% success on challenging new tasks with as little as 1 hour of data! 🤯 Watch it master two of them: cup stacking & celery chopping on repeat, no failures. 👇
1:53

Excited to share our latest progress on DYNA-1 pre-training! 🤖 The base model now can perform diverse, dexterous tasks (laundry folding, package sorting, …) without any post-training, even in unseen environments. This powerful base also allows extremely efficient fine-tuning to ~100% success on challenging new tasks with as little as 1 hour of data! 🤯 Watch it master two of them: cup stacking & celery chopping on repeat, no failures. 👇

Dyna Robotics

67,037 次观看 • 9 个月前

What does it mean for software engineering when we no longer write the code? Here's the take from Boris Cherny (Boris Cherny), the creator of Claude Code. Timestamps: 00:00 Intro 11:15 Lessons from Meta 19:46 Joining Anthropic 23:08 The origins of Claude Code 32:55 Boris's Claude Code workflow 36:27 Parallel agents 40:25 Code reviews 47:18 Claude Code's architecture 52:38 Permissions and sandboxing 55:05 Engineering culture at Anthropic 1:05:15 Claude Cowork 1:12:48 Observability and privacy 1:14:45 Agent swarms 1:21:16 LLMs and the printing press analogy 1:30:16 Standout engineer archetypes 1:32:12 What skills still matter for engineers 1:35:24 Book recommendations Brought to you by: • Statsig — ⁠ The unified platform for flags, analytics, experiments, and more. • Sonar – The makers of SonarQube, the industry standard for automated code review. Proactively find and fix issues in real-time with the SonarQube MCP Server: • WorkOS – Everything you need to make your app enterprise ready. Three interesting things from this conversation: 1. Boris automated himself out of code review well before AI. Boris was one of the most prolific code reviewers at Meta company. And he worked hard to minimize time spent on code review. His system::every time he left the same kind of review comment, he logged it in a spreadsheet. Once a pattern hit 3-4 occurrences, he’d write a lint rule to automate it away! 2. PRDs are dead on the Claude Code team: prototypes replaced them. Instead of writing Product Requirement Documents (specs), they build hundreds of working prototypes before shipping a feature. Boris: “There’s just no way we could have shipped this if we started with static mocks and Figma or if we started with a PRD.” 3. This is the year of the generalist (and maybe the year of those with ADHD) Boris’s work has shifted from deep-focus single-threaded coding to managing multiple parallel agents and context-switching rapidly. As Boris put it: “It’s not so much about deep work, it’s about how good I am at context switching and jumping across multiple different contexts very quickly.”
1:37:58

What does it mean for software engineering when we no longer write the code? Here's the take from Boris Cherny (Boris Cherny), the creator of Claude Code. Timestamps: 00:00 Intro 11:15 Lessons from Meta 19:46 Joining Anthropic 23:08 The origins of Claude Code 32:55 Boris's Claude Code workflow 36:27 Parallel agents 40:25 Code reviews 47:18 Claude Code's architecture 52:38 Permissions and sandboxing 55:05 Engineering culture at Anthropic 1:05:15 Claude Cowork 1:12:48 Observability and privacy 1:14:45 Agent swarms 1:21:16 LLMs and the printing press analogy 1:30:16 Standout engineer archetypes 1:32:12 What skills still matter for engineers 1:35:24 Book recommendations Brought to you by: • Statsig — ⁠ The unified platform for flags, analytics, experiments, and more. • Sonar – The makers of SonarQube, the industry standard for automated code review. Proactively find and fix issues in real-time with the SonarQube MCP Server: • WorkOS – Everything you need to make your app enterprise ready. Three interesting things from this conversation: 1. Boris automated himself out of code review well before AI. Boris was one of the most prolific code reviewers at Meta company. And he worked hard to minimize time spent on code review. His system::every time he left the same kind of review comment, he logged it in a spreadsheet. Once a pattern hit 3-4 occurrences, he’d write a lint rule to automate it away! 2. PRDs are dead on the Claude Code team: prototypes replaced them. Instead of writing Product Requirement Documents (specs), they build hundreds of working prototypes before shipping a feature. Boris: “There’s just no way we could have shipped this if we started with static mocks and Figma or if we started with a PRD.” 3. This is the year of the generalist (and maybe the year of those with ADHD) Boris’s work has shifted from deep-focus single-threaded coding to managing multiple parallel agents and context-switching rapidly. As Boris put it: “It’s not so much about deep work, it’s about how good I am at context switching and jumping across multiple different contexts very quickly.”

Gergely Orosz

490,123 次观看 • 5 个月前