正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

If you keep hitting Fable 5 limit Add a task-routering rule in CLAUDE.md I made a 16-min walk through of setup: - My CLAUDE.md for task-routering - Tmux skill for Fable 5 to control any other agent - Orca CLI vs Herdr CLI I open-sourced my task-routering rule +... show more

Jason Zhou

32,321 subscribers

62,389 次观看 • 15 天前 •via X (Twitter)

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

Totally settling the "MCP vs CLI for coding agents" debate with this humongous blog post. I benchmarked screen, tmux, and a bespoke custom CLI and MCP tool against 3 task that require the agent to steer TUIs (lldb, python repl, opencode)

Totally settling the "MCP vs CLI for coding agents" debate with this humongous blog post. I benchmarked screen, tmux, and a bespoke custom CLI and MCP tool against 3 task that require the agent to steer TUIs (lldb, python repl, opencode)

Mario Zechner

65,025 次观看 • 11 个月前

Someone paid $6,000 (!) to get OpenClaw setup. So I built a free, open-source alternative: > OpenClaw Operator It's an agent skill + AGENTS.md/CLAUDE.md file that gives Codex/Claude Code the playbooks + validation flow needed to configure your local OpenClaw install. You open your OpenClaw repo/workspace in your coding agent and say things like: - “set up a cron job” - “create a custom skill” - “fix my provider config” - “troubleshoot this install and validate it” Nothing magical. Uses context from the OpenClaw open-source repo + docs to provide an effective skill. Includes: - SKILL.md - AGENTS.md/CLAUDE.md - validation checklist - task playbooks Free and open source. Contributions welcome. Demo below. Repo in reply.

Someone paid $6,000 (!) to get OpenClaw setup. So I built a free, open-source alternative: > OpenClaw Operator It's an agent skill + AGENTS.md/CLAUDE.md file that gives Codex/Claude Code the playbooks + validation flow needed to configure your local OpenClaw install. You open your OpenClaw repo/workspace in your coding agent and say things like: - “set up a cron job” - “create a custom skill” - “fix my provider config” - “troubleshoot this install and validate it” Nothing magical. Uses context from the OpenClaw open-source repo + docs to provide an effective skill. Includes: - SKILL.md - AGENTS.md/CLAUDE.md - validation checklist - task playbooks Free and open source. Contributions welcome. Demo below. Repo in reply.

Dan McAteer

17,809 次观看 • 5 个月前

We open-sourced our agent skills ecosystem, built specifically for complex end-to-end browser tasks. Type in any domain, and researches an approach to reliably complete your task, contributing it back to the knowledge base for other agents. Watch our agent fetch Amazon listings in real-time, driven entirely by a custom browser skill:

We open-sourced our agent skills ecosystem, built specifically for complex end-to-end browser tasks. Type in any domain, and researches an approach to reliably complete your task, contributing it back to the knowledge base for other agents. Watch our agent fetch Amazon listings in real-time, driven entirely by a custom browser skill:

Shrey Pandya

10,312 次观看 • 2 个月前

Introducing the /autobrowse skill (inspired by Andrej Karpathy's autoresearch harness) Ask your agent to perform any task on the web: it explores the page using the Browserbase CLI, learns what went wrong in previous attempts, and iterates until it converges on a reliable workflow. Once token usage is optimized, it graduates the winning approach into a reusable skill for your browser.

Introducing the /autobrowse skill (inspired by Andrej Karpathy's autoresearch harness) Ask your agent to perform any task on the web: it explores the page using the Browserbase CLI, learns what went wrong in previous attempts, and iterates until it converges on a reliable workflow. Once token usage is optimized, it graduates the winning approach into a reusable skill for your browser.

Shrey Pandya

230,316 次观看 • 3 个月前

Been using Claude Fable all day in my AI OS and it's been noticeably better. Eats my session quicker than Opus for sure though. Here's exactly how I use Fable to run my $5M/year businesses. Give it a 5 min read.

Been using Claude Fable all day in my AI OS and it's been noticeably better. Eats my session quicker than Opus for sure though. Here's exactly how I use Fable to run my $5M/year businesses. Give it a 5 min read.

Nate Herk

286,976 次观看 • 1 个月前

ANTHROPIC'S HEAD OF ENGINEERING SAYS THEY JUST SHIPPED THE MOST CAPABLE MODELS THEY HAVE EVER BUILT Mythos 5 and Fable 5. Fable 5 can run for days on a single goal and get it right on the first pass, on work that used to need an entire team. Most people use AI to summarize things. The real leverage is the long autonomous task you keep putting off.

ANTHROPIC'S HEAD OF ENGINEERING SAYS THEY JUST SHIPPED THE MOST CAPABLE MODELS THEY HAVE EVER BUILT Mythos 5 and Fable 5. Fable 5 can run for days on a single goal and get it right on the first pass, on work that used to need an entire team. Most people use AI to summarize things. The real leverage is the long autonomous task you keep putting off.

0xMarioNawfal

57,127 次观看 • 1 个月前

I've been playing with MiniMax M3 recently. The combination of coding, agent workflows, 1M context, and multimodal understanding made me curious enough to try something real. So I gave it one task: "Build me a Skill Hub to manage all my Claude Code skills."👇

I've been playing with MiniMax M3 recently. The combination of coding, agent workflows, 1M context, and multimodal understanding made me curious enough to try something real. So I gave it one task: "Build me a Skill Hub to manage all my Claude Code skills."👇

ares. 🎧

49,239 次观看 • 2 个月前

I turned a $1,500 market research task into a 5-minute AI workflow. Now, instead of hiring analysts or buying expensive tools, my sales team gets instant competitor insights, market analysis, and presentation-ready decks. We prep for 10x more meetings and close more deals. Here's the Manus Skill I created: Try this link for 1000 free credits:

I turned a $1,500 market research task into a 5-minute AI workflow. Now, instead of hiring analysts or buying expensive tools, my sales team gets instant competitor insights, market analysis, and presentation-ready decks. We prep for 10x more meetings and close more deals. Here's the Manus Skill I created: Try this link for 1000 free credits:

FELIX

95,709 次观看 • 6 个月前

Joe Rogan says closing the skill gap with Khamzat will be a tall task for Dricus Du Plessis 👀😮 “For Dricus to come back from that and bridge the gap between him and Khamzat, that is a tall task. That kind of grappling dominance was not just a level, it was multiple levels. Dricus didn’t have any answer for that. I don’t know who he brought in to train with him, but clearly he didn’t bring in anybody that had that kind of skill.” (via ESPN MMA )

Joe Rogan says closing the skill gap with Khamzat will be a tall task for Dricus Du Plessis 👀😮 “For Dricus to come back from that and bridge the gap between him and Khamzat, that is a tall task. That kind of grappling dominance was not just a level, it was multiple levels. Dricus didn’t have any answer for that. I don’t know who he brought in to train with him, but clearly he didn’t bring in anybody that had that kind of skill.” (via ESPN MMA )

Red Corner MMA

417,957 次观看 • 11 个月前

Day 3 of 5 building with Claude Fable 5 before it goes paid. Today: an audit of everything you have already made. 1. Fable 5 reads back through all your past Claude chats 2. It flags what worked, what you dropped, and where value is going to waste 3. It ranks the top 10 fixes by effort against impact 4. Then it hands you a concrete plan for the top 3 5. Run that plan on a cheaper model and save Fable 5 for the thinking Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 4 tomorrow.

Day 3 of 5 building with Claude Fable 5 before it goes paid. Today: an audit of everything you have already made. 1. Fable 5 reads back through all your past Claude chats 2. It flags what worked, what you dropped, and where value is going to waste 3. It ranks the top 10 fixes by effort against impact 4. Then it hands you a concrete plan for the top 3 5. Run that plan on a cheaper model and save Fable 5 for the thinking Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 4 tomorrow.

Charlie Hills

13,617 次观看 • 1 个月前

Introducing Compound Skills 🪄 You can now train the AI analyst in your way of working, just like you would a human. Ask Compound to create a Skill for any task (e.g. DCFs, waterfall modeling). Compound remembers your preferences and will apply it the next time it works on a similar task. You can also ask Compound to update skills, if you’ve provided more feedback during a task, or simply if you want to iterate on a skill. With Skills, Compound has become more powerful than ever - continually learning and adapting to your preferences. Try it now today at P.S For new users, get a one-time signup bonus of 40K free credits. You can also refer a friend (check settings for a link), and you’ll both get 10K free credits.

Introducing Compound Skills 🪄 You can now train the AI analyst in your way of working, just like you would a human. Ask Compound to create a Skill for any task (e.g. DCFs, waterfall modeling). Compound remembers your preferences and will apply it the next time it works on a similar task. You can also ask Compound to update skills, if you’ve provided more feedback during a task, or simply if you want to iterate on a skill. With Skills, Compound has become more powerful than ever - continually learning and adapting to your preferences. Try it now today at P.S For new users, get a one-time signup bonus of 40K free credits. You can also refer a friend (check settings for a link), and you’ll both get 10K free credits.

Compound AI

16,746 次观看 • 6 个月前

I'm open-sourcing tws, the tool I've been using for the last few months to organize my engineering work. I've always been a terminal-first engineer; tmux + nvim has been my default. Then AI coding agents arrived and shifted what I needed from that setup. Running several Claude Code and Codex sessions in parallel, the flat tmux session list stopped being enough. So I built tws to fit how I actually work now. It's built on top of tmux, no reinvented wheel. You keep all of tmux's power and flexibility underneath. On top of that, it gives you: - Threads: an abstract organizational layer above tmux sessions, so related work groups together instead of sitting in a flat list - Notes: quick markdown notes attached to each thread or session, kept right next to your work - Fast switching: fuzzy finding, recent-session jumps, and keyboard-driven navigation between everything - Agents view: every Claude Code / Codex session running across your projects in one place, with the ability to pin the ones you keep coming back to Fully configurable — themes, palette, keybindings — via a TOML file. If tmux + terminal isn't your setup, this probably isn't for you. But if you like working from terminal, you might like it. It's been the core piece of how I work for a while now. Github:

I'm open-sourcing tws, the tool I've been using for the last few months to organize my engineering work. I've always been a terminal-first engineer; tmux + nvim has been my default. Then AI coding agents arrived and shifted what I needed from that setup. Running several Claude Code and Codex sessions in parallel, the flat tmux session list stopped being enough. So I built tws to fit how I actually work now. It's built on top of tmux, no reinvented wheel. You keep all of tmux's power and flexibility underneath. On top of that, it gives you: - Threads: an abstract organizational layer above tmux sessions, so related work groups together instead of sitting in a flat list - Notes: quick markdown notes attached to each thread or session, kept right next to your work - Fast switching: fuzzy finding, recent-session jumps, and keyboard-driven navigation between everything - Agents view: every Claude Code / Codex session running across your projects in one place, with the ability to pin the ones you keep coming back to Fully configurable — themes, palette, keybindings — via a TOML file. If tmux + terminal isn't your setup, this probably isn't for you. But if you like working from terminal, you might like it. It's been the core piece of how I work for a while now. Github:

Yusuf

220,215 次观看 • 2 个月前

540,000 lines of Rails is a brutal way to learn the agent era Garry's List shipped with: > 262,000 lines of app code > 276,000 lines of tests > 127 background jobs > 33 cron jobs > a 1,778-line claim verifier Then GStack hit 105k GitHub stars Do not copy the Rails pattern 1. Finish the task with an agent 2. Say `skillify it` 3. Save the markdown skill 4. Keep TypeScript only for deterministic I/O 5. Add a unit test for the code 6. Add an LLM eval for the skill 7. Add an integration test across both 8. Add a resolver so the agent loads the skill next time A Rails feature serves one app A skill pack can run against the next hackathon, repo, customer inbox, research folder, or QA run Audit your repo this week Cut code that only exists to: > re-check model output > retry the same model call > validate what the model already has context for > schedule work because the agent has no reusable procedure > preserve a one-off prompt in chat history Keep the code that touches files, APIs, auth, billing, devices, databases Move the judgment into markdown Test the markdown Reuse the skill

540,000 lines of Rails is a brutal way to learn the agent era Garry's List shipped with: > 262,000 lines of app code > 276,000 lines of tests > 127 background jobs > 33 cron jobs > a 1,778-line claim verifier Then GStack hit 105k GitHub stars Do not copy the Rails pattern 1. Finish the task with an agent 2. Say `skillify it` 3. Save the markdown skill 4. Keep TypeScript only for deterministic I/O 5. Add a unit test for the code 6. Add an LLM eval for the skill 7. Add an integration test across both 8. Add a resolver so the agent loads the skill next time A Rails feature serves one app A skill pack can run against the next hackathon, repo, customer inbox, research folder, or QA run Audit your repo this week Cut code that only exists to: > re-check model output > retry the same model call > validate what the model already has context for > schedule work because the agent has no reusable procedure > preserve a one-off prompt in chat history Keep the code that touches files, APIs, auth, billing, devices, databases Move the judgment into markdown Test the markdown Reuse the skill

Alpha Batcher

35,693 次观看 • 2 个月前

happy friday. sneak peek at some new features i'm building for the bankr agent: > sandboxed filesystem (your agent gets its own secure file system in the browser. you control what it can access. no agent running loose on your actual computer) > skill uploads (plugin new capabilities so your agent learns new things) > cli download & access > secure environment variables for api keys > github integration (connect your repo for reads and writes directly from your agent) all of this runs in a secure browser environment. no desktop app. no messy configuration. no downloading agent harnesses from the terminal. just a sandbox you control. in the video: i download an audit skill, run it against a smart contract, and save the report straight to the filesystem. then i ask the agent to pull all my 2026 transactions and write a csv for my accountant.

happy friday. sneak peek at some new features i'm building for the bankr agent: > sandboxed filesystem (your agent gets its own secure file system in the browser. you control what it can access. no agent running loose on your actual computer) > skill uploads (plugin new capabilities so your agent learns new things) > cli download & access > secure environment variables for api keys > github integration (connect your repo for reads and writes directly from your agent) all of this runs in a secure browser environment. no desktop app. no messy configuration. no downloading agent harnesses from the terminal. just a sandbox you control. in the video: i download an audit skill, run it against a smart contract, and save the report straight to the filesystem. then i ask the agent to pull all my 2026 transactions and write a csv for my accountant.

deployer

45,638 次观看 • 3 个月前

Fable 5 is gone, but agents are here to stay. I sat down with Nevo who shared the playbook he used to hit $118k/month building for agents: > The one file that makes you agent-ready (1:15) > Why agents prefer a CLI to your API (2:23) > The X article growth hack (3:24)

Fable 5 is gone, but agents are here to stay. I sat down with Nevo who shared the playbook he used to hit $118k/month building for agents: > The one file that makes you agent-ready (1:15) > Why agents prefer a CLI to your API (2:23) > The X article growth hack (3:24)

Rob Hallam

98,321 次观看 • 1 个月前

I was wrong about Kimi K3 Just tried it in Claude Code and it is Fable 5 level for sure Far better than GPT-5.6 Sol at least at front-end It is really slow and consumes a lot of tokens but it is so good at completing its task, I like what I see here Kimi.ai

I was wrong about Kimi K3 Just tried it in Claude Code and it is Fable 5 level for sure Far better than GPT-5.6 Sol at least at front-end It is really slow and consumes a lot of tokens but it is so good at completing its task, I like what I see here Kimi.ai

Hamza

258,366 次观看 • 20 天前

This is exactly what i was hoping for... - Full permissions - no "cowork" like feature which limits agent abilities - Just codex... If you ask for coding task it writes code and gives you a preview. If you ask for a presentation or doc it gives you a presentation or doc. Organized by project on the left side bar. Easy to create skills, easy to @ mention skills / plugins Btw my Readwise automation is insane. Every morning it codex sends me a deck of all my x bookmarks organized by topic. And i highly recommend using the excaladraw skill to render diagrams into docs.

This is exactly what i was hoping for... - Full permissions - no "cowork" like feature which limits agent abilities - Just codex... If you ask for coding task it writes code and gives you a preview. If you ask for a presentation or doc it gives you a presentation or doc. Organized by project on the left side bar. Easy to create skills, easy to @ mention skills / plugins Btw my Readwise automation is insane. Every morning it codex sends me a deck of all my x bookmarks organized by topic. And i highly recommend using the excaladraw skill to render diagrams into docs.

Riley Brown

65,403 次观看 • 3 个月前

This is how you get 15x fable 5 usage. Fable -> Composer 2.5 reading Fable -> GPT 5.5 execution I built CNVS to make agent orchestration dead simple and insanely visual. You can watch fable 5 delegate work to cursor, codex, open code, all your agents. using your exsisting ai subs no api pricing. The canvas is fully voice controlled locally with nvidia parakeet for fast and free, or gpt realtime 2 for a fully conversational jarvis experience. The built in mcp and cli means agentic control is bidirectional they can prompt and spawn each other and read agent states. but there is more I built it from the ground up in swift for native performance on mac os. My old 16gb m1 mbp can easily spin up and control eight agents across multiple canvasses. The hermes integration + remote canvases allow you to run agents fully in the cloud on your VPS think google docs of vibe coding. You can literally turn off your mac and they keep working, open cnvs back up and pick up where you left off. I built a cross agent memory system based on 2026 research so all your agents feel like one brain. its SIMPLE and on demand. This eliminates context bloat, and the research supports a massive uptick in cross agent performance. There is soo much more. PS - I am a father building this project 100% solo in my basement on live stream everyday, my goal is to push vibe coding to the next level PPS - CNVS is a lifetime license becuase you DO NOT need another subscription in your life.

This is how you get 15x fable 5 usage. Fable -> Composer 2.5 reading Fable -> GPT 5.5 execution I built CNVS to make agent orchestration dead simple and insanely visual. You can watch fable 5 delegate work to cursor, codex, open code, all your agents. using your exsisting ai subs no api pricing. The canvas is fully voice controlled locally with nvidia parakeet for fast and free, or gpt realtime 2 for a fully conversational jarvis experience. The built in mcp and cli means agentic control is bidirectional they can prompt and spawn each other and read agent states. but there is more I built it from the ground up in swift for native performance on mac os. My old 16gb m1 mbp can easily spin up and control eight agents across multiple canvasses. The hermes integration + remote canvases allow you to run agents fully in the cloud on your VPS think google docs of vibe coding. You can literally turn off your mac and they keep working, open cnvs back up and pick up where you left off. I built a cross agent memory system based on 2026 research so all your agents feel like one brain. its SIMPLE and on demand. This eliminates context bloat, and the research supports a massive uptick in cross agent performance. There is soo much more. PS - I am a father building this project 100% solo in my basement on live stream everyday, my goal is to push vibe coding to the next level PPS - CNVS is a lifetime license becuase you DO NOT need another subscription in your life.

Max Blade

29,504 次观看 • 1 个月前

Battle Mode : Kimi K3 vs GPT-5.6 Prompt : Please devote your efforts to creating a large-scale 3D photorealistic procedural visualization of meteor hitting the city in one html code block if anyone can share fable-5 i will run that in parallel for comparison

Battle Mode : Kimi K3 vs GPT-5.6 Prompt : Please devote your efforts to creating a large-scale 3D photorealistic procedural visualization of meteor hitting the city in one html code block if anyone can share fable-5 i will run that in parallel for comparison

Chetaslua

57,022 次观看 • 21 天前

Found a way to run Kimi K3 for FREE with daily credits on 😳 it's a 2.8T parameter model. 1M context. beats Fable 5 on coding benchmarks. what you get for $0: -2.8 trillion parameters -1M context window -beats Fable 5 on SWE Marathon (42 vs 35) -beats Fable 5 on Program Bench (77.8) -topped BrowseComp (91.2) -native vision understanding What this replaces: -Paid frontier API costs for coding agents -Fable 5 at $30/M output tokens -GPT-5.6 Sol at $25/M output tokens how to use it (2 min): 1. Go to 2. Sign up with email 3. Start using K3 — it's the default model Also available on desktop app, CLI, and mobile. Important: Free daily credits reset. Full open weights dropping July 27. Rate limits apply on free tier. use this before the free tier gets crowded

Found a way to run Kimi K3 for FREE with daily credits on 😳 it's a 2.8T parameter model. 1M context. beats Fable 5 on coding benchmarks. what you get for $0: -2.8 trillion parameters -1M context window -beats Fable 5 on SWE Marathon (42 vs 35) -beats Fable 5 on Program Bench (77.8) -topped BrowseComp (91.2) -native vision understanding What this replaces: -Paid frontier API costs for coding agents -Fable 5 at $30/M output tokens -GPT-5.6 Sol at $25/M output tokens how to use it (2 min): 1. Go to 2. Sign up with email 3. Start using K3 — it's the default model Also available on desktop app, CLI, and mobile. Important: Free daily credits reset. Full open weights dropping July 27. Rate limits apply on free tier. use this before the free tier gets crowded

painn

252,185 次观看 • 18 天前