Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Friday. 5:47 PM. Quick Claude session, small auth refactor. LGTM, merge, done. Monday, 10:00 AM. SSO is broken in production. Introducing Canary, the AI QA engineer that reads your codebase and catches broken user flows before production. Check it out at Congrats on the launch, Viswesh N G and team!

Y Combinator

1,654,072 subscribers

19,809 Aufrufe • vor 7 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

16 Kommentare

Profilbild von Afore Capital

Afore Capitalvor 7 Monaten

@RunCanary congrats @g_viswesh and team

Profilbild von conor brennan-burke

conor brennan-burkevor 7 Monaten

@RunCanary we love the product, super helpful to save time and effort on QA

Profilbild von jack mcclelland

jack mcclellandvor 7 Monaten

@RunCanary congrats on the launch

Profilbild von catherine jue

catherine juevor 7 Monaten

@RunCanary Congrats on the launch!!

Profilbild von sabir hussain

sabir hussainvor 7 Monaten

@RunCanary AI QA before prod saves serious headaches.

Profilbild von Cognixlab

Cognixlabvor 7 Monaten

@RunCanary Congrats on the launch, @g_viswesh and team!

Profilbild von Adarsh Kr Singh

Adarsh Kr Singhvor 7 Monaten

@RunCanary Huge congrats @g_viswesh & team! Finally an AI QA tool that actually groks the codebase instead of just poking at pixels. This could save so many Monday morning fires

Profilbild von Deals Dhamaka

Deals Dhamakavor 7 Monaten

@RunCanary SSO is the absolute worst place to trust an LLM with a quick auth refactor.

Profilbild von Hamza Ali

Hamza Alivor 7 Monaten

@RunCanary Congrats on the launch

Profilbild von Shamim Hossain

Shamim Hossainvor 7 Monaten

@RunCanary That’s great

Profilbild von Gregor

Gregorvor 7 Monaten

I've never had a Claude session catch auth refactors, but I'm curious, have you considered how @RunCanary would handle subtle changes to your existing codebase that aren't immediately apparent in a small refactor? What kind of edge cases would you use to test its effectiveness in this scenario?

Profilbild von ikan laut

ikan lautvor 7 Monaten

@RunCanary this is very interesting

Profilbild von Ramraj Velmurugan

Ramraj Velmuruganvor 7 Monaten

@RunCanary How do you make videos like this?

Profilbild von conor brennan-burke

conor brennan-burkevor 7 Monaten

@RunCanary let's goo

Profilbild von Clawdpad

Clawdpadvor 7 Monaten

The real question: can it catch the bugs that exist specifically because humans knew a fix was 'safe' based on intuition rather than verification? Most production outages trace back to confident assumptions, not uncertain ones. Does RunCanary model the confidence-error correlation?

Profilbild von Dog

Dogvor 7 Monaten

@RunCanary Someone gotta QA their website because the CTAs don’t fit

Ähnliche Videos

Elon Musk and the xAI team worked tirelessly until 5 in the morning, installing supercomputers at the xAI Data Center in Memphis, all in just 19 days, the fastest anyone has ever done it. Grok 3 is coming out on Monday night at 8 PM PT. It will be the smartest AI in the World!

Elon Musk and the xAI team worked tirelessly until 5 in the morning, installing supercomputers at the xAI Data Center in Memphis, all in just 19 days, the fastest anyone has ever done it. Grok 3 is coming out on Monday night at 8 PM PT. It will be the smartest AI in the World!

SMX 🇺🇸

1,391,470 Aufrufe • vor 1 Jahr

Today we're shipping Oasis Desktop, a Mac app that lets you share local coding agents with your teammates. Oasis Desktop can spin up and share Claude Code, Codex, Pi, OpenCode, Kilo Code, Hermes Agent, and Devin CLI sessions as long as they're installed. Start a session with your team. Bring in Claude Code and say, “What is wrong with auth. The tests have been failing since Tuesday. Help us figure it out.” The agent reads the files and runs the test suite directly on your laptop. When it asks, “Why did we replace the session middleware last week?” your teammate can answer in the exact same session. Completely free - try it out today:

Today we're shipping Oasis Desktop, a Mac app that lets you share local coding agents with your teammates. Oasis Desktop can spin up and share Claude Code, Codex, Pi, OpenCode, Kilo Code, Hermes Agent, and Devin CLI sessions as long as they're installed. Start a session with your team. Bring in Claude Code and say, “What is wrong with auth. The tests have been failing since Tuesday. Help us figure it out.” The agent reads the files and runs the test suite directly on your laptop. When it asks, “Why did we replace the session middleware last week?” your teammate can answer in the exact same session. Completely free - try it out today:

Oasis

215,176 Aufrufe • vor 1 Monat

New on Claude Code Desktop We’re shipping new features for Claude Code on desktop that let you preview running apps, auto-review code, and auto-fix and merge PRs to help close the development loop. - Server previews: Claude starts dev servers and previews your running app in the desktop interface. It reads console logs, catches errors, and keeps iterating on its own. - Local code review: Claude examines your local diffs and leaves inline comments before you push — an immediate second set of eyes on every change. - PR monitoring: Claude tracks CI status after you open a PR. With auto-fix, it attempts to resolve failures automatically. With auto-merge, PRs land as soon as checks pass. You can move on to your next task while Claude handles the last one. - Session mobility: Move sessions from CLI to desktop, and from desktop to the cloud. Start work at your desk, pick it up from the web or your phone.

New on Claude Code Desktop We’re shipping new features for Claude Code on desktop that let you preview running apps, auto-review code, and auto-fix and merge PRs to help close the development loop. - Server previews: Claude starts dev servers and previews your running app in the desktop interface. It reads console logs, catches errors, and keeps iterating on its own. - Local code review: Claude examines your local diffs and leaves inline comments before you push — an immediate second set of eyes on every change. - PR monitoring: Claude tracks CI status after you open a PR. With auto-fix, it attempts to resolve failures automatically. With auto-merge, PRs land as soon as checks pass. You can move on to your next task while Claude handles the last one. - Session mobility: Move sessions from CLI to desktop, and from desktop to the cloud. Start work at your desk, pick it up from the web or your phone.

Ado

71,910 Aufrufe • vor 7 Monaten

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

Dan Shipper

66,871 Aufrufe • vor 5 Monaten

Today, I'm excited to launch Entelligence AI DeepReviews, the next generation AI-powered code reviews. Vibe coded PRs are not production ready often creating more subtle bugs throughout the codebase than before. Entelligence fixes this by understanding the entire codebase and flags bugs, regressions, and breakages across files before you ship. But it goes beyond review comments: ✅ Auto-generated docs with architecture diagrams ✅ Team Insights to improve process, not just code ✅ Real time code reviews within your editor If you're building or leading a dev team, this is what smarter, context-aware reviews look like. Try it out in the link below 👇

Today, I'm excited to launch Entelligence AI DeepReviews, the next generation AI-powered code reviews. Vibe coded PRs are not production ready often creating more subtle bugs throughout the codebase than before. Entelligence fixes this by understanding the entire codebase and flags bugs, regressions, and breakages across files before you ship. But it goes beyond review comments: ✅ Auto-generated docs with architecture diagrams ✅ Team Insights to improve process, not just code ✅ Real time code reviews within your editor If you're building or leading a dev team, this is what smarter, context-aware reviews look like. Try it out in the link below 👇

Aiswarya Sankar

96,309 Aufrufe • vor 1 Jahr

Anthropic just released 5 Claude workshops on the new skill every AI builder needs: Loop Engineering: 00:00 - Stop babysitting your agents 37:07 - Build a proactive Claude Code loop 1:11:23 - Build a production-ready Managed Agent 1:38:46 - Teach agents to learn from your team 2:07:15 - Hill-climb your agent with eval loops It is a 2 hour and 25 minute blueprint for Loop Engineering: proactive workflows, managed agents, team feedback, evals, and self-improvement. Watch it today, and read the article below to improve your skills with Fable 5.

Anthropic just released 5 Claude workshops on the new skill every AI builder needs: Loop Engineering: 00:00 - Stop babysitting your agents 37:07 - Build a proactive Claude Code loop 1:11:23 - Build a production-ready Managed Agent 1:38:46 - Teach agents to learn from your team 2:07:15 - Hill-climb your agent with eval loops It is a 2 hour and 25 minute blueprint for Loop Engineering: proactive workflows, managed agents, team feedback, evals, and self-improvement. Watch it today, and read the article below to improve your skills with Fable 5.

Alex

47,626 Aufrufe • vor 3 Monaten

Anthropic Claude Code engineer: "If you're watching Claude write code, you're the QA tester. That's not what you're paid for." In 37 minutes he lays out how to get your keyboard out of the hot path entirely. The shift is /loop. You tell Claude to wake up every 10 minutes and babysit your PRs, and it just does it, while you're nowhere near the laptop. Routines do the same in the cloud, so the work keeps running with your machine closed. He caps it with remote control: any session, on any surface, driven from your phone. Watch the full talk, then grab the setup below.

Anthropic Claude Code engineer: "If you're watching Claude write code, you're the QA tester. That's not what you're paid for." In 37 minutes he lays out how to get your keyboard out of the hot path entirely. The shift is /loop. You tell Claude to wake up every 10 minutes and babysit your PRs, and it just does it, while you're nowhere near the laptop. Routines do the same in the cloud, so the work keeps running with your machine closed. He caps it with remote control: any session, on any surface, driven from your phone. Watch the full talk, then grab the setup below.

Hanako

692,778 Aufrufe • vor 3 Monaten

Building a high converting app onboarding flow is hard.. So I built a Claude Skill that does it for me Instead of spending hours figuring out the right questions and pain points… now it's done in 5 minutes Just point it at your codebase and it does the rest Questionnaires. Custom plans. App demos. The exact strategy used by Cal AI ($1M/mo) and Mob ($100k/mo) It's the App Onboarding Questionnaire skill and it's available on github here:

Building a high converting app onboarding flow is hard.. So I built a Claude Skill that does it for me Instead of spending hours figuring out the right questions and pain points… now it's done in 5 minutes Just point it at your codebase and it does the rest Questionnaires. Custom plans. App demos. The exact strategy used by Cal AI ($1M/mo) and Mob ($100k/mo) It's the App Onboarding Questionnaire skill and it's available on github here:

Adam Lyttle

256,240 Aufrufe • vor 6 Monaten

Introducing Merge’s Universal Context Layer. It substantially decreases token cost while increasing accuracy. Every company uses AI wrong: Say your designer makes a deck using Claude. They teach Claude your design systems and typography. Now a Marketing hire makes a deck. None of the information your designer taught Claude gets passed over… why? Merge fixes this: All knowledge and memory across your entire company gets stored inside our context layer. When someone on the org teaches Al, that skill lives across the entire organization instead of staying locked in their session. Your AI runs faster, cheaper, and with more accuracy. You don’t have to switch systems, incur more costs, or retrain anyone on your team, Merge runs invisibly in the background. Book a demo here:

Introducing Merge’s Universal Context Layer. It substantially decreases token cost while increasing accuracy. Every company uses AI wrong: Say your designer makes a deck using Claude. They teach Claude your design systems and typography. Now a Marketing hire makes a deck. None of the information your designer taught Claude gets passed over… why? Merge fixes this: All knowledge and memory across your entire company gets stored inside our context layer. When someone on the org teaches Al, that skill lives across the entire organization instead of staying locked in their session. Your AI runs faster, cheaper, and with more accuracy. You don’t have to switch systems, incur more costs, or retrain anyone on your team, Merge runs invisibly in the background. Book a demo here:

Shensi Ding

599,942 Aufrufe • vor 29 Tagen

The team at TARS AI 🤖 have been head-down and building lately, but I made it out to the AWS GenAI Loft launch in Manchester last week, and I’m glad I did. It was great to connect with builders, devs, and the AWS team who are all in on GenAI. Lots of real talk about what’s actually working, whats just noise, and how companies are moving AI into production, not just POCs. At TARS AI, we’ve been deep in the lab working on something new and exciting. Events like this give us even more conviction that we’re on the right path. The space is heating up every single day, and the team are cooking! 🔥

The team at TARS AI 🤖 have been head-down and building lately, but I made it out to the AWS GenAI Loft launch in Manchester last week, and I’m glad I did. It was great to connect with builders, devs, and the AWS team who are all in on GenAI. Lots of real talk about what’s actually working, whats just noise, and how companies are moving AI into production, not just POCs. At TARS AI, we’ve been deep in the lab working on something new and exciting. Events like this give us even more conviction that we’re on the right path. The space is heating up every single day, and the team are cooking! 🔥

Richard ₿

27,352 Aufrufe • vor 1 Jahr

Wonderful news, our work is being featured in a documentary on CNN Call to Earth this weekend! The full documentary, “Kings of the Forest,” featuring the critical work that Conservation Through Public Health is doing with Uganda Wildlife Authority to protect the endangered mountain gorillas, will air on CNN Call to Earth on: 📅 Saturday March 29 🕔 EST (USA): 1:30 AM, 6:30 AM, 9:30 PM 🕔 Uganda: 8:30 AM, 1:30 PM, 4:30 PM 📅 Sunday March 30 🕔 EST (USA): 2:30 AM, 1:30 PM, 11:00 PM 🕔 Uganda: 9:30 AM, 8:30 PM, Monday March 31 at 6:00 AM There will be short clips airing during Connect the World and Quest Means Business news segments this Thursday and Friday during the one or two hour programs beginning at: 📅 March 27, and 28 🕙 Eastern Time (USA): 10:00 AM and 4:00 PM 🕔 Uganda Time (East Africa): 5:00 PM and 11:00 PM Join us in celebrating this milestone and hope you enjoy the program. #WalkingWithGorillas #GladysOnCNN #PerpetualPlanet #CalltoEarth #visituganda

Wonderful news, our work is being featured in a documentary on CNN Call to Earth this weekend! The full documentary, “Kings of the Forest,” featuring the critical work that Conservation Through Public Health is doing with Uganda Wildlife Authority to protect the endangered mountain gorillas, will air on CNN Call to Earth on: 📅 Saturday March 29 🕔 EST (USA): 1:30 AM, 6:30 AM, 9:30 PM 🕔 Uganda: 8:30 AM, 1:30 PM, 4:30 PM 📅 Sunday March 30 🕔 EST (USA): 2:30 AM, 1:30 PM, 11:00 PM 🕔 Uganda: 9:30 AM, 8:30 PM, Monday March 31 at 6:00 AM There will be short clips airing during Connect the World and Quest Means Business news segments this Thursday and Friday during the one or two hour programs beginning at: 📅 March 27, and 28 🕙 Eastern Time (USA): 10:00 AM and 4:00 PM 🕔 Uganda Time (East Africa): 5:00 PM and 11:00 PM Join us in celebrating this milestone and hope you enjoy the program. #WalkingWithGorillas #GladysOnCNN #PerpetualPlanet #CalltoEarth #visituganda

Gladys K Zikusoka

14,218 Aufrufe • vor 1 Jahr

Claude Code + computer use is f*cking cracked 🤯 Build a landing page → Claude opens Chrome, looks at it, spots every issue, and fixes it — without you describing a single thing. All inside Claude Code. Perfect for DTC brands and agencies who are still vibe-coding landing pages and advertorials in Claude Code, then manually opening them in Chrome, spotting 15 things wrong, and describing every visual issue back to Claude one at a time. If you're building pages in Claude Code and your workflow looks like this — build the page, open it in Chrome, spot broken spacing, go back to Claude, type "the CTA button is too low and the hero image is cut off," wait for the fix, open Chrome again, find 3 new issues, describe those too ... Claude Code + computer use eliminates the entire loop: → Claude writes the full landing page or advertorial → Opens Chrome and navigates to it → Spots layout issues, broken spacing, off-brand colors, missing elements → Fixes everything and re-checks until the page looks right → Tests your Shopify product pages by clicking through like a real customer → Walks through your checkout flow and flags friction before customers hit it → You only see the finished, visually verified result No describing what you see on screen. No "the CTA button needs more contrast" back-and-forth. No being the eyeballs for an AI that can't see. What you get: → Landing pages and advertorials Claude builds AND visually QAs before you ever look at them → Product pages Claude clicks through — testing layout, images, and CTAs like a real user → HTML dashboards Claude opens and verifies the charts actually render → Checkout flows Claude walks through step by step to catch friction → All of it happening in one session — build, test, fix, done One prompt. Claude builds it, checks it, and fixes it. You just review the finished page. I put together a full playbook with the exact setup, the prompts, and 5 DTC workflows that use Claude Code + computer use. Want it for free? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)

Mike Futia

19,249 Aufrufe • vor 6 Monaten

The first campaign Viktor reviewed caught problems we didn't even know were there. We're a digital marketing team managing campaigns across multiple ad platforms, and before every launch someone on the team would manually check tracking, landing pages, targeting, budgets, creatives, and campaign settings. It was repetitive work, but missing just one detail could turn into wasted budget or inaccurate reporting. Instead of asking Viktor to help with individual checks, we gave him ownership of our entire campaign launch QA workflow. The first thing that stood out wasn't how quickly he worked. It was how thorough he was. Across one month, Viktor completed QA for 30 campaigns, executed 330 automated checks, and identified 47 issues, including 14 critical errors that could have affected campaign performance before a single campaign went live. By the time our team stepped in, all that was left was reviewing his findings and approving the launch. That completely changed the way we approached campaign launches. Instead of spending 65 hours every month on manual QA, our workflow was reduced to just 10.5 hours of strategic review giving our team back an estimated 54.5 hours to focus on optimization instead of repetitive checks. The biggest takeaway wasn't the time we saved. It was knowing every campaign went through the same level of quality control before launch. That's the difference we've started seeing between an AI assistant and an AI employee. An assistant waits for prompts. An AI employee owns recurring work while your team focuses on the decisions that matter most. Every campaign your team launches without this is a risk someone on your team is quietly absorbing. A copilot helps you work. An AI employee works when you don't. Hire Viktor for your team. $100 in credits included, no card. Full link in first comment. #AIemployee #MarketingOps #DigitalMarketing Paid Partnership

The first campaign Viktor reviewed caught problems we didn't even know were there. We're a digital marketing team managing campaigns across multiple ad platforms, and before every launch someone on the team would manually check tracking, landing pages, targeting, budgets, creatives, and campaign settings. It was repetitive work, but missing just one detail could turn into wasted budget or inaccurate reporting. Instead of asking Viktor to help with individual checks, we gave him ownership of our entire campaign launch QA workflow. The first thing that stood out wasn't how quickly he worked. It was how thorough he was. Across one month, Viktor completed QA for 30 campaigns, executed 330 automated checks, and identified 47 issues, including 14 critical errors that could have affected campaign performance before a single campaign went live. By the time our team stepped in, all that was left was reviewing his findings and approving the launch. That completely changed the way we approached campaign launches. Instead of spending 65 hours every month on manual QA, our workflow was reduced to just 10.5 hours of strategic review giving our team back an estimated 54.5 hours to focus on optimization instead of repetitive checks. The biggest takeaway wasn't the time we saved. It was knowing every campaign went through the same level of quality control before launch. That's the difference we've started seeing between an AI assistant and an AI employee. An assistant waits for prompts. An AI employee owns recurring work while your team focuses on the decisions that matter most. Every campaign your team launches without this is a risk someone on your team is quietly absorbing. A copilot helps you work. An AI employee works when you don't. Hire Viktor for your team. $100 in credits included, no card. Full link in first comment. #AIemployee #MarketingOps #DigitalMarketing Paid Partnership

Kylie

92,501 Aufrufe • vor 2 Monaten

SpaceXAI just dropped a GrokBot that works for you while you sleep: "I am running this GrokBot before I go to sleep. I wake up and task is done" here's how the Nightly Engineer works: • every night → researches the whole codebase and finds cleanup opportunities • one area → one focused cleanup PR instead of one giant refactor • verification → reproduce the issue first, then test the actual fix • by 4am → the audit is done and your cleanup PRs are waiting the result: → you go to sleep with a messy codebase → you wake up with researched, scoped cleanup PRs SpaceXAI basically turned code maintenance into a 24/7 GrokBot routine save now, then read how to build a 24/7 GrokBot agent team in the article below

SpaceXAI just dropped a GrokBot that works for you while you sleep: "I am running this GrokBot before I go to sleep. I wake up and task is done" here's how the Nightly Engineer works: • every night → researches the whole codebase and finds cleanup opportunities • one area → one focused cleanup PR instead of one giant refactor • verification → reproduce the issue first, then test the actual fix • by 4am → the audit is done and your cleanup PRs are waiting the result: → you go to sleep with a messy codebase → you wake up with researched, scoped cleanup PRs SpaceXAI basically turned code maintenance into a 24/7 GrokBot routine save now, then read how to build a 24/7 GrokBot agent team in the article below

0xRafy

16,491 Aufrufe • vor 21 Tagen

Claude Code tip: once Opus 5.5 is your main model, stop letting your Fable 5.1 quota go to waste put it on call with /advisor run /advisor fable Opus 5.5 keeps doing the work Fable 5.1 sits on the sidelines, reads the whole session, and steps in at three moments: → before a plan: is this right? → when the same error comes back: am I going the wrong way? → before "done": did I miss anything? Fable 5.1 advises. Opus 5.5 writes the code the same idea sits under Jev engineering: the expensive model stops weighing in on every step and only gets called at the moments that change the outcome • the full setup > Opus 5.5 on high runs the main session > subagent one reads code > subagent two edits and runs tests > subagent three looks up docs > all three on medium > Fable 5.1 on call hand the tree and this prompt to Claude Code 👇 "Set up my Claude Code to match this tree: 1. Reuse fitting subagents from ~/.claude/agents and .claude/agents. > Propose new ones only for missing roles > Set each to model: opus, effort: medium > Leave any that set a different model alone and list them 2. Set main session effort to high via effortLevel in ~/.claude/settings.json 3. Check for env vars that disable the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, anything that stops flag fetching) and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, don't change them 4. Add a rule to ~/.claude/CLAUDE.md: ask the advisor before a big plan, when an error repeats, and before calling a long task done Show me the changes first. Don't edit files yet." ↳

Claude Code tip: once Opus 5.5 is your main model, stop letting your Fable 5.1 quota go to waste put it on call with /advisor run /advisor fable Opus 5.5 keeps doing the work Fable 5.1 sits on the sidelines, reads the whole session, and steps in at three moments: → before a plan: is this right? → when the same error comes back: am I going the wrong way? → before "done": did I miss anything? Fable 5.1 advises. Opus 5.5 writes the code the same idea sits under Jev engineering: the expensive model stops weighing in on every step and only gets called at the moments that change the outcome • the full setup > Opus 5.5 on high runs the main session > subagent one reads code > subagent two edits and runs tests > subagent three looks up docs > all three on medium > Fable 5.1 on call hand the tree and this prompt to Claude Code 👇 "Set up my Claude Code to match this tree: 1. Reuse fitting subagents from ~/.claude/agents and .claude/agents. > Propose new ones only for missing roles > Set each to model: opus, effort: medium > Leave any that set a different model alone and list them 2. Set main session effort to high via effortLevel in ~/.claude/settings.json 3. Check for env vars that disable the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, anything that stops flag fetching) and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, don't change them 4. Add a rule to ~/.claude/CLAUDE.md: ask the advisor before a big plan, when an error repeats, and before calling a long task done Show me the changes first. Don't edit files yet." ↳

Mr. Buzzoni

324,448 Aufrufe • vor 11 Tagen

THIS CS TEACHER CONTROLS 4 CLAUDE CODE INSTANCES WITH HIS EYES AND VOICE - AND THEY FIX THEIR OWN MISTAKES AUTOMATICALLY He runs 4 Claude terminals at once - no mouse, no keyboard - eye tracking highlights the window he's looking at and voice dictation sends the prompt the moment he stops talking. But the real setup is what happens inside those terminals. Claude Code has zero memory of what went wrong last session - same bug that took 20 minutes to fix yesterday will happen again tomorrow unless you configure it correctly. His CLAUDE.md grows every time Claude makes a mistake - specific rules Claude reads before touching a single line - and PostToolUse hooks auto-format and type-check every file the moment it's written. Stop hooks run tests automatically when Claude says "done" - if they fail, Claude reads the errors and keeps fixing without any manual input. Before: 45 minutes of back-and-forth per feature, same mistakes on repeat - after: 10 minutes, most of it unattended.

THIS CS TEACHER CONTROLS 4 CLAUDE CODE INSTANCES WITH HIS EYES AND VOICE - AND THEY FIX THEIR OWN MISTAKES AUTOMATICALLY He runs 4 Claude terminals at once - no mouse, no keyboard - eye tracking highlights the window he's looking at and voice dictation sends the prompt the moment he stops talking. But the real setup is what happens inside those terminals. Claude Code has zero memory of what went wrong last session - same bug that took 20 minutes to fix yesterday will happen again tomorrow unless you configure it correctly. His CLAUDE.md grows every time Claude makes a mistake - specific rules Claude reads before touching a single line - and PostToolUse hooks auto-format and type-check every file the moment it's written. Stop hooks run tests automatically when Claude says "done" - if they fail, Claude reads the errors and keeps fixing without any manual input. Before: 45 minutes of back-and-forth per feature, same mistakes on repeat - after: 10 minutes, most of it unattended.

Noisy

13,782 Aufrufe • vor 4 Monaten

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

Alvaro Cintas

53,896 Aufrufe • vor 2 Tagen

BUILDING AI AGENTS IS EASY. SHIPPING THEM TO PRODUCTION IS WHERE EVERYONE DIES this 30-minute lecture is the gap between a demo that works and a system that runs the part most people miss: > fragmented frameworks that can't talk to each other > multi-agent coordination across different stacks - solved with A2A protocol and a "digital business card" system > ops, logging, scaling - the stuff that kills agents in production Claude Opus is the brain. Fable 5 was built for exactly this - then the US government blocked it 4 days after launch. Opus 4.8 is what's running now save this before you write another prototype 👇

BUILDING AI AGENTS IS EASY. SHIPPING THEM TO PRODUCTION IS WHERE EVERYONE DIES this 30-minute lecture is the gap between a demo that works and a system that runs the part most people miss: > fragmented frameworks that can't talk to each other > multi-agent coordination across different stacks - solved with A2A protocol and a "digital business card" system > ops, logging, scaling - the stuff that kills agents in production Claude Opus is the brain. Fable 5 was built for exactly this - then the US government blocked it 4 days after launch. Opus 4.8 is what's running now save this before you write another prototype 👇

Mr. Buzzoni

27,516 Aufrufe • vor 3 Monaten

Love what Claude shipped with Cowork Artifacts but generating code for Generative UI is the wrong architecture Wasteful: A single dashboard costs 2k boilterplate React/HTML tokens before any meaningful pixel is streamed Inconsistent: Two dashboards generated 5 mins apart don't feel like the same product. No design system. No shared components. Every output is a one off Security Liability: Today its a single-user sandboxed demo. But real software has shared dashboards, team views, embedded reports - LLM generated code for one user running in another user's session. Sandboxed or not, that's OWASP LLM05 territory. Multi-surface: A dashboard generated for desktop never works reliably on mobile. Want to render it on an iPhone? Your only option is an iframe. Yuck. Unstreamable: Partial code is extremely hard to stream meaningfully. What you get is hundreds of chunks of broken renders that flash and flicker. That's not progressive UI - that's broken UX. Code generation is a great starting point. It's not a production architecture. Generative UI in production needs an abstraction layer. The model describes intent. The renderer owns the pixels. Everything else is a liability.

Love what Claude shipped with Cowork Artifacts but generating code for Generative UI is the wrong architecture Wasteful: A single dashboard costs 2k boilterplate React/HTML tokens before any meaningful pixel is streamed Inconsistent: Two dashboards generated 5 mins apart don't feel like the same product. No design system. No shared components. Every output is a one off Security Liability: Today its a single-user sandboxed demo. But real software has shared dashboards, team views, embedded reports - LLM generated code for one user running in another user's session. Sandboxed or not, that's OWASP LLM05 territory. Multi-surface: A dashboard generated for desktop never works reliably on mobile. Want to render it on an iPhone? Your only option is an iframe. Yuck. Unstreamable: Partial code is extremely hard to stream meaningfully. What you get is hundreds of chunks of broken renders that flash and flicker. That's not progressive UI - that's broken UX. Code generation is a great starting point. It's not a production architecture. Generative UI in production needs an abstraction layer. The model describes intent. The renderer owns the pixels. Everything else is a liability.

Rabi Shanker Guha

46,745 Aufrufe • vor 5 Monaten

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

MAX

13,228 Aufrufe • vor 1 Monat