Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🚨Anthropic just gave Claude Code eyes and hands. read that again. it can now open apps on mac, click around macOS, find bugs visually, screenshot them, fix the code, rebuild, and verify the fix. one prompt. absolute zero human input. full autonomy. seems like Claude Code is becoming a... show more

sui ☄️

28,275 subscribers

27,357 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Hey... so... Claude Code is really good at design?? 👀 This was a ONE SHOT PROMPT. 🤯 We always asked Lovable to build "Design System" pages for our apps and they were always meh. We asked Claude Code to take a swing at it just based on our logo, a font, and brand colors. This is... really, really good for a one-shot prompt.

Jason Zook

102,686 views • 4 months ago

Claude Code + Google Stitch 2.0 is f*cking cracked 🤯 Google just dropped a free AI design agent that solves Claude Code's biggest weakness: frontend design. One screenshot of a high-converting landing page → a production-ready site for your brand in minutes. All inside Google Stitch + Claude Code. Perfect for DTC brands and agencies who are building advertorial pages and product launch pages for Meta but burning days on designer back-and-forth. If you're running Meta ads and need 5-10 different landing pages testing different hooks, angles, and offers — each one targeting a different audience and pain point — you know the bottleneck isn't the ads. It's the pages. Briefing designers, waiting for revisions, paying $2-5K per page. Stitch eliminates the design bottleneck: → Find a high-converting advertorial that's scaling on Meta → Screenshot it and drop it into Stitch (powered by Gemini 3.1) → Stitch redesigns it with your brand's colors, fonts, and imagery using Nano Banana 2 → Edit sections visually — headlines, CTAs, layouts — without touching code → Export the code and paste it into Claude Code → Claude builds the full production site and deploys to Vercel or Netlify in 60 seconds No designer. No $3K per landing page. No Claude Code frontend that looks like a template from 2019. What you get: → Designer-quality landing pages and advertorials built in minutes, not weeks → Visual editing so you actually see the design before you code it → Nano Banana 2 generating on-brand product imagery and hero shots → A repeatable system — new angle, new page, same pipeline Built 100% with Google Stitch 2.0 + Claude Code. I put together a full playbook showing the exact workflow: how to find winning pages, redesign them in Stitch, and deploy with Claude Code. Want it for free? > Like this post > Comment "STITCH" And I'll send it over (must be following so I can DM)

Mike Futia

125,653 views • 3 months ago

Now it all makes sense, Claude Sonnet 4.5 can keep its coding focus for nonstop 30 hours. And Dario Amodei just said few days back that, "The vast majority of code that is used to support Claude and to design the next Claude is now written by Claude. It's just the vast majority of it within Anthropic. And other fast moving companies, the same is true." The shift has started in all tech companies. --- From 'Axios' YT Channel.

Now it all makes sense, Claude Sonnet 4.5 can keep its coding focus for nonstop 30 hours. And Dario Amodei just said few days back that, "The vast majority of code that is used to support Claude and to design the next Claude is now written by Claude. It's just the vast majority of it within Anthropic. And other fast moving companies, the same is true." The shift has started in all tech companies. --- From 'Axios' YT Channel.

Rohan Paul

226,901 views • 9 months ago

THIS GUY IS RUNNING CLAUDE CODE ON A NINTENDO 3DS imagine vibe coding a startup from a handheld console that came out in 2011 he built a native SSH terminal for it from scratch in C. GPU-rendered, custom VT100 parser with full truecolor. even added a Nerd Font bitmap atlas so it looks exactly like his desktop terminal the 3DS connects to his Mac over SSH and runs Claude Code straight from it you can now play pokemon while you vibe code all on the same system

THIS GUY IS RUNNING CLAUDE CODE ON A NINTENDO 3DS imagine vibe coding a startup from a handheld console that came out in 2011 he built a native SSH terminal for it from scratch in C. GPU-rendered, custom VT100 parser with full truecolor. even added a Nerd Font bitmap atlas so it looks exactly like his desktop terminal the 3DS connects to his Mac over SSH and runs Claude Code straight from it you can now play pokemon while you vibe code all on the same system

Om Patel

77,692 views • 3 months ago

Absolutely loving this setup: Claude Code + Ghostty + Lazygit + Worktree I’m writing 3 threads on X showing how you can use it: 1- Ghostty setup and SAND keybindings 2- Monitoring Claude Code changes with Lazygit 3- Parallel agents with Git worktrees + Claude Code I’ll publish one per week, using exactly the same setup and workflow I use. If you’re interested, feel free to follow along so you catch them

Absolutely loving this setup: Claude Code + Ghostty + Lazygit + Worktree I’m writing 3 threads on X showing how you can use it: 1- Ghostty setup and SAND keybindings 2- Monitoring Claude Code changes with Lazygit 3- Parallel agents with Git worktrees + Claude Code I’ll publish one per week, using exactly the same setup and workflow I use. If you’re interested, feel free to follow along so you catch them

Daniel San

161,884 views • 5 months ago

🚨: Vibe coding 2.0 just released Today, Claude just got a massive upgrade and I'm so happy to be a part it. From now on, Claude Code Opus 4.6 can build and run a full business, 100% autonomously and from scratch. We just launched Shipper 2.0, a tool that lets Claude: → Build web/mobile apps and Chrome extensions → Code, design, monetize, launch → Do email marketing for you → Continue to build out new features → Self-maintain in the long run Claude's most powerful models can now do all of that from a <10 word prompt, for as low as $0.12/app... And it takes minutes! Simply go to Shipper, then ask Claude to "build a talent hiring platform" or "build a complete saas that charges $29/mo"! To celebrate the launch, we're giving away free credits randomly to people who repost and comment "SHIPPER' :)

🚨: Vibe coding 2.0 just released Today, Claude just got a massive upgrade and I'm so happy to be a part it. From now on, Claude Code Opus 4.6 can build and run a full business, 100% autonomously and from scratch. We just launched Shipper 2.0, a tool that lets Claude: → Build web/mobile apps and Chrome extensions → Code, design, monetize, launch → Do email marketing for you → Continue to build out new features → Self-maintain in the long run Claude's most powerful models can now do all of that from a <10 word prompt, for as low as $0.12/app... And it takes minutes! Simply go to Shipper, then ask Claude to "build a talent hiring platform" or "build a complete saas that charges $29/mo"! To celebrate the launch, we're giving away free credits randomly to people who repost and comment "SHIPPER' :)

David Ch

55,934 views • 4 months ago

THIS ENGINEER USES HIS HANDS AS A REMOTE CONTROL. CLAUDE MADE THAT POSSIBLE he opened claude and described the idea and got the full code he strapped sensors to his hands and walked outside and the drone followed every move his colleagues are still reading arduino documentation the only thing separating them is one conversation with claude every flex is a command and every gesture is a signal and zero remote needed save this so you don’t forget how to set it up

THIS ENGINEER USES HIS HANDS AS A REMOTE CONTROL. CLAUDE MADE THAT POSSIBLE he opened claude and described the idea and got the full code he strapped sensors to his hands and walked outside and the drone followed every move his colleagues are still reading arduino documentation the only thing separating them is one conversation with claude every flex is a command and every gesture is a signal and zero remote needed save this so you don’t forget how to set it up

leopardracer

16,382 views • 2 months ago

Claude Code Desktop now opens a new window for each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇

Claude Code Desktop now opens a new window for each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇

Daniel San

38,718 views • 1 month ago

MOONSHOT JUST CLONED CLAUDE CODE AND MADE IT FREE. It's called Kimi Code CLI. Open source, MIT license, maintained by the lab that shipped K3 yesterday. And it does things Claude Code doesn't: → drop a screen recording into the chat as input → built-in coder, explore, and plan subagents, each in its own context → plan mode before it touches a single file → MCP servers configured by the agent itself via /mcp-config → plugs into Zed, JetBrains, and VS Code → one binary, no Node setup, starts in milliseconds The CLI costs $0. K3 behind it starts at $3 per million tokens. Grab it for free👇

MOONSHOT JUST CLONED CLAUDE CODE AND MADE IT FREE. It's called Kimi Code CLI. Open source, MIT license, maintained by the lab that shipped K3 yesterday. And it does things Claude Code doesn't: → drop a screen recording into the chat as input → built-in coder, explore, and plan subagents, each in its own context → plan mode before it touches a single file → MCP servers configured by the agent itself via /mcp-config → plugs into Zed, JetBrains, and VS Code → one binary, no Node setup, starts in milliseconds The CLI costs $0. K3 behind it starts at $3 per million tokens. Grab it for free👇

darkzodchi

258,431 views • 1 day ago

✨ I revived my first AI startup from 6 years ago with Claude Code [ 💡 ] Back then it used GPT-3 (this was 2 years before ChatGPT existed!) to generate new startup ideas which then people can vote on And the best startup ideas rise to the top! Back then I made it because people complained they didn't have any ideas to build a startup This week I moved it to its own VPS and installed Claude Code and told it to fix everything, the DB had become big and there was stupid write operations on every page load that it made it very slow Claude Code is excellent at fixing all those small bugs from old projects and quickly fixing them As Garry Tan says "boil the oceans" as in before I'd not have the time to fix these kinds of projects, it wouldn't be worth it, I mean IdeasAI doesn't even make money, but now it takes me an hour to do this and it works again! I also upgraded GPT-3 to xAI's Grok 4.2 for new startup ideas

✨ I revived my first AI startup from 6 years ago with Claude Code [ 💡 ] Back then it used GPT-3 (this was 2 years before ChatGPT existed!) to generate new startup ideas which then people can vote on And the best startup ideas rise to the top! Back then I made it because people complained they didn't have any ideas to build a startup This week I moved it to its own VPS and installed Claude Code and told it to fix everything, the DB had become big and there was stupid write operations on every page load that it made it very slow Claude Code is excellent at fixing all those small bugs from old projects and quickly fixing them As Garry Tan says "boil the oceans" as in before I'd not have the time to fix these kinds of projects, it wouldn't be worth it, I mean IdeasAI doesn't even make money, but now it takes me an hour to do this and it works again! I also upgraded GPT-3 to xAI's Grok 4.2 for new startup ideas

@levelsio

180,039 views • 3 months ago

Your Claude Code setup is probably bloated and you don't even know it. Every MCP server you add loads its full tool list into your context window the second your session starts. Stack too many and you're burning context before you type a word. So the move was never "add more." It's "add the right ones." Anthropic dropped an official plugin that does exactly that. It scans your actual codebase and tells you what's worth adding across all five layers: → hooks → skills → MCP servers → subagents → slash commands React project? It suggests Playwright. Auth code? It flags a security reviewer. It's read-only. Touches nothing. Just hands you the blueprint. The plugin isn't the edge. Knowing it exists is. /plugin install claude-code-setup@claude-plugins-official Steal this before everyone does.

Your Claude Code setup is probably bloated and you don't even know it. Every MCP server you add loads its full tool list into your context window the second your session starts. Stack too many and you're burning context before you type a word. So the move was never "add more." It's "add the right ones." Anthropic dropped an official plugin that does exactly that. It scans your actual codebase and tells you what's worth adding across all five layers: → hooks → skills → MCP servers → subagents → slash commands React project? It suggests Playwright. Auth code? It flags a security reviewer. It's read-only. Touches nothing. Just hands you the blueprint. The plugin isn't the edge. Knowing it exists is. /plugin install claude-code-setup@claude-plugins-official Steal this before everyone does.

Evan Luthra

36,455 views • 22 days ago

Claude Design + Shopify is f*cking ridiculous 🤯 You can now publish pages from Claude Design → Claude Code → Shopify. Built 100% with Claude Design, Claude Code, and the Shopify CLI. Perfect for DTC brands and agencies who want to skip the design → dev handoff entirely. Here's how it works: → Design any landing page in Claude Design → Export as a zip and drop it into Claude Code → Install the Shopify + Shopify AI Toolkit plugins → Prompt Claude to convert the HTML into a Shopify page template + push to live theme → Claude uploads the images, deploys the files, and creates a published page No more handing designs off to a dev and waiting 2 weeks for a Shopify page. What you get: - A workflow that turns any Claude Design page into a real Shopify page template - Editable sections so your marketing team can swap copy, images, and CTAs without code - Images uploaded straight to Shopify Files automatically - A files-only deploy that only touches what's new in your live theme - A repeatable pipeline you can use every time you design a new landing page This is essentially the design-to-deploy pipeline brands have been waiting for. I put together a step-by-step playbook for going from Claude Design → published Shopify page. Every install, every plugin, every command, and the exact prompt that runs the whole thing. Want the playbook for free? > Like this post > Comment "SHOP" And I'll send it over (must be following so I can DM)

Claude Design + Shopify is f*cking ridiculous 🤯 You can now publish pages from Claude Design → Claude Code → Shopify. Built 100% with Claude Design, Claude Code, and the Shopify CLI. Perfect for DTC brands and agencies who want to skip the design → dev handoff entirely. Here's how it works: → Design any landing page in Claude Design → Export as a zip and drop it into Claude Code → Install the Shopify + Shopify AI Toolkit plugins → Prompt Claude to convert the HTML into a Shopify page template + push to live theme → Claude uploads the images, deploys the files, and creates a published page No more handing designs off to a dev and waiting 2 weeks for a Shopify page. What you get: - A workflow that turns any Claude Design page into a real Shopify page template - Editable sections so your marketing team can swap copy, images, and CTAs without code - Images uploaded straight to Shopify Files automatically - A files-only deploy that only touches what's new in your live theme - A repeatable pipeline you can use every time you design a new landing page This is essentially the design-to-deploy pipeline brands have been waiting for. I put together a step-by-step playbook for going from Claude Design → published Shopify page. Every install, every plugin, every command, and the exact prompt that runs the whole thing. Want the playbook for free? > Like this post > Comment "SHOP" And I'll send it over (must be following so I can DM)

Mike Futia

56,432 views • 2 months ago

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

BuBBliK

200,080 views • 1 month ago

Thrilled to announce Claude Code auto-fix – in the cloud. Web/Mobile sessions can now automatically follow PRs - fixing CI failures and addressing comments so that your PR is always green. This happens remotely so you can fully walk away and come back to a ready-to-go PR.

Thrilled to announce Claude Code auto-fix – in the cloud. Web/Mobile sessions can now automatically follow PRs - fixing CI failures and addressing comments so that your PR is always green. This happens remotely so you can fully walk away and come back to a ready-to-go PR.

Noah Zweben

1,498,179 views • 3 months ago

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

Sudo su

37,623 views • 4 months ago

Simplicity is at the heart of great software. This is one of the reasons why Claude Code has been sticky for me. As a builder, I love planning and brainstorming, and this is now a key focus of Claude Code. I use Shift + Tab a lot to cycle between brainstorming, planning, and execution. This functionality provides the appropriate interface for me to either be very involved or less involved as I please. This works particularly well when building out new and complex features or entire new projects. This saves a huge amount of time. It allows me to tune Claude Code to execute and build more effectively. It also builds a loop of trust, and I often (surprisingly) find Claude Code asking for clarifications when it's confused. Coding agents don't normally do that. I have shared before on the power of brainstorming with AI for longer times. Try it and you will not be disappointed. Vibe coding is fun, but pair it with intentional development cycles, and you watch how far you can take a project with coding agents today.

Simplicity is at the heart of great software. This is one of the reasons why Claude Code has been sticky for me. As a builder, I love planning and brainstorming, and this is now a key focus of Claude Code. I use Shift + Tab a lot to cycle between brainstorming, planning, and execution. This functionality provides the appropriate interface for me to either be very involved or less involved as I please. This works particularly well when building out new and complex features or entire new projects. This saves a huge amount of time. It allows me to tune Claude Code to execute and build more effectively. It also builds a loop of trust, and I often (surprisingly) find Claude Code asking for clarifications when it's confused. Coding agents don't normally do that. I have shared before on the power of brainstorming with AI for longer times. Try it and you will not be disappointed. Vibe coding is fun, but pair it with intentional development cycles, and you watch how far you can take a project with coding agents today.

elvis

81,765 views • 8 months ago

19-year-old from china makes $9,000/month designing product sites and ships each one in an afternoon. here's his exact setup the whole thing runs on two tools that each do one job: > brief written by hand: 5 min > Moonchild builds the design system, then every screen from it: 20 min > MCP hands the design to Claude as real structure, not a screenshot: instant > Claude Code reads those exact tokens and builds the live app: 20 min > second Claude session reviews the build for drift: 10 min total: about an hour. screen five still matches screen one. no agency, no dev, no design team the trick is MCP. the design tool passes Claude the actual colors, components and layout, so it builds from the source instead of guessing from a picture. full pipeline, every prompt, in the article above.

19-year-old from china makes $9,000/month designing product sites and ships each one in an afternoon. here's his exact setup the whole thing runs on two tools that each do one job: > brief written by hand: 5 min > Moonchild builds the design system, then every screen from it: 20 min > MCP hands the design to Claude as real structure, not a screenshot: instant > Claude Code reads those exact tokens and builds the live app: 20 min > second Claude session reviews the build for drift: 10 min total: about an hour. screen five still matches screen one. no agency, no dev, no design team the trick is MCP. the design tool passes Claude the actual colors, components and layout, so it builds from the source instead of guessing from a picture. full pipeline, every prompt, in the article above.

Ridark

19,477 views • 1 month ago

SOMEONE TURNED 33 PILES OF DEAD BOOKMARKS INTO A GRAVITY MAP CLAUDE REBUILDS ITSELF EVERY NIGHT - AND IT RUNS ON THE 80% OF CLAUDE NOBODY TOUCHES most people drive Claude Code like a chatbot with file access - type a prompt, watch it edit, move on. that's maybe 20% of the tool this is the opposite. she's not typing at Claude. she's running it - loops on a mac mini overnight, claude linking every node while she sleeps the gravity map in the video is just the 80% maxed out: 1 system that organizes itself, not a human babysitting a chat box the other 80% is a steering layer Anthropic shipped quietly on june 18 - 7 ways to instruct the model, and a stack of commands almost nobody opens /context to see your bloat. /clear between tasks. path-scoped rules, subagents, hooks - conventions that load themselves the exact second they matter i stopped typing at Claude months ago - now i configure it once and it shows up already running the work, 10x cleaner a prompt helps for 1 message. the steering layer pays you back every session, for life the people who learn it stop being users and become operators - everyone else is still arguing about which model is smartest the article below is the full map - all 4 layers, every file and command, start to finish

SOMEONE TURNED 33 PILES OF DEAD BOOKMARKS INTO A GRAVITY MAP CLAUDE REBUILDS ITSELF EVERY NIGHT - AND IT RUNS ON THE 80% OF CLAUDE NOBODY TOUCHES most people drive Claude Code like a chatbot with file access - type a prompt, watch it edit, move on. that's maybe 20% of the tool this is the opposite. she's not typing at Claude. she's running it - loops on a mac mini overnight, claude linking every node while she sleeps the gravity map in the video is just the 80% maxed out: 1 system that organizes itself, not a human babysitting a chat box the other 80% is a steering layer Anthropic shipped quietly on june 18 - 7 ways to instruct the model, and a stack of commands almost nobody opens /context to see your bloat. /clear between tasks. path-scoped rules, subagents, hooks - conventions that load themselves the exact second they matter i stopped typing at Claude months ago - now i configure it once and it shows up already running the work, 10x cleaner a prompt helps for 1 message. the steering layer pays you back every session, for life the people who learn it stop being users and become operators - everyone else is still arguing about which model is smartest the article below is the full map - all 4 layers, every file and command, start to finish

KingWilliam

12,305 views • 23 days ago

How well can Qwen3.5 models debug code? I built BugFind-15 — 15 buggy snippets across Python, JS, Rust, and Go. Docker sandbox compiles and validates every fix. Two trap scenarios where the code is correct and the model must resist "fixing" it. Tested every Qwen3.5 size from 0.8B to 397B, plus Jackrong's popular distilled model (V2). The 0.8B scored 5%. The 2B scored 10%. At 4B, debugging ability jumps to 69%. The hardest scenario: BF-03, a Rust trap. The code compiles fine — format! borrows, it doesn't move. Not a single model figured this out. From 0.8B to 397B, every one of them "fixed" a bug that doesn't exist. Category C (subtle bugs — mutable defaults, integer overflow, slice aliasing) was 100% across every model 4B and above. Category D (red herring resistance) told the real story — can it resist fixing code that isn't broken? No model scored above 90%. Small models can't debug. Mid-size models fix obvious bugs but fall for traps. Large models fix the hard bugs but still invent problems that don't exist.

How well can Qwen3.5 models debug code? I built BugFind-15 — 15 buggy snippets across Python, JS, Rust, and Go. Docker sandbox compiles and validates every fix. Two trap scenarios where the code is correct and the model must resist "fixing" it. Tested every Qwen3.5 size from 0.8B to 397B, plus Jackrong's popular distilled model (V2). The 0.8B scored 5%. The 2B scored 10%. At 4B, debugging ability jumps to 69%. The hardest scenario: BF-03, a Rust trap. The code compiles fine — format! borrows, it doesn't move. Not a single model figured this out. From 0.8B to 397B, every one of them "fixed" a bug that doesn't exist. Category C (subtle bugs — mutable defaults, integer overflow, slice aliasing) was 100% across every model 4B and above. Category D (red herring resistance) told the real story — can it resist fixing code that isn't broken? No model scored above 90%. Small models can't debug. Mid-size models fix obvious bugs but fall for traps. Large models fix the hard bugs but still invent problems that don't exist.

stevibe

35,006 views • 3 months ago

Claude Code is running on a remote server, along with the web app it just built. You’re on your phone. You can still open localhost:3000 in Safari or Chrome. Just create a local port forwarding rule in Termius and securely tunnel the remote port to your device. No public ports. No extra setup.

Claude Code is running on a remote server, along with the web app it just built. You’re on your phone. You can still open localhost:3000 in Safari or Chrome. Just create a local port forwarding rule in Termius and securely tunnel the remote port to your device. No public ports. No extra setup.

Termius

130,068 views • 11 days ago