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.

Took Andrej Karpathy's advice and started asking the agent for more visuals to walk through code. He's right. These models are so capable now. Here I asked for a before-and-after HTML explainer on a PR that adds caching to our mobile app. Opus 5.5 gave a step-by-step diagram of... show more

Ben Holmes

47,956 subscribers

57,607 views • 3 days ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Yaxel Lendeborg on the meaningful advice Draymond gave him during their first interaction: “The messages… I was a little worried to text him and Steph ‘cause those are the big dogs. I’m new here. I asked him a question, just asking him for advice, and he gave me great and meaningful advice. I was very excited.” The advice: “Find ways to be useful on the team without losing who I am as a person.”

Yaxel Lendeborg on the meaningful advice Draymond gave him during their first interaction: “The messages… I was a little worried to text him and Steph ‘cause those are the big dogs. I’m new here. I asked him a question, just asking him for advice, and he gave me great and meaningful advice. I was very excited.” The advice: “Find ways to be useful on the team without losing who I am as a person.”

aly ✶

17,763 views • 2 months ago

Stop manually making flowcharts. Try this GitHub skill with Claude Code. I found an open-source tool that turns a plain description of a software system into a clean, interactive diagram. It's called Archify, and it has more than 66,000 stars on GitHub. You add it as a skill to an AI coding agent like Claude Code, Codex, Cursor, or OpenCode. Then you describe the system in the chat in one line. Archify turns that line into a single HTML file you can open, click through, and send to anyone. If you point your agent at an existing codebase, it reads the code and Archify maps how the pieces connect. I liked five things about it. 1. It makes five kinds of diagrams, including system maps and step-by-step workflows. 2. You can click any piece and trace what connects to it. 3. It checks the layout before it hands the diagram over, so arrows don't pile up and labels don't overlap. 4. It has dark and light themes and exports to PNG, SVG, or a short video. 5. You keep editing in plain chat, with requests like "add Redis" or "highlight the rollback path." You don't need a codebase to use it. A description in the chat is enough.

Stop manually making flowcharts. Try this GitHub skill with Claude Code. I found an open-source tool that turns a plain description of a software system into a clean, interactive diagram. It's called Archify, and it has more than 66,000 stars on GitHub. You add it as a skill to an AI coding agent like Claude Code, Codex, Cursor, or OpenCode. Then you describe the system in the chat in one line. Archify turns that line into a single HTML file you can open, click through, and send to anyone. If you point your agent at an existing codebase, it reads the code and Archify maps how the pieces connect. I liked five things about it. 1. It makes five kinds of diagrams, including system maps and step-by-step workflows. 2. You can click any piece and trace what connects to it. 3. It checks the layout before it hands the diagram over, so arrows don't pile up and labels don't overlap. 4. It has dark and light themes and exports to PNG, SVG, or a short video. 5. You keep editing in plain chat, with requests like "add Redis" or "highlight the rollback path." You don't need a codebase to use it. A description in the chat is enough.

Alex Veremeyenko

61,928 views • 19 days ago

Something just launched that makes VS Code feel ancient. And im all in for it: Cline Desktop app, an open-source app for open-weight models (and you know how much i love open source) brings its coding agent into a standalone Cline Desktop app for Mac + Windows. Just open a project and tell it what you want to change. No need to open VS Code first. In Cline's demo, it adds priority filters to a task board, works through the code and runs the build. Glad to see the model choice stays open, too. You can bring your own API keys, use supported open-weight models and even switch models halfway through a project!

Something just launched that makes VS Code feel ancient. And im all in for it: Cline Desktop app, an open-source app for open-weight models (and you know how much i love open source) brings its coding agent into a standalone Cline Desktop app for Mac + Windows. Just open a project and tell it what you want to change. No need to open VS Code first. In Cline's demo, it adds priority filters to a task board, works through the code and runs the build. Glad to see the model choice stays open, too. You can bring your own API keys, use supported open-weight models and even switch models halfway through a project!

Chubby♨️

40,292 views • 24 days ago

Opal, our no-code visual builder for AI workflows, just got a major upgrade. 🧠💎 We’ve added a new agent step that analyzes your goal, determines the best approach, and automatically calls the right tools — such as Veo for video or web search for research — to complete the task. We’re also adding new tools to make the agent even more capable: 💾 Memory – Remember info, like a user’s name or your style preferences across sessions. 🚀 Dynamic Routing – Let the agent choose the next best step using the “@ Go to” tool. 💬 Interactive Chat – Initiate user interactions to gather missing information or present options before moving on. Try it now →

Opal, our no-code visual builder for AI workflows, just got a major upgrade. 🧠💎 We’ve added a new agent step that analyzes your goal, determines the best approach, and automatically calls the right tools — such as Veo for video or web search for research — to complete the task. We’re also adding new tools to make the agent even more capable: 💾 Memory – Remember info, like a user’s name or your style preferences across sessions. 🚀 Dynamic Routing – Let the agent choose the next best step using the “@ Go to” tool. 💬 Interactive Chat – Initiate user interactions to gather missing information or present options before moving on. Try it now →

Google Labs

1,008,974 views • 7 months ago

Seems like Visual Studio Code is starting to tell you: your agent primitives need to move. There is now a new migration banner in the Chat panel, and it is part of a much bigger change happening under the hood: the move from the old Local harness to the new Agent Host architecture built around AHP. This is not just about moving where an agent runs. The old model was very VS Code-centric: prompts, custom agents, instructions and skills could live in VS Code-specific locations and the agent runtime lived inside the extension host. The new Agent Host separates the agent runtime from the editor. Sessions can keep running when the window closes, be shared across VS Code windows, run remotely, and support different harnesses such as Copilot, CLI and Copilot Desktop App through a common session layer. And that means some of our primitives need to move too. Prompt files are being deprecated for Agent Host and migrated to Skills. User-level agents and instructions that lived in VS Code profile storage need to move to harness-supported locations. Even the old location settings are being deprecated. The new migration experience can detect these things and guide you through moving or converting them, while keeping the originals unless you explicitly remove them. The new banner is basically the first visible sign that this migration is becoming a real product workflow. Basically telling us - it's time to move on!!!! If you have accumulated a lot of prompts, custom agents, instructions and skills over the last year, now is probably a good time to understand where they actually live and which harness owns them. To summarize the shift - it isn't just: VS Code Chat → Agent Host It is: VS Code-specific primitives → harness-native primitives. And I think this is going to become increasingly important as agents stop being features inside an IDE and become runtimes that multiple clients can connect to. Go run your migrations now 🏃‍♀️

Oren Melamed

29,753 views • 7 days ago

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

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

elvis

37,824 views • 2 months ago

Experimenting with tldraw, xyflow · React Flow · Svelte Flow & Mermaid JS as visual ways to interact with a code base for interactive modern code review. Claude & Codex can generate so much code so quickly that we are going to need new ways to review and understand their work. Markdown documents, ERDs, tree-maps, flow-charts, systems architecture diagrams, process maps. These could be the new lingua franca of a higher level abstraction of software development. What you're seeing below is a visualisation of the database structure of a Laravel app, automatically generated in a visual code review tool to help with the review of a new feature.

Experimenting with tldraw, xyflow · React Flow · Svelte Flow & Mermaid JS as visual ways to interact with a code base for interactive modern code review. Claude & Codex can generate so much code so quickly that we are going to need new ways to review and understand their work. Markdown documents, ERDs, tree-maps, flow-charts, systems architecture diagrams, process maps. These could be the new lingua franca of a higher level abstraction of software development. What you're seeing below is a visualisation of the database structure of a Laravel app, automatically generated in a visual code review tool to help with the review of a new feature.

Peter Thomson

27,048 views • 8 months ago

Beta time! OASIS – a smart ring to control other devices. No healthcare, just interactions. Click the icons on our website to get a sense of what it can do and DM me for a code if you want to be part of the beta – its $289.00

Beta time! OASIS – a smart ring to control other devices. No healthcare, just interactions. Click the icons on our website to get a sense of what it can do and DM me for a code if you want to be part of the beta – its $289.00

Ricky Rosa

23,022 views • 1 year ago

Just tried something cool on my own app. I let my app generate a workout for me using the new beta mode… and it actually built a solid session based on my goals. The idea is simple.. instead of guessing what to train, you hit generate and the app builds the workout for you. Still early days but I’m keen for people to test it and tell me what you think. Try it here:

Just tried something cool on my own app. I let my app generate a workout for me using the new beta mode… and it actually built a solid session based on my goals. The idea is simple.. instead of guessing what to train, you hit generate and the app builds the workout for you. Still early days but I’m keen for people to test it and tell me what you think. Try it here:

Shannon

14,459 views • 6 months ago

I wanted to showcase some of the sprite work i did for my Lost lands set. Made some new stuff and reworked a LOT of old stuff 😎 i definitely underestimated the amount of work. My full set is about 43 songs, so that means 43 individual visuals. it took me about 2 weeks just to adjust everything i had for the big mainstage screen. Definitely learned a lot in the process and really excited to work on the new show. Im limited to 4 here if u wanna see more there’s 12 on my instagram 😘

I wanted to showcase some of the sprite work i did for my Lost lands set. Made some new stuff and reworked a LOT of old stuff 😎 i definitely underestimated the amount of work. My full set is about 43 songs, so that means 43 individual visuals. it took me about 2 weeks just to adjust everything i had for the big mainstage screen. Definitely learned a lot in the process and really excited to work on the new show. Im limited to 4 here if u wanna see more there’s 12 on my instagram 😘

EPTIC

24,771 views • 1 year ago

Claude Code can now go find the right skill itself, instead of you searching for one. it's called find-skills. a small package that plugs into Claude Code, and instead of you hunting for rest, you just describe the task and it searches the whole open skills ecosystem, finds the ones that fit, and installs them for you. > tell it what you're trying to do, in plain english > it scans the skills registry and maps your task to real skills > it pulls the right ones in and sets them up half the time you don't even know a skill exists for what you're doing. now you don't have to.

Claude Code can now go find the right skill itself, instead of you searching for one. it's called find-skills. a small package that plugs into Claude Code, and instead of you hunting for rest, you just describe the task and it searches the whole open skills ecosystem, finds the ones that fit, and installs them for you. > tell it what you're trying to do, in plain english > it scans the skills registry and maps your task to real skills > it pulls the right ones in and sets them up half the time you don't even know a skill exists for what you're doing. now you don't have to.

Alvaro Cintas

38,829 views • 1 month ago

Dentist did a 3D X-ray of my jaw before a root canal and said I wouldn't be able to open the raw data, it needs specialized software. It's 800 DICOM files. Asked Claude Code with Opus 5.5 to make me a viewer. A single prompt later... this is nicer than what he showed me on his screen, and even better than what Fable did a few weeks ago!

Dentist did a 3D X-ray of my jaw before a root canal and said I wouldn't be able to open the raw data, it needs specialized software. It's 800 DICOM files. Asked Claude Code with Opus 5.5 to make me a viewer. A single prompt later... this is nicer than what he showed me on his screen, and even better than what Fable did a few weeks ago!

Paolo Rosson

80,517 views • 15 days ago

Introducing Pages on Superset mobile Your agents can now deliver interactive demos, mockups, and reports as Pages you can review from your phone. Ask an agent to build a feature, compare designs, or investigate a problem. It can put the result in a Page with the context you need to review it and give feedback. A few ways to use it: • Feature work: try an interactive demo, then inspect the code in the PR. • Design reviews: compare mockups and before-and-after screenshots. • Investigations: explore findings, charts, and recommendations in one place. To try it, ask your agent to build a feature and create a Page for you to review.

Introducing Pages on Superset mobile Your agents can now deliver interactive demos, mockups, and reports as Pages you can review from your phone. Ask an agent to build a feature, compare designs, or investigate a problem. It can put the result in a Page with the context you need to review it and give feedback. A few ways to use it: • Feature work: try an interactive demo, then inspect the code in the PR. • Design reviews: compare mockups and before-and-after screenshots. • Investigations: explore findings, charts, and recommendations in one place. To try it, ask your agent to build a feature and create a Page for you to review.

Kiet

85,841 views • 14 days ago

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.

elvis

47,678 views • 5 months ago

Lately I've been asking Claude Code to show me the feature before building it: "Create a plan and a low-fidelity artifact showing how the UI will look and the systems fit together. Keep them in sync as we iterate." This moves more of the iteration from the code to the plan.

Lately I've been asking Claude Code to show me the feature before building it: "Create a plan and a low-fidelity artifact showing how the UI will look and the systems fit together. Keep them in sync as we iterate." This moves more of the iteration from the code to the plan.

Dan Fein

38,143 views • 3 months ago

Opus 5.5 just filed a pull request that changes the streaming behavior in T3 code. It's so cool that I can send off a prompt with a vague idea of what I want, and the result is a ready-to-merge pull request with a video demo of the changes directly in the PR. The PRs I make with AI are significantly better than the ones I used to make by hand. The future is awesome.

Opus 5.5 just filed a pull request that changes the streaming behavior in T3 code. It's so cool that I can send off a prompt with a vague idea of what I want, and the result is a ready-to-merge pull request with a video demo of the changes directly in the PR. The PRs I make with AI are significantly better than the ones I used to make by hand. The future is awesome.

Theo - t3.gg

94,090 views • 13 days ago

Here is the tool I built yesterday in Claude code in maybe 10-20 minutes? It truly baffles me when people say “the AI bubble” this simple tool would’ve took devs 2-5 days and would have cost me 500$-1000$ Claude code made it for me on a 20$ monthly subscription, and a free Gemini api key. I actually want to preform an experiment asking developers how much they would charge for such a tool to get a consensus on how much money Claude Code has saved me.

Here is the tool I built yesterday in Claude code in maybe 10-20 minutes? It truly baffles me when people say “the AI bubble” this simple tool would’ve took devs 2-5 days and would have cost me 500$-1000$ Claude code made it for me on a 20$ monthly subscription, and a free Gemini api key. I actually want to preform an experiment asking developers how much they would charge for such a tool to get a consensus on how much money Claude Code has saved me.

Chris

170,273 views • 8 months ago

This is the best AI agent-first notes app I've found. It's called . It has the potential to be a productized version of Karpathy's "LLM Wiki" knowledge bases. Here's what I did: 1. Imported "Learning, Fast and Slow" a Continual Learning paper 2. Asked OpenKnowledge to create a visual explainer 3. Read the explainer and had Claude explain to me 4. Created a new section of my own understanding 5. Saved the durable version in my Obsidian vault because it's markdown Free and open-source. Absolutely incredible learning tool.

This is the best AI agent-first notes app I've found. It's called . It has the potential to be a productized version of Karpathy's "LLM Wiki" knowledge bases. Here's what I did: 1. Imported "Learning, Fast and Slow" a Continual Learning paper 2. Asked OpenKnowledge to create a visual explainer 3. Read the explainer and had Claude explain to me 4. Created a new section of my own understanding 5. Saved the durable version in my Obsidian vault because it's markdown Free and open-source. Absolutely incredible learning tool.

Dan McAteer

17,326 views • 3 months ago