Aaron

Being able to select the specific follow up questions and comment directly on them before accepting a plan inside Grok Build is pretty awesome.

@aaronlemke @threejs @karpathy @claudeai @WebGPU That’s really cool. You should check out Kaggle Orbit Wars - recently launched competition similar to this.

Inspired by @karpathy's practice of tinkering with smaller GPTs to gain intuition, I've been training small neural nets to play this simple 2d game I created. On the left is a visualization of the neural net firing in real time. Built with @claudeai, @threejs, and @WebGPU and using JAX from @GoogleDeepMind. I’m piping the neuron activation into @Ableton as MIDI to trigger Serum 2.

// Self-Evolving Agent Protocol // One of the more interesting papers I read this week. (bookmark it if you are an AI dev) The paper introduces Autogenesis, a self-evolving agent protocol where agents identify their own capability gaps, generate candidate improvements, validate them through testing, and integrate what works back into their own operational framework. No retraining, no human patching, just an ongoing loop of assessment, proposal, validation, and integration. Why it's worth reading this paper: Static agents age quickly. As deployment environments change and new tools arrive, the agents that survive will be the ones that can safely rewrite themselves. Autogenesis is part of a growing wave of self-improving agent systems, alongside work like Meta-Harness and the Darwin Gödel Machine line, and it's one of the cleaner protocol-level takes on continual self-improvement so far. Paper: arxiv.org/abs/2604.15034 Learn to build effective AI agents in our academy: academy.dair.ai

@kamdaloo22 @bridgemindai both are true. Opus 4.6 is really good - but it's not as good as it was previously.

@bridgemindai Why is it that everyone on X is saying that Claude opus 4.6 is “nerfed” but mine is currently doing pretty well with a really complex rust coding project? Is it just me or is opus 4.6 like really good?

CLAUDE OPUS 4.6 IS NERFED. BridgeBench just proved it. Last week Claude Opus 4.6 ranked #2 on the Hallucination benchmark with an accuracy of 83.3%. Today Claude Opus 4.6 was retested and it fell to #10 on the leaderboard with an accuracy of only 68.3%. A 98% increase in hallucination. bridgebench.ai just confirmed that Claude Opus 4.6 has reduced reasoning levels and is nerfed.

@FourVork @karpathy @fchollet @ylecun Should also check out @omarsar0

15 AI related accounts you should follow on Twitter: 1. @karpathy His tweets already create LLMs narratives that you later see on linkedin in 2 months. 2. @fchollet posts thoughtful research on intelligence, benchmarks, and AI limitations. Keras creator + ARC-AGI 3. @ylecun Yann LeCun is Deep learning pioneer & Meta Chief AI Scientist; big-picture research takes and critiques (and drama). 4. @AndrewYNg Andrew Ng is AI education legend; practical ML advice, courses, and real-world implementation. creator of deeplearning ai 5 @rasbt Sebastian Raschka posts on Practical ML/LLM implementations, "build from scratch" tutorials, and books. 6. @dair_ai Weekly ML/AI paper threads and accessible research explainers (high-signal for staying current). 7. @lilianweng Lilian Weng is ex-OpenAI and her Lil'Log-style threads are good. has In-depth LLM research breakdowns 8. @jeremyphoward posts interesting takes on AI/crypto news, and works on democratizing practical deep learning and accessible education. 9. @simonw Simon post Practical LLM tools, takes, experiments, prompting, and engineering breakdowns. django co-founder 10. @_akhaliq Curates the latest arXiv papers, model releases, and open-source AI drops. 11. @ID_AA_Carmack AGI/low-level optimization takes that makes you think about the problem. 12. @gwern Really high-quality long-form AI research notes and essays. 13. @goodside LLM evaluation, prompting research, and real capabilities testing 14 @drfeifei Computer vision pioneer; human-centered AI and spatial intelligence research 15 @demishassabis Been following his work for 9 years. Demmis is my hope against google usurpating their power with AI. Demmis is google DeepMind's CEO Let me know who I missed guys

@chongdashu @boomvideoapp perfect timing! Was just trying to work through how much CC could help with a 2d game.

Almost done with the full video tutorial on how I vibe code 2d games > phaser js skill > playwright skill > works with claude code / codex cli / cursor Lands tomorrow! Also first time I'm using @boomvideoapp

@techartist_ Very cool!

Interactive Three.js wireframe lattice morphing between parametric math surfaces. Custom GLSL shaders drive neon gradients, pulse waves, and bloom for a futuristic cyberpunk visualisation. Demo/code in comments. 👇

@trq212 This is great. Now I don't have to be as picky which ones I use.

@bcherny This is great

A small quality of life detail: you can now press tab to add more instructions when accepting/rejecting a permission prompt. We tried probably a dozen iterations of this UX over the last few weeks before deciding to ship this one. Let us know what you think!

@DilumSanjaya This is awesome, great job!

Vibe coded a game character selection screen Everything here was made with AI tools Nano Banana: character design + UI Tencent Hunyuan3D: image to 3D Gemini Pro: UI More details ↓

@businessbarista Claude

I want to start a community dedicated to Claude Code. It’s become the gateway drug to coding and experiencing the power of AI for tons of people. This will be a space for people to share killer use cases, agentic workflows, proven prompts, and connect with other CC obsessives. Comment “Claude” if you want to join.

@techartist_ Great work as always!

Wheels of All Things

@AquariusBlake Thanks!

@DataVisGuy I gotta admit, this is kinda cool

I visualized all 1,309 Titanic passengers in 3D, positioned by their actual cabin locations. Used Three.js to render the ship's structure with passengers as colored dots - green survived, red didn't. The vertical distribution tells the whole story.

@techartist_ That looks great!

Let’s understand the universe. Just Grok it.

@AnthropicAI Well that's pretty cool. Being forced into MS 365 at work so this is good to hear.

Claude Sonnet 4 and Opus 4.1 are now available in Microsoft 365 Copilot, bringing Claude’s advanced reasoning capabilities to millions of enterprise users. Read more: anthropic.com/news/claude-no…

@FieldYates Cool, now let Henderson have the ball!

And now Antonio Gibson has lost a fumble for the Patriots...

@DannyLimanseta I would definitely be interested in the Patreon.

I think I might have discovered the best 2D game engine for vibe coding games. For the past few weeks, I have been making a lovecraftian fishing game with peaceful day time fishing and intense night time combat where you fend off mutated sea creatures. And I've been using Love2D game engine for this. Love2D game engine runs on LUA, which is a compact (token-friendly) programming language that many models (GPT5, Grok Code and Sonnet) are pretty good at. I'm considering to set up a Patreon where I'll share more in depth content (devlogs, prompts, advice, tips etc) where I'll share my learnings as I vibe code an indie game from scratch. If you're interested in this, please let me know in the replies. Trying to gauge interest on this!

@techartist_ Thanks, I appreciate it!

@DataVisGuy Nice work mate, keep going. 🔥🫶

I put "Both of the above" but honestly it's whatever you enjoy working on the most. One thing that would be cool to see is the workflow you do on the backend to create the pieces you share. I know you show your code but I'm talking more about the process you work through to identify what you're going to visualize.

Hey everyone, pls help me decide what to focus on. What content interests you the most? You can also make suggestions in the comments if those are not in poll choices. Not sure I may have skills for them but can try.