Muhammad Ayan (@socialwithaayan) on X
My Thoughts
I'm going to try this out over the next week. I think it's going to solve a real problem with the AI providers constantly releasing new models and changing the accepted parameters. Hopefully a lot more APIs get added over time.
🚨 BREAKING: Andrew Ng just dropped a fix for one of the most frustrating problems in AI coding agents. They hallucinate API parameters. They call deprecated endpoints. And they do it over and over because their training data is frozen. Context Hub solves this: → A versioned, Show more
You might also like
share Chayenne Zhao (@GenAI_is_real) on X
I've been using Claude Code heavily lately, and while doing so, I've been casually watching the OpenClaw codebase evolve. What I've witnessed mirrors a pattern I've seen play out with every agent framework before it — and it's worth talking about. OpenClaw is a remarkable
share Andrej Karpathy (@karpathy) on X
A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in
share The End of Coding: Andrej Karpathy on Agents, AutoResearch, and the Loopy Era of AI
What happens when AI agents can design experiments, collect data, and improve — without a human in the loop? Andrej Karpathy joins Sarah Guo on the state of models, the future of engineering and education, thinking about impact on jobs, and his project AutoResearch: where agents close the loop on a piece of AI research (experimentation, training, and optimization, autonomously). 00:00 Andrej Karpathy Introduction 02:55 What Capability Limits Remain? 06:15 What Mastery of Coding Agents Looks Like 11:16 Second Order Effects of Natural Language Coding 15:51 Why AutoResearch 22:45 Relevant Skills in the AI Era 28:25 Model Speciation 32:30 Building More Collaboration Surfaces for Humans and AI 37:28 Analysis of Jobs Market Data 48:25 Open vs. Closed Source Models 53:51 Autonomous Robotics 1:00:59 MicroGPT and Agentic Education 1:05:40 Conclusion