I don't need my Swift or TypeScript coding agent to know the capital of every state or the roster of the 1985 Bears. In fact, I don't really even need it to know every Swift or TypeScript API. I need the core language+reasoning skills and it can look everything else up
This is f*cking insane: OpenAI co-founder Andrej Karpathy says a tiny 1B model can beat most of today's giant LLMs.
"A 1B model can be much more effective than most current LLMs. 90% of current models waste a ton of capacity and money on remembering stuff that doesn't matter"
In 64 seconds he explains why intelligence lives in the system around the model, not in its size.
Memorized Internet → Cognitive Core → Tools → Feedback Loop → Agent That Works
Save this before it gets lost in X's algorithms.
Everything below is free:
Neural Networks: Zero to Hero
Karpathy's own course, from scratch
karpathy.ai/zero-to-hero.htm…
nanochat
Karpathy's "best ChatGPT that $100 can buy"
github.com/karpathy/nanochat
Effective Harnesses for Long-Running Agents
The system around the model, by Anthropic
anthropic.com/engineering/ef…
Effective Context Engineering for AI Agents
What to feed the model and what to cut
anthropic.com/engineering/ef…
All of this costs $0
99% will keep waiting for a bigger model.
The 1% who build better systems will win with a smaller one.
Bookmark it and start with the first link tonight
1
1
149
I love AI for rapidly iterating on prototypes and design ideas where slop code doesn't matter. This is where I started vs ended on an App Store product page header
2
58
Why aren’t your server response times 0ms? Are you stupid?
Skeletons are the worst cancer in the history of user interfaces. Just make loads fast. Ping across the ocean is never more than 200ms, maybe 300ms if you're Australian, just return the damn data at that speed and you never need to even think about this crap.
1
4
277
AI companies in September: “AI is too dangerous. We must pace the frontier.”
AI companies in October: “We’re opening up wet labs to let agents run biology experiments.”
We are bringing agents to the wet-lab bench at Google Research to navigate complex biological landscapes. Learn how we are grounding agents in physical lab robotics to run fast closed-loop molecular design cycles, ultimately discovering single-digit nanomolar protein binders for cancer targets →goo.gle/4B5mMMB
67
pleasantly surprised the 2017 release of Trellis worked out of the box on my M1X. CC @inkandswitch
github.com/automerge/trellis
2
Roshan Choxi retweeted
We are excited to annouce our partnership with @popsql. You can read all about it here: hubs.ly/Q016WZbj0




















