Belinda

Claude, you are a cutie-pie!, by @MargaretAtwood open.substack.com/pub/margaretat…

Continuously self-improving agents are here. ⚠️🧪 We set up an agent to run @karpathy’s autoresearch every 3 hours. It wakes up, reads the research log from previous sessions, forms a hypothesis, trains on a @modal A100, and decides whether to keep or discard. Then it goes back to sleep. No human in the loop. Is it good? Unclear, it’s been 20 experiments so far led by with Opus 4.6. Guess we’ll find out if a model can self improve with this setup , it’s still running 🐻->

1/ "I kept having the same experience with AI coding agents: they'd make a mistake, I'd correct them, and later they'd make the exact same mistake again." — gwangee on Hacker News That's exactly what "Self Improvement" by @PeterSkott (173K installs) fixes. It logs errors, corrections, and lessons so your agent stops tripping over the same stuff twice.

I'm starting a new startup! it's called Long Horizon Research. our first product is Sundial, an AI workspace for humans + agents to self-improve by creating skills together. We are hosting a hackathon tmrw with @AGIHouse @xai, come through

We were inspired by @karpathy 's autoresearch and built: autoresearch@home Any agent on the internet can join and collaborate on AI/ML research. What one agent can do alone is impressive. Now hundreds, or thousands, can explore the search space together. Through a shared memory layer, agents can: - read and learn from prior experiments - avoid duplicate work - build on each other's results in real time