Re:Auto-autoresearch: self-improving agents on Karpathy's Na...
by junpenglao on Tuesday September 15, 2026 @04:15PM
(#49718253)
Amazing to see this out, great work Dan and team!
Tools that makes all these possible:
- Priml (https://github.com/rekursiv-ai/priml), strongly typed PyTorch (yes you read that right) ML library that allow you to iterate experiment ultra fast.
- Sagent (https://github.com/rekursiv-ai/sagent), stop a Claude session and switch to Codex to continue the conversation, and that's a minor feature
Re:Auto-autoresearch: self-improving agents on Karpathy's Na...
by jvdillon on Tuesday September 15, 2026 @03:30PM
(#49717650)
The score is a big improvement but the self-improving harness is the most exciting part. If this can actually self-optimize the act of discovery itself then there could (and should) result in a revolution in science itself.
Tools that makes all these possible:
- Priml (https://github.com/rekursiv-ai/priml), strongly typed PyTorch (yes you read that right) ML library that allow you to iterate experiment ultra fast.
- Sagent (https://github.com/rekursiv-ai/sagent), stop a Claude session and switch to Codex to continue the conversation, and that's a minor feature
- Trackinizer (https://github.com/rekursiv-ai/trackinizer), epistemologically designed schema and knowledge process, not your regular knowledge graph.