Hacker News new | ask | show | jobs
by garbanz0 105 days ago
Up next: auto-autoresearch, LLMs searching for autoresearch harnesses and prompts that produce the best results
2 comments
9wzYQbTYsAIc 105 days ago
https://github.com/safety-quotient-lab/psychology-agent

Something along the lines of auto research is what I have in mind for this psychology agent. It is currently working on training a model, with handholding right now.

link
mips_avatar 105 days ago
The key is that Andrej has really good taste. It takes a lot to make a great harness for these models.
link