regression
5 stories and discussions about regression, aggregated from every source we track.
1.
2.
Record AI agent runs locally and find which part of the context caused a decision. - RehanMohammed985/runtape
3.
Python implementation of the PGE algorithm. Contribute to verdverm/pypge development by creating an account on GitHub.
4.
Your evals test what you thought of. Etna runs your agent's real code in a sandbox against scenarios it has never seen — and tells you what it can be talked into.
5.