autolab-ai · Agent Skills

autolab-ai

Community

hills

Optimize anything through autonomous experimentation, against an evaluator you cannot grade yourself with. Use whenever the user wants to improve a number by iterating - raise accuracy, cut val loss, make training or inference faster, reduce latency or cost, beat a baseline, tune a pipeline or prompt, squeeze a kernel, run experiments overnight, or set up a benchmark for someone else to beat. Also use for any request to create, inspect, update or score against a hill, or when the user types /hil

1h installs

1

GitHub stars

20

Updated

Sep 28