Viewing profile — andrew_ocs

We ran a single agent session through all 89 sequential tasks of Terminal Bench 2.0 or over 80 million tokens, with no measurable accuracy loss versus running each task in its own …

hi, you should try https://ollama.com/ which is imo the most convenient way to run local LLMs

hm, duly noted

I wouldnt be so sure Fable wouldnt just refuse to do this

I think you should try submitting it to anthropic community :) https://claude.com/community#:~:text=What,Claude%3F