Aaron Smith

The behaviour is explained in [custom-eval.md](https://github.com/openai/evals/blob/19bfdba1fd9027f6818672e35615f45584de8b02/docs/custom-eval.md): > If you notice evals has cached your data and you need to clear that cache, you can do so with `rm -rf /tmp/filecache`....

I've updated the prompt to v1, where gpt-3.5-turbo performs a little better. The accuracy is currently at 0.2 - pretty good considering! Super excited to see how gpt-4 performs on...

Huge thanks to OpenAI for the gpt-4 access, the results of the new model are very interesting! Overall there seems to be a ~5% increase in match chance. ```console [2023-03-16...

Hey @joe-at-openai and @usama-openai , many thanks for the helpful suggestions in improving my eval in #288 ! I've taken a fresh look at the prompt and results, and I've...

Many thanks for reviewing my PR @usama-openai ! I've just added the requested changes alongside the generator script. Please let me know if there are any extra changes you'd like...

My apologies! I noticed it as the tests were coming through. That should be fixed now :)

Great, many thanks @andrew-openai and @usama-openai ! I am happy for my GPT-4 access to go to someone else, I already have it :)

Hello, and thank you very much! This is a really interesting addition to think about. I imagine it would be relatively simple to add a 'sticky note' style drawing tool,...

Hey @jrowinski-irreventlabs, thanks for submitting this, and I'm glad you're enjoying Houdini-Docker! Is the bug with NCT something that can be fixed on my end, or am I good to...