Hacker News new | ask | show | jobs
by simonw 591 days ago
It looks like this defaults to GPT-4o: https://github.com/microsoft/TinyTroupe/blob/7ae16568ad1c4de...

If you're going to try this out I would strongly recommend running it against GPT-4o mini instead. Mini is 16x cheaper and I'm confident the results you'll get out of it won't be 1/16th as good for this kind of experiment.

1 comments

I suppose the Microsoft researchers default to 4o because the models are free in their environment…