News for hackers. Stuff that matters.
Re:Claude Opus 4.7 by fancyfredbot on Thursday April 16, 2026 @04:51PM (#47799336)
Wow that is terrible. In my memory GPT 2 was more interesting than that. I remember thinking it could pass a Turing test but that output is barely better than a Markov chain.

I guess I was using the large model?

Re:Claude Opus 4.7 by sillysaurusx on Thursday April 16, 2026 @06:27PM (#47800334)
There’s an art to GPT sampling. You have to use temperature 0.7. People never believe it makes such a massive difference, but it does.
Re:Claude Opus 4.7 by wat10000 on Thursday April 16, 2026 @05:32PM (#47799765)
Probably a much better prompt, too. I just literally pasted in the top part of my comment and let fly to see what would happen.
Re:Claude Opus 4.7 by daveguy on Thursday April 16, 2026 @05:23PM (#47799673)
Here is the XL model. 20x the size of the medium model. Still just 2B parameters, but on the bright side it was trained pre-wordslop.

https://huggingface.co/openai-community/gpt2-xl