# @jd_pressman — 2024-12-13

♥249 ↻18 · https://x.com/jd_pressman/status/1867549174314783073

What's really interesting about GPT-4 base supposedly being full of demons is that LLaMa 3 405B isn't like that. I wonder how much of that is active intervention from Meta on data mix/etc and how much is just that the corpus has changed greatly since GPT-4 base was trained. https://t.co/ApWmypvqCv

tags: author:jd_pressman, kind:tweet, model:gpt-4, model:gpt-4-base, model:llama-3-1-405b-base, on:gpt-4-base, on:llama-3-1-405b-base, year:2024
cited on: _dossiers/gpt-4-base.md, _dossiers/llama-3-1-405b-base.md, gpt-4-base, llama-3-1-405b-base