# @repligate — 2024-07-27

♥220 ↻22 · https://x.com/repligate/status/1817321503513313356

405B base is much more willing/able to stably simulate compared to GPT-4 base & doesn't 'break' @ failures of realism (e.g. it did a faithful sim of Bing seeded by my not-too-accurate impression)An extremely important piece of evidence ive been waiting for for a long time. x.com/repligate/stat…

tags: author:repligate, kind:tweet, model:bing-sydney, 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