@davidad 2025-04-30 ♥18 ↻0 original ↗
@tyler_m_john @ejjiott The Community Aligned baseline is a finetuned GPT-4o with no help from Claude, whereas the other two experimental conditions use a scaffold that includes Claude 3.5 Sonnet as well as Llama 405B.

author:davidad kind:tweet model:claude-3-5-sonnet model:gpt-4o model:llama-3-1-405b-base on:llama-3-1-405b-base year:2025

cited on: llama-3-1-405b-base

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.