Tutorial
Low
@simonw
Importance score: 7 • Posted: March 31, 2026 at 11:51
Score
7
When I published this post I hadn't yet come across Trip's own writeup of the project, which provides way more detail about how he trained the model including SFT (supervised fine tuning) against synthetic chat examples created using Claude Haiku and GPT-4o-mini https://www.estragon.news/mr-chatterbox-or-the-modern-prometheus/
Grok reasoning
Simon Willison shares details on fine-tuning a model using Claude and GPT for synthetic data.
Likes
25
Reposts
1
Views
5,998
Tweet ID: 2038947285003129161
Prompt source: ai-influencers-news
Fetched at: April 01, 2026 at 06:03