SFT
Type: Concept
Supervised Fine-Tuning; described as early dominant post-training method, analogous to mimicking a master by copying examples.
Field: Machine learning
Domain: Artificial Intelligence
Mentioned in 1 podcast episode
Who brought it up
- The $1B Al company training ChatGPT, Claude & Gemini on the path to responsible AGI | Edwin Chen on Lenny's Podcast
Originally the way models started getting post train was purely through SFT.