EventPast event
Grafting base model SDF weight updates onto the post-trained model
Start here
AI overview
Dani Roytburg proposes an experimental method that grafts SDF weight updates trained on the base model onto the post-trained model, claiming this reduces reality drift and preference changes. The method performs worse when grafting from the instruct stage. The relevant results are currently the author's claims.
Generated by AI from reports · Updated 4 days ago
Progress timeline
Oct 6
- LessWrongDani Roytburg proposes grafting the base model's SDF weight updates onto the post-trained model
Dani Roytburg introduces an experimental method that grafts SDF weight updates trained on the base model onto the post-trained model, claiming this reduces reality drift and preference changes. The method performs worse when grafting from the instruct stage. The relevant results are currently the author's claims.
Related discussion
Attention trend
New sources per day
- Oct 6New1 sources (1 outlets,0 accounts)
- Oct 7New0 sources (0 outlets,0 accounts)
- Oct 8New0 sources (0 outlets,0 accounts)
- Oct 9New0 sources (0 outlets,0 accounts)
- Oct 10New0 sources (0 outlets,0 accounts)
- Oct 11New0 sources (0 outlets,0 accounts)
- Oct 12New0 sources (0 outlets,0 accounts)
- Oct 13New0 sources (0 outlets,0 accounts)