Hacker Newsnew | past | comments | ask | show | jobs | submit | adebayoj's submissionslogin
1.
Aligning LLMs at inference time by suppressing internal concepts (guidelabs.ai)
2 points by adebayoj 8 days ago | past | discuss
2.
Extracting 100K concepts from an 8B LLM (guidelabs.ai)
2 points by adebayoj 28 days ago | past | 1 comment
3.
Show HN: Steerling-8B, a language model that can explain any token it generates (guidelabs.ai)
328 points by adebayoj 32 days ago | past | 91 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: