Loading activity…
@jacobli99
PhD Student @MIT (EECS & CSAIL & @nlp_mit) advised by @lateinteraction. Prev. @BrownUniversity
AI
The reported MATH-500 score rose from 7.9% to 48.1% with the same sampling settings.
AI
Weaviate says MIT doctoral student Jacob X. Li discusses AI agents studying code or logs before knowing their tasks.
AI
MIT PhD student posts question about supervised fine-tuning for agent traces.