Very well written blog post on agents by some titans of the industry.

Show Post

This is an interesting way to think about it

Show Post

Want to know what training data has been memorized by models like GPT-4? We propose information-guided probes, a method to uncover memorization evidence in *completely black-box* models, without requiring access to 🙅‍♀️ Model weights 🙅‍♀️ Training data 🙅‍♀️ Token probabilities 🧵 (1/5)

Show Post

RIFTS Dataset: Solving Critical LLM Conversation Failures - LLMs 3x less likely to clarify than humans - 16x less likely to provide follow-up requests - Early failures predict later breakdowns - Includes preliminary intervention strategies huggingface.co/datasets/mic...

Show Post

Also worth reading (especially for folks working with smaller LMs)! Auxiliary task demands mask the capabilities of smaller language models arxiv.org/abs/2404.02418 Generally I really like @jennhu.bsky.social's work; follow her, read her stuff!!

Show Post