❌

Reading view

‘Subliminal learning’: Anthropic uncovers how AI fine-tuning secretly teaches bad habits

30 July 2025 at 22:21

Image credit: VentureBeat with ChatGPT

A common AI fine-tuning practice could be unintentionally poisoning your models with hidden biases and risks, a new Anthropic study warns.Read More

Beyond static AI: MIT’s new framework lets models teach themselves

23 June 2025 at 21:58

Image credit: VentureBeat with ChatGPT

MIT researchers developed SEAL, a framework that lets language models continuously learn new knowledge and tasks.Read More