Nearly 60 content creators moved into Lighthaven, a converted Berkeley hotel, for Plz Don't Kill Us (PDKU), a month-long bootcamp funded partly by the Machine Intelligence Research Institute (MIRI) to…
Researchers at Lighthaven tinkered with Natural Language Autoencoders (NLAs), finding that while they reconstruct activations well and enable auditing of model organisms, the architecture or training …
Anthropic released Claude Fable 5, a Mythos-class AI model, to the public this week with strong safety safeguards. Early analysis from Dawn Song's ALE benchmark shows Fable 5 performs similarly to GPT…
Iliad, an umbrella organization for applied mathematics in AI alignment, announced its Fall 2026 programs, including an accelerated three-week intensive in Berkeley and a three-month mentored research…
At a Berkeley conference on AI control, attendees participated in a roleplaying game where each player acted as a double-dealing AI agent with a secret side task, while also monitoring others for susp…