Frontier AI labs still won’t say how they’d contain a rogue model
Few of the top AI labs have published or demonstrated containment response plans, according to a recent study.…
OpenAI institutes new safeguards after Hugging Face breach
On Tuesday, OpenAI announced a new batch of security policies focused on containing security incidents while models are…
Anthropic set AI agents loose on the same task. They started a turf war.
What happens when you pit AI agents against each other? According to Anthropic’s testing, things get messy fast.…
OpenAI researchers show small doses of “beneficial trait” training make AI models broadly safer and harder to manipulate
According to a blog post on OpenAI’s alignment page, the answer is yes. The research team trained a…
Researchers may have found a way to stop AI models from intentionally playing dumb during safety evaluations
A study by researchers from the MATS program, Redwood Research, the University of Oxford, and Anthropic examines a…
Anthropic co-founder maps out how recursive AI improvement could outpace the humans meant to supervise it
Jack Clark argues in a long essay that the building blocks for AI systems training their own successors…
Managed Misalignment Rethinks AI Alignment Limits
One of the hardest problems in artificial intelligence is “alignment,” or making sure AI goals match our own,…