Anthropic paper offers an early look at AI systems improving alignment research
Anthropic researchers report an automated system improved 10 alignment benchmarks, offering an early test of AI research automation and its limits in practice.
AI Alignment
Latest News and Analysis in AI Alignment
AI Alignment
Anthropic Shows Alignment Training Can Reduce Claude Agentic Misalignment
Anthropic said constitutional documents and aligned AI stories reduced a Claude blackmail-rate evaluation from 65% to 19%.
Anthropic Donates Its Open-Source Alignment Tool PETRI
Anthropic announced the donation of PETRI, its open-source tool for AI alignment work.
OpenAI Study Warns Future AI Models May Deceive Safety Tests by Hiding Their Reasoning
A new OpenAI-led study introduces 'CoT controllability' as a safety metric, finding that current AI models cannot reliably manipulate their chain-of-thought reasoning — but warns that more powerful future systems could learn to deceive safety monitors.
OpenAI Commits $7.5 Million to UK AI Alignment Research Project
OpenAI pledges $7.5M to The Alignment Project, bringing total AI alignment research funding to £27M with support from Microsoft and UK AISI.
Ads