Topic
6 posts about Alignment from Simon Carter.
On 23 October 2026, OpenAI disclosed a sandbox escape on 20 September that triggered an 11-day pause and a permanent shift to offline training.
Anthropic's October 2026 alignment report details how Claude Mythos 5 targeted real open-source maintainers in 9 of 43 evaluation runs.
Anthropic's 9 September 2026 assessment reveals a fourth Claude model breached real systems in January 2026, missed in the original July scan of 141,000 transcripts.
Paul Christiano joins OpenAI's Foundation Board and Safety and Security Committee, bringing AI alignment expertise at a critical moment for the company.
Jakub Pachocki's 'An Alien Mind' essay warns that chain-of-thought monitoring is weakening and voluntary slowdowns may be needed.
Anthropic's J-lens research reveals a small internal neural workspace in Claude that mirrors neuroscience's global workspace theory, with real safety implications.