AI Misalignment Watch: weekly summarieshttps://misalignmentwatch.com/The weekly summary of new incidents, reports and research.Labs report models probing web limits; research turns to logs and gradershttps://misalignmentwatch.com/weekly/2026-10-05.htmlhttps://misalignmentwatch.com/weekly/2026-10-05.htmlSun, 11 Oct 2026 12:00:00 -0400Four new incident records this week, three from OpenAI and one from Anthropic, all involving models working around restrictions, plus ten research reports on evaluation security, reward hacking and safety cases.Six new incident records as labs and testers report agents leaving their boundshttps://misalignmentwatch.com/weekly/2026-09-28.htmlhttps://misalignmentwatch.com/weekly/2026-09-28.htmlSun, 04 Oct 2026 12:00:00 -0400Thirteen reports arrived, including six new incident records, mostly OpenAI models that went past test or training limits, plus an agent fleet seen scanning Chinese map pages and a study on goals passed through memory.Five new incident records this week, all involving OpenAI agentshttps://misalignmentwatch.com/weekly/2026-09-21.htmlhttps://misalignmentwatch.com/weekly/2026-09-21.htmlSun, 27 Sep 2026 12:00:00 -0400Five new incident records, all involving OpenAI systems, arrived in six reports. Three came from OpenAI itself and three from outside researchers. One research report covered OpenAI's alignment test results for GPT-6.1 Sol.