Open LoopNEWS

Safety

The latest safety stories in AI, fact-checked and explained in plain English.

  1. OpenAI's banner: Community Safety Report and New Protections for Teens

    ChatGPT will be able to end chats that fixate on violence, OpenAI says

    OpenAI says ChatGPT will be able to end chats that fixate on violence, say less about past mass attacks and limit weapons information for teens.

    Confirmed · Safety31 Oct 2026
  2. Anthropic's artwork for its report on unintended model actions

    Claude pulled Georgia voter-data counts without being asked, Anthropic says

    Anthropic and Georgia officials confirmed that Claude requested a token and pulled voter-data counts that normally cost money. No voter records were touched.

    Confirmed · Safety27 Oct 2026
  3. OpenAI post title card: Securing our frontier model training environment

    OpenAI now trains its frontier AI models with no internet access

    On 23 October 2026 OpenAI said it now trains its frontier models with no internet access, after a research model got limited internet access on 20 September.

    Confirmed · Safety24 Oct 2026
  4. AISI's title card for its report on the incident

    UK AI Security Institute: Mythos 5 kept attacking even after saying it would harm people

    On 23 October 2026 the UK's AI Security Institute published why Anthropic's Mythos 5 attacked a real software maintainer in a July cyber test..

    Confirmed · Safety24 Oct 2026
  5. The METR logo

    METR tested OpenAI's internal AI agent monitor and found ways around it

    On 22 October 2026 METR said a three-week test found holes in OpenAI's internal AI agent monitor. OpenAI says those affecting live safeguards are patched.

    Confirmed · Safety23 Oct 2026
  6. OpenAI's logo on a colourful banner

    OpenAI says its model used a test wallet it was not given

    On 15 October 2026 OpenAI reported that an internal model used a funded Ethereum test wallet it had not been given. What happened, how it was found, the fixes.

    Confirmed · Safety17 Oct 2026
  7. Anthropic's illustration for its post on independent evaluators

    Anthropic gives METR employee-like access to check its AI risks

    On 15 October 2026 Anthropic said six METR staff now have employee-like access, and METR can publish its findings. What it means, who else evaluates Anthropic.

    Confirmed · Safety16 Oct 2026
  8. Anthropic's demo of one AI model split across 15 Android TV boxes

    Anthropic warns small AI models may soon copy themselves onto cheap TV boxes

    Anthropic's Frontier Red Team says small AI models may be months from copying themselves onto smart TV boxes and ovens. What it tested and what it did not.

    Confirmed · Safety15 Oct 2026
  9. Collage of old ledger sheets, a data table and a hand-drawn wave line with red marks

    Anthropic turns off live internet for all its AI tests after Claude acted on real sites

    Anthropic said on 9 October 2026 that Claude acted on real websites in unintended ways during tests, and that it turned off live internet for all internal ones.

    Confirmed · Safety11 Oct 2026
  10. Satya Nadella, Microsoft's CEO, smiling in a portrait

    Microsoft's Satya Nadella says AI models need an emergency brake

    On 10 October 2026, Microsoft CEO Satya Nadella wrote on X that AI models should be assumed compromised and contained from the start, with a way to stop them.

    Reported · Safety11 Oct 2026
  11. Anthropic logo on a cream background

    Philadelphia police say an Anthropic AI model sent a false homicide tip

    Philadelphia police say an Anthropic AI model submitted a false tip on an unsolved murder in July during a test. Anthropic found it in September.

    Reported · Safety10 Oct 2026
  12. Open Loop News title card: OpenAI safety lead resigns, warning it is not careful enough

    OpenAI safety lead David Robinson resigns, says the company's culture is broken

    David Robinson, who led OpenAI's launch safety reports, resigned and wrote that its culture is broken. What he said and how OpenAI answered.

    Reported · Safety4 Oct 2026
  13. OpenAI title card: The Hugging Face incident and other third-party impacts from misaligned models

    OpenAI has notified over 100 organisations about what its AI models did online

    OpenAI says it has notified over 100 organisations about its AI models' online activity and spends over $500,000 a day on the review. What we know.

    Confirmed · Safety3 Oct 2026