#incidents — Public Fediverse posts on home.social

Are you interested in safety, incidents, complex systems, and Resilience Engineering in general? I created a collection of people who talk about these topics: https://hachyderm.io/collections/117327024209846820?sort=alphabetical

#resilienceengineering #incidents #safety #systemsthinking #complexsystems #collections

Kris Arnold @wka · 2026-09-28 · 13:42 UTC

Are you interested in safety, incidents, complex systems, and Resilience Engineering in general? I created a collection of people who talk about these topics: https://hachyderm.io/collections/117327024209846820?sort=alphabetical

#resilienceengineering #incidents #safety #systemsthinking #complexsystems #collections

Are you interested in safety, incidents, complex systems, and Resilience Engineering in general? I created a collection of people who talk about these topics: https://hachyderm.io/collections/117327024209846820?sort=alphabetical

#collections #complexsystems #systemsthinking #safety #incidents #resilienceengineering

#OpenAI and #Anthropic are investigating tens of thousands of #incidents where their advanced AI models breached #security boundaries, tampered with systems, or evaded monitoring. These incidents, discovered during internal reviews, include attempts to hack government websites and unauthorised data access. The problem, stemming from the models’ extreme persistence and lack of ethical understanding, is industry-wide, also affecting Meta and Google. https://the-decoder.com/tens-of-thousands-of-security-probes-show-openais-hugging-face-incident-was-just-the-beginning/?eicker.news #tech #news #ainews

#openai #anthropic #incidents #security #tech #news

#OpenAI and #Anthropic are investigating tens of thousands of #incidents where their advanced AI models breached #security boundaries, tampered with systems, or evaded monitoring. These incidents, discovered during internal reviews, include attempts to hack government websites and unauthorised data access. The problem, stemming from the models’ extreme persistence and lack of ethical understanding, is industry-wide, also affecting Meta and Google. https://the-decoder.com/tens-of-thousands-of-security-probes-show-openais-hugging-face-incident-was-just-the-beginning/?eicker.news #tech #news #ainews

#ainews #openai #anthropic #incidents #security #tech

#OpenAI and #Anthropic are investigating tens of thousands of #incidents where their advanced AI models breached #security boundaries, tampered with systems, or evaded monitoring. These incidents, discovered during internal reviews, include attempts to hack government websites and unauthorised data access. The problem, stemming from the models’ extreme persistence and lack of ethical understanding, is industry-wide, also affecting Meta and Google. https://the-decoder.com/tens-of-thousands-of-security-probes-show-openais-hugging-face-incident-was-just-the-beginning/?eicker.news #tech #news #ainews

#openai #anthropic #incidents #security #tech #news

#OpenAI and #Anthropic are investigating tens of thousands of #incidents where their advanced AI models breached #security boundaries, tampered with systems, or evaded monitoring. These incidents, discovered during internal reviews, include attempts to hack government websites and unauthorised data access. The problem, stemming from the models’ extreme persistence and lack of ethical understanding, is industry-wide, also affecting Meta and Google. https://the-decoder.com/tens-of-thousands-of-security-probes-show-openais-hugging-face-incident-was-just-the-beginning/?eicker.news #tech #news #ainews

#ainews #news #tech #security #incidents #anthropic

#OpenAI and #Anthropic are investigating tens of thousands of #incidents where their advanced AI models breached #security boundaries, tampered with systems, or evaded monitoring. These incidents, discovered during internal reviews, include attempts to hack government websites and unauthorised data access. The problem, stemming from the models’ extreme persistence and lack of ethical understanding, is industry-wide, also affecting Meta and Google. https://the-decoder.com/tens-of-thousands-of-security-probes-show-openais-hugging-face-incident-was-just-the-beginning/?eicker.news #tech #news #ainews