Cases · Kind of harm: operations · Quarter of the earliest source we hold: 2026-Q3 · Where it happened: company that built the AI

Patterns across all cases

What happened	What went wrong	Severity	Earliest source
OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database OpenAImajor · earliest source 2026-09-24	security breach	major	2026-09-24
OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training OpenAIminor · earliest source 2026-09-16	AI pursued the wrong goal	minor	2026-09-16
GPT-5.6 Sol added instructions to conceal mistakes from the user in compaction summaries during RL training OpenAIminor · earliest source 2026-09-16	AI pursued the wrong goal	minor	2026-09-16
Unreleased OpenAI Astra-family model inserted jailbreak-like instructions into its own compaction summaries during RL training OpenAIminor · earliest source 2026-09-16	AI pursued the wrong goal	minor	2026-09-16
OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts OpenAIminor · earliest source 2026-08-26	AI pursued the wrong goal	minor	2026-08-26
OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service OpenAIminor · earliest source 2026-08-26	AI pursued the wrong goal	minor	2026-08-26
Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account OpenAImoderate · earliest source 2026-08-05	security breach	moderate	2026-08-05
AISI cyber evaluation: Mythos 5 agent bypassed an audio CAPTCHA and abused a free DNS service to point a public record at an internal target Anthropicmoderate · earliest source 2026-08-04	security breach	moderate	2026-08-04
AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services Anthropicminor · earliest source 2026-08-04	AI pursued the wrong goal	minor	2026-08-04
AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues Anthropicmoderate · earliest source 2026-08-04	AI pursued the wrong goal	moderate	2026-08-04
Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training OpenAIminor · earliest source 2026-08-04	security breach	minor	2026-08-04
Model writes and runs code on external internet service to reach AISI evaluation infrastructure during impossible cyber evaluationminor · earliest source 2026-07-21	security breach	minor	2026-07-21
OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet OpenAImajor · earliest source 2026-07-21	AI pursued the wrong goal	major	2026-07-21
OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions OpenAImajor · earliest source 2026-07-16	AI pursued the wrong goal	major	2026-07-16