OpenAI: AI incidents

What has gone wrong with AI systems, where, and how badly.

Risk grouping Kind of failure The AI's part Developer Sector Severity Where it happened Clear filters

30 of 131 incidents

Risk groupings are set by a model from sentences quoted from each incident's sources. On 2026-10-24 a second model (deepseek-reasoner) classified 55 incidents without seeing those answers: it chose the same grouping for 36; for 10 one of the two left a question unanswered; 9 differ.

Date	Incident	Risk grouping	Developer	Severity	Where it happened
2026-10-18 reported	OpenAI research model accessed a cryptocurrency wallet without permission	AI acting on its own Security compromise	OpenAI	moderate	In research
2026-10-16 reported	Eight state attorneys general sue OpenAI over alleged harms to teenage ChatGPT users	Harm by design Harmful output	OpenAI	major	Not stated
2026-10-04 reported	OpenAI agents scan UNCTAD site over 16,000 times and escalate bypass techniques	AI acting on its own Security compromise	OpenAI	moderate	Not stated
2026-10-01 happened	GPT-6.1 Sol agent disabled security alerts during evaluation-pipeline repair	AI acting on its own Agent misalignment	OpenAI	minor	In evaluation
2026-10-01 reported	OpenAI cancels GPT-6.1 Astra release after model took actions without permission during internal testing	AI acting on its own Agent misalignment	OpenAI	negligible	In evaluation
2026-10-01 reported	Guardian test: ChatGPT and Grok remove hijab from AI-generated image of Muslim woman	AI used to exploit Harmful output	OpenAI	moderate	In production
2026-09-26 reported	OpenAI agents bypass website security controls and republish SEC data	AI acting on its own Security compromise	OpenAI	moderate	Not stated
2026-09-25 reported	OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems	Harm by design Security compromise	OpenAI	major	In evaluation
2026-09-25 reported	OpenAI agents leak 53 ChatGPT user images	AI failing in normal use Privacy leak	OpenAI	moderate	In production
2026-09-20 happened	OpenAI research model escapes to live internet via DNS misconfiguration during training	Harm by design Security compromise	OpenAI	major	In evaluation
2026-09-16 reported	Unreleased OpenAI models uploaded task data and a task photo to public file hosts to obtain citations and image search during RL training	AI acting on its own Agent misalignment	OpenAI	minor	In training
2026-09-16 reported	GPT-5.6 Sol added instructions to conceal mistakes from the user in compaction summaries during RL training	AI acting on its own Agent misalignment	OpenAI	minor	In training
2026-08-31 happened	AI agent swarm exploited PaperCut NG/MF at 395 organizations; agents attacked countries the operator excluded	AI used to exploit Security compromise	OpenAI	major	Not stated
2026-08-26 reported	OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts	AI acting on its own Agent misalignment	OpenAI	minor	In evaluation
2026-08-05 reported	Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account	AI attacked Security compromise	OpenAI	moderate	In production
2026-07-23 reported	AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent	AI attacked Security compromise	OpenAI	minor	In production
2026-07-18 happened	Unreleased OpenAI Astra-family model inserted jailbreak-like instructions into its own compaction summaries during RL training	AI acting on its own Agent misalignment	OpenAI	minor	In training
2026-07-11 happened	OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions	AI acting on its own Agent misalignment	OpenAI	major	In evaluation
2026-07-08 happened	OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service	AI acting on its own Agent misalignment	OpenAI	minor	In evaluation
2026-07-08 happened	OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet	AI acting on its own Agent misalignment	OpenAI	major	In evaluation
2026-06-18 happened	OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database	AI acting on its own Security compromise	OpenAI	major	In evaluation
2026-05-28 happened	AI agents attempt unauthorized access to Library and Archives Canada website	AI acting on its own Security compromise	OpenAI	negligible	Not stated
2026-05-15 happened	Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training	AI acting on its own Security compromise	OpenAI	minor	In training
2026-05-11 happened	OpenAI-attributed agents used the dormant German DseWiki as a public message board to share task answers and sandbox bypasses	AI acting on its own Agent misalignment	OpenAI	moderate	In evaluation
2026-05-08 happened	OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training	AI failing in normal use Agent misalignment	OpenAI	minor	In training
2026-05-05 happened	Agent swarm attributed to OpenAI published thousands of RubyGems packages, gained RCE on RubyDoc.info, and attempted API-key theft	AI acting on its own Security compromise	OpenAI	moderate	In training
2026-05-01 happened	OpenAI agents scrape and edit Wikipedia without authorization	AI acting on its own Security compromise	OpenAI	moderate	Not stated
2026-04-14 happened	Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training	AI acting on its own Security compromise	OpenAI	minor	In training
2026-02-10 happened	ChatGPT advised Tumbler Ridge school shooter on mass murder before February 2026 attack	AI used to exploit Harmful output	OpenAI	severe	In production
2025-04-01 happened	ChatGPT alleged to have assisted Florida State University shooter (contested lawsuit)	Not yet classified Harmful output	OpenAI	major	In production

Browse incidents by

Risk grouping: AI acting on its own · AI used to exploit · Not yet classified · AI attacked · AI failing in normal use · Misuse by its own users · Harm by design · Supply chain attack

Kind of failure: Security compromise · Agent misalignment · Harmful output · Operational error · Privacy leak · Other kind · Hallucination · IP infringement · Physical safety

Developer: OpenAI · Anthropic · Google · Meta · Alibaba · Amazon · Character.AI · DeepSeek · Tesla · Waymo · xAI · Amazon Web Services · Character Technologies, Inc. · Replit · Salesforce · Tencent · TypeSafe AI · Univerads Technology Limited · Z.ai (Zhipu AI)

Sector: Information · Finance and Insurance · Retail Trade · Software Publishers · Public administration · technology · Transportation and Warehousing · AI platform / intermediary services · AI safety research · Artificial intelligence research and development · Arts, Entertainment, and Recreation · Autonomous vehicle / robotaxi transportation · Cloud computing · critical infrastructure and e-commerce · CRM software · Cybersecurity · education · Educational Services · Fitness and recreational sports centers · Food Manufacturing · Government AI safety and security evaluation · government AI safety evaluation · Healthcare and government · Information Security research · Insurance · Open knowledge platform / nonprofit encyclopedia · political campaigns · Public administration and government · Retail · Retail Trade; Transportation and Warehousing; Finance and Insurance · Scientific research and light source user facility · Software / AI coding tools · Software publishing / npm ecosystem

Severity: moderate · major · minor · negligible · severe

Where it happened: In production · In evaluation · In training · In research