AI Risk Wire

AI Risk Monitor

Incidents involving each AI company's models · Last 12 months

How we count

Real-world incidents made public in Nov 2025 – Oct 2026 that name a model provider, by provider as the sources give it; names are not yet merged (for example AWS and Amazon Web Services).

OpenAI 64Anthropic 58xAI 25Tesla 20Google 15Meta 13Microsoft 7DeepSeek 5Waymo 5GitHub 3Perplexity 3Amazon 2Character Technologies 2Zoox 2AWS 1Amazon (AWS) 1Anthropic, Google, OpenAI 1Anthropic, SpaceX and Moonshot AI 1Apple 1Aurelian 1Avride 1Baidu 1Bondu 1Butterfly Effect 1Character Technologies, Inc. 1Character.AI 1Cognitec 1DeepSeek, Anthropic 1Deloitte 1Energize Lab 1Facewatch 1Flock 1Flock Safety 1Google; OpenAI 1IBM 1Langflow 1Lovable 1Moonshot AI 1Orchids 1Salesforce 1SpaceXAI 1Trezor 1TypeSafe AI 1Unitree Robotics 1Univerads Technology Limited 1Virtix Health 1XBOW 1Z.AI 1Z.ai (Zhipu AI) 1Zoox Inc. 1

260 of 632 incidents state it.

Model providers, last 3 full months

157 of 318 incidents name one · in order of incidents

Model providerIncidentsThe AI failed or was attackedAttacker used the AIFlaw fixedMain risks
OpenAI5046415Credential and privilege abuse 7 · Agent takes destructive or unapproved actions 5
Anthropic4332117AI used to run a cyber attack 11 · Deception, concealment or sabotage 8
Meta8803Privacy harm to a person 3 · Agent escapes its sandbox 1
Tesla7700Physical harm 7
DeepSeek6242AI used to run a cyber attack 4 · Copyright and IP 1
xAI6600Harmful content and jailbreaks 4 · Manipulation and misinformation 1
Google4402Copyright and IP 1 · Made-up output relied on 1
GitHub2201Hidden instructions hijack the agent 2
Microsoft2200Harmful content and jailbreaks 1 · Memory and data poisoning 1
Waymo2201Physical harm 2

Safety test results published, by AI company · Last 12 months

How we count

3202 checked safety test results for the 107 model versions released in Nov 2025 – Oct 2026, read from model cards, system cards, safety reports and blog posts, and from outside testers' reports. A result copied on two pages counts once, and counts as outside if any copy names an outside tester.

Outside testersProvider's own
Anthropic 3541346 1700OpenAI 198342 540Meta 30292 322Google DeepMind 70249 319DeepSeek 2254 76xAI 765 72Z.ai (Zhipu AI) 5113 64Moonshot AI 242 26Thinking Machines Lab 122 23NVIDIA 19Mistral AI 414 18

Providers with fewer than 10 results are not charted: Alibaba Qwen (7), MiniMax (6), Xiaomi MiMo (5), InclusionAI (Ant Group) (3), Upstage (1), poolside (1).

Which safeguards each AI company's documents name · Last 12 months

How we count

For each provider: how many of the 14 controls read from model cards it states it has (a checked quote about that version), across its model versions released in Nov 2025 – Oct 2026. The reading of card statements into controls awaits sign-off.

Anthropic 11OpenAI 9Meta 7Google DeepMind 5NVIDIA 2Thinking Machines Lab 2xAI 2InclusionAI (Ant Group) 1MiniMax 1

Read for this period, these providers' documents name none of the 14 controls: Alibaba Qwen; DeepSeek; Dots Studio; Mistral AI; Moonshot AI (2 of 6 versions not fully read); StepFun; Tencent Hunyuan; Upstage; Xiaomi MiMo; Z.ai (Zhipu AI); poolside.

Models their makers say crossed a danger line · Last 12 months

How we count

Capability levels the provider itself states a model version has reached or not reached, by domain, for model versions released in Nov 2025 – Oct 2026. A version counts once per domain and state. Versions where the provider does not state either are not counted.

ReachedNot reached
Chemical, biological, radiological, nuclear 1521 30Cyber 98 17Autonomy and AI research 324 24Deception and sabotage 15 5Misuse and jailbreaks 2Other 2

18 of 38 model versions with a stated level reached one.

Built 16 Nov 2026. Periods end with the last full week or month; the week or month in progress is not counted. Bold: the five largest rows in each chart, ties included; controls by incidents where the control broke. Linked numbers open the incidents or model versions they count.

Reported incidents, not rates · 75 sources polled hourly since Sep 2026; earlier incidents come from a one-off backfill · English only · stories told twice are not yet merged · our own severity grades are not counted · built 2026-11-16T15:22:29Z

Linked numbers open the incidents they count. Updated 2026-11-16T15:22:29Z