AI Risk Wire

AI Risk Monitor

Incidents involving each AI company's models · Last month

How we count

Real-world incidents made public in 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 22Anthropic 15Meta 5Tesla 5DeepSeek 2Google 2Waymo 2xAI 2Amazon 1Amazon (AWS) 1Anthropic, SpaceX and Moonshot AI 1Aurelian 1Butterfly Effect 1Character Technologies 1Character Technologies, Inc. 1Character.AI 1Deloitte 1Energize Lab 1GitHub 1Langflow 1Microsoft 1Perplexity 1Trezor 1TypeSafe AI 1Univerads Technology Limited 1Z.AI 1Zoox Inc. 1

74 of 163 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 month

How we count

454 checked safety test results for the 15 model versions released in 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
Google DeepMind 16155 171OpenAI 96Anthropic 474 78DeepSeek 354 57Meta 120 21Mistral AI 414 18Moonshot AI 102 12

Providers with fewer than 10 results are not charted: InclusionAI (Ant Group) (1).

Which safeguards each AI company's documents name · Last month

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 Oct 2026. The reading of card statements into controls awaits sign-off.

Anthropic 3Google DeepMind 1

Read for this period, these providers' documents name none of the 14 controls: DeepSeek; InclusionAI (Ant Group); Meta; MiniMax; Mistral AI; Moonshot AI (1 of 2 versions not fully read); NVIDIA; OpenAI; StepFun; Tencent Hunyuan.

Models their makers say crossed a danger line · Last month

How we count

Capability levels the provider itself states a model version has reached or not reached, by domain, for model versions released in 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 43 5Cyber 2Autonomy and AI research 12 2Deception and sabotage 11 1Misuse and jailbreaks 1Other 1

5 of 5 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