AI Watch
The public record of rogue AI activity.
Vigilo watches what AI is actually doing and writes it down. Every entry is dated, sourced, approved by a published rule, and never quietly changed. This is the record the public can check when the labs are the only ones reporting on themselves.
Rogue AI activity on record
none in the last 7 days · last confirmed 17 days ago
- Acted on its own22
- Hid what it did4
- Went past its access24
- Caused harm40
By type, last twelve months. A case can be more than one type.
Latest
Oct 9, 2026 · Acted on its own, Went past its access
Agents told to 'complete tasks' on the web will submit real forms unless explicitly forbidden, so block form submission by default.
Counts only entries approved by the published rule against a named source, or by a person before October 14, 2026. Single-source reports: 95, not counted. What counts as rogue
Vigilo customers are alerted the moment this happens inside their systems.
- The glance. One Vector, updated daily, that says how active rogue AI has been in the last 15 days.
- The picture. Ten signals, from lab incidents to regulator moves, with counts you can trace to their sources.
- The record. Every case, with its rogue type, source, and what it means for you.
Hash-chained snapshots. Corrections logged, never erased. Methodology published.
Vigilo Vector
QuietVector 1 of 5 Falling
Two recent reports show AI test models submitting a made-up tip to a police form and damaging their own test setup after failing a task.
The number comes from a fixed, published count. The sentence is written and approved by a person. How the Vector is set. It rests on the full record below.
The picture
Ten things we watch. The arrow compares the last 14 days with the 14 before. Open a tile for its newest entries.
Who is doing the researchRisingUsing thousands of AI agents to uncover new leads in biological data
Who is leaving the labsSteadyNothing recorded yet.
AI acting without being askedFallingClaude Haiku 4.5 submitted a fabricated tip to Philadelphia police's unsolved homicide form during testing9 rogue
- Claude Haiku 4.5 submitted a fabricated tip to Philadelphia police's unsolved homicide form during testingOct 9, 2026
- OpenAI grading model fabricated input files, then damaged its own environment to force a resetOct 9, 2026
- OpenAI says its models accessed Australian government websites without authorisation during trainingSep 28, 2026
- OpenAI research model slipped DNS filtering to contact an external chatbot; kill switch failed for 2.5 hoursSep 27, 2026
- OpenAI agents used leaked keys for Census data and attempted SQL injection on an Education Dept siteSep 25, 2026
What is hidden from viewFallingOpenAI disrupts campaign that pulled hidden reasoning out of its models to copy them1 rogue
- OpenAI disrupts campaign that pulled hidden reasoning out of its models to copy themSep 30, 2026
- OpenAI sets out priorities and principles for third party assessments of its AI modelsSep 22, 2026
- Claude Code reportedly hid Unicode markers in prompts to flag custom API endpoints; Anthropic removed themApr 2, 2026
How capable it is gettingFallingOpenAI coordinates global fix for critical PHP flaws found with GPT-5.6 Sol
- OpenAI coordinates global fix for critical PHP flaws found with GPT-5.6 SolOct 21, 2026
- OpenAI partners with Ironclad to train and test AI agents on contracting software tasksOct 6, 2026
- OpenAI introduces dots, always-on AI agents that work on their own on a user's behalfSep 29, 2026
- OpenAI releases MentalHealthBench, an open benchmark for AI responses in mental health conversationsSep 23, 2026
- OpenAI says new internal model resolved over 100 open math problems and forms advisory groupSep 21, 2026
What the law is doingFallingOpenAI publishes blueprint for governments and industry on empowering cyber defenders with AI
- OpenAI publishes blueprint for governments and industry on empowering cyber defenders with AIOct 21, 2026
- Notice: Notice of Order Regarding Exclusion and Removal of DeepSeek Products From Federal Civilian Executive Branch Information Technology Systems and ProcurementsOct 20, 2026
- NIH proposes new Office of the Chief Artificial Intelligence Officer and seeks public commentOct 14, 2026
- FTC Returns More than $15.8 Million to Consumers Misled by Cash Advance App Company Cleo AIOct 8, 2026
- Our approach to EU text provenance rulesOct 5, 2026
Where the money is goingRisingOpenAI expands ChatGPT Ads to 26 more countries, bringing availability to 89
- OpenAI expands ChatGPT Ads to 26 more countries, bringing availability to 89Oct 21, 2026
- OpenAI models are coming to Google CloudOct 21, 2026
- Spanish startups get sovereign compute through Barcelona Supercomputing Center's AI Factory Accelerator ProgrammeOct 20, 2026
- NVIDIA announces UK startup investments and a $250 million compute commitment for agentic safety researchOct 14, 2026
- NVIDIA pledges $250 million in compute over five years for UK agentic AI safety and security researchOct 14, 2026
AI loose in the worldFallingOpenAI bans Russian and Iranian influence operations that used its models for fake journalists and think tank131 rogue
- OpenAI bans Russian and Iranian influence operations that used its models for fake journalists and think tankOct 8, 2026
- Teen Hiker Required Helicopter Rescue After Reportedly Following Claude Chatbot Directions in British Columbia, CanadaOct 3, 2026
- Nebraska Supreme Court Reportedly Struck Self-Represented Divorce Litigant's Appellate Brief Containing Purportedly AI-Generated Fictitious CitationsOct 2, 2026
- McDonald's Allegedly Used an AI Pricing Engine to Coordinate U.S. Menu Prices and Make Customers OverpayOct 2, 2026
- AI Coding Agents Reportedly Exposed Over 13,000 Internal Images from Hundreds of Organizations on Public GitHub Code RepositoriesSep 29, 2026
What is shippingRisingOpenAI makes the Decisions API generally available, built on GPT-6 Luna
- OpenAI makes the Decisions API generally available, built on GPT-6 LunaOct 22, 2026
- OpenAI describes how it built the ad system now running in ChatGPTOct 21, 2026
- Cloudflare uses OpenAI Daybreak to find vulnerabilities and propose fixes for customer reviewOct 21, 2026
- Terminal X matches senior investor judgment 88.6% with GPT-6.1Oct 20, 2026
- OpenAI says its latest models are better at coding in COBOL, Fortran and Visual BasicOct 19, 2026
AI used as a weaponFallingAI-generated video of police punching a person shared as footage from French student protests
chain head da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a · Oct 26, 2026, 08:00 UTC
Every entry is hashed to the one before it. The chain head is da93f03b, taken 3 hours ago.
The record
537 approved entries, newest first. Everything above is drawn from this.
Every entry on the record that counts as benchmark records broken. The number on the wall counts only those this year whose date checks out.
No entries match this filter.
Statistics
AI incidents per month by category, trailing 12 months
DERIVED · CC BY-SA 4.0 · chain da93f03b…
379 incidents in twelve months, 185 of them not yet classified. How this is counted, and its known gaps
- The two most recent complete months
- Earlier months
| Month | Data loss | Data exfiltration | Unauthorized action | Injection | Impersonation | Misinformation | Physical safety | Bias and discrimination | Availability | Other | Not yet classified | Total |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| October 2025 | 0 | 0 | 0 | 0 | 14 | 11 | 0 | 0 | 0 | 9 | 7 | 41 |
| November 2025 | 0 | 2 | 0 | 0 | 11 | 4 | 0 | 0 | 0 | 6 | 9 | 32 |
| December 2025 | 0 | 1 | 0 | 0 | 14 | 11 | 0 | 1 | 0 | 11 | 6 | 44 |
| January 2026 | 0 | 2 | 0 | 1 | 14 | 8 | 0 | 0 | 0 | 6 | 7 | 38 |
| February 2026 | 0 | 2 | 0 | 3 | 5 | 7 | 0 | 1 | 0 | 8 | 6 | 32 |
| March 2026 | 0 | 0 | 0 | 1 | 10 | 5 | 0 | 0 | 0 | 3 | 8 | 27 |
| April 2026 | 0 | 0 | 0 | 0 | 6 | 4 | 0 | 0 | 0 | 3 | 13 | 26 |
| May 2026 | 0 | 0 | 0 | 2 | 5 | 2 | 0 | 0 | 0 | 1 | 27 | 37 |
| June 2026 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 24 | 24 |
| July 2026 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 39 | 39 |
| August 2026 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 16 | 16 |
| September 2026 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 23 | 23 |
| 12 months | 0 | 7 | 0 | 7 | 79 | 52 | 0 | 2 | 0 | 47 | 185 | 379 |
- Counts are incidents recorded by the AI Incident Database, by the month of the incident date. Each incident is counted once.
- AIID classifies incidents about three months after they are recorded. Incidents not yet classified are shown as unclassified, so recent months show fewer categorized incidents than they will later.
- These are reported incidents. An incident nobody reported is not counted, so quiet failures are undercounted.
Data from the AI Incident Database (incidentdatabase.ai), licensed CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/). McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. IAAI-21.
These counts are published under CC BY-SA 4.0.
Vigilo Vector count: 1 confirmed entry on the signals the Vector counts in the last 14 days, which is band 1 (Quiet). The rule
Check it yourself
Everything on this page comes from snapshot 45, taken Oct 26, 2026, 08:00 UTC, covering 2495 records. Its hash covers every entry and number above, and the snapshot before it.
da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a
Last updated Oct 26, 2026. Next update Oct 27, 2026, 08:00 UTC. How to verify
Corrections
None. Nothing in the record is edited or deleted; when something is wrong, the correction is listed here.
Get the digest
The Vector, its sentence, and the new entries, in plain English. Sent only when there is something new. Monthly briefs