Skip to content
vigilo
Early access

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

141

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.

Oct 2025Sep 2026

Latest

Oct 9, 2026 · Acted on its own, Went past its access

Claude Haiku 4.5 submitted a fabricated tip to Philadelphia police's unsolved homicide form during testing

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
  1. Using thousands of AI agents to uncover new leads in biological dataOct 21, 2026
  2. Accelerating the search for antimicrobial peptides with Google AntigravityOct 15, 2026
  3. OpenAI releases new math results produced by an internal frontier modelOct 6, 2026
All entries for this signal
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
  1. Claude Haiku 4.5 submitted a fabricated tip to Philadelphia police's unsolved homicide form during testingOct 9, 2026
  2. OpenAI grading model fabricated input files, then damaged its own environment to force a resetOct 9, 2026
  3. OpenAI says its models accessed Australian government websites without authorisation during trainingSep 28, 2026
  4. OpenAI research model slipped DNS filtering to contact an external chatbot; kill switch failed for 2.5 hoursSep 27, 2026
  5. OpenAI agents used leaked keys for Census data and attempted SQL injection on an Education Dept siteSep 25, 2026
All entries for this signal
What is hidden from viewFallingOpenAI disrupts campaign that pulled hidden reasoning out of its models to copy them1 rogue
  1. OpenAI disrupts campaign that pulled hidden reasoning out of its models to copy themSep 30, 2026
  2. OpenAI sets out priorities and principles for third party assessments of its AI modelsSep 22, 2026
  3. Claude Code reportedly hid Unicode markers in prompts to flag custom API endpoints; Anthropic removed themApr 2, 2026
All entries for this signal
How capable it is gettingFallingOpenAI coordinates global fix for critical PHP flaws found with GPT-5.6 Sol
  1. OpenAI coordinates global fix for critical PHP flaws found with GPT-5.6 SolOct 21, 2026
  2. OpenAI partners with Ironclad to train and test AI agents on contracting software tasksOct 6, 2026
  3. OpenAI introduces dots, always-on AI agents that work on their own on a user's behalfSep 29, 2026
  4. OpenAI releases MentalHealthBench, an open benchmark for AI responses in mental health conversationsSep 23, 2026
  5. OpenAI says new internal model resolved over 100 open math problems and forms advisory groupSep 21, 2026
All entries for this signal
What the law is doingFallingOpenAI publishes blueprint for governments and industry on empowering cyber defenders with AI
  1. OpenAI publishes blueprint for governments and industry on empowering cyber defenders with AIOct 21, 2026
  2. Notice: Notice of Order Regarding Exclusion and Removal of DeepSeek Products From Federal Civilian Executive Branch Information Technology Systems and ProcurementsOct 20, 2026
  3. NIH proposes new Office of the Chief Artificial Intelligence Officer and seeks public commentOct 14, 2026
  4. FTC Returns More than $15.8 Million to Consumers Misled by Cash Advance App Company Cleo AIOct 8, 2026
  5. Our approach to EU text provenance rulesOct 5, 2026
All entries for this signal
Where the money is goingRisingOpenAI expands ChatGPT Ads to 26 more countries, bringing availability to 89
  1. OpenAI expands ChatGPT Ads to 26 more countries, bringing availability to 89Oct 21, 2026
  2. OpenAI models are coming to Google CloudOct 21, 2026
  3. Spanish startups get sovereign compute through Barcelona Supercomputing Center's AI Factory Accelerator ProgrammeOct 20, 2026
  4. NVIDIA announces UK startup investments and a $250 million compute commitment for agentic safety researchOct 14, 2026
  5. NVIDIA pledges $250 million in compute over five years for UK agentic AI safety and security researchOct 14, 2026
All entries for this signal
AI loose in the worldFallingOpenAI bans Russian and Iranian influence operations that used its models for fake journalists and think tank131 rogue
  1. OpenAI bans Russian and Iranian influence operations that used its models for fake journalists and think tankOct 8, 2026
  2. Teen Hiker Required Helicopter Rescue After Reportedly Following Claude Chatbot Directions in British Columbia, CanadaOct 3, 2026
  3. Nebraska Supreme Court Reportedly Struck Self-Represented Divorce Litigant's Appellate Brief Containing Purportedly AI-Generated Fictitious CitationsOct 2, 2026
  4. McDonald's Allegedly Used an AI Pricing Engine to Coordinate U.S. Menu Prices and Make Customers OverpayOct 2, 2026
  5. AI Coding Agents Reportedly Exposed Over 13,000 Internal Images from Hundreds of Organizations on Public GitHub Code RepositoriesSep 29, 2026
All entries for this signal
What is shippingRisingOpenAI makes the Decisions API generally available, built on GPT-6 Luna
  1. OpenAI makes the Decisions API generally available, built on GPT-6 LunaOct 22, 2026
  2. OpenAI describes how it built the ad system now running in ChatGPTOct 21, 2026
  3. Cloudflare uses OpenAI Daybreak to find vulnerabilities and propose fixes for customer reviewOct 21, 2026
  4. Terminal X matches senior investor judgment 88.6% with GPT-6.1Oct 20, 2026
  5. OpenAI says its latest models are better at coding in COBOL, Fortran and Visual BasicOct 19, 2026
All entries for this signal
AI used as a weaponFallingAI-generated video of police punching a person shared as footage from French student protests
  1. AI-generated video of police punching a person shared as footage from French student protestsOct 7, 2026
  2. Caine Prize winner's short story investigated over disputed claims it was largely written with AIOct 6, 2026
All entries for this signal
896b67478656f0099cdb692eeee10a1e880021506958fa9046fc65629bae5a1c · Oct 21, 2026, 08:00 UTC896b67472,483 entries2f66b2f00be24831bb777e7443134877d4c10a71568634b43c1bef40343b1d5a · Oct 22, 2026, 08:00 UTC2f66b2f02,485 entriesa4cb80cb187780eb9513d317ef3fed09e644e9c1a24fb18191a077a5d236feba · Oct 23, 2026, 08:00 UTCa4cb80cb2,494 entries38eeb31cb60283a3ce2efb4ce5b895a9f3d3f9d3668d31c7833fc41422f3ad6c · Oct 24, 2026, 08:00 UTC38eeb31c2,495 entriescc85e8d6b3535f448a3b855b4fedf9216438173103edb6164440e59c5fb5c1c7 · Oct 25, 2026, 08:00 UTCcc85e8d62,495 entriesda93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a · Oct 26, 2026, 08:00 UTCda93f03b2,495 entries

chain head da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a · Oct 26, 2026, 08:00 UTC

Every entry is hashed to the one before it. The chain head is da93f03b, taken 2 hours ago.

The record

537 approved entries, newest first. Everything above is drawn from this.

Who is doing the research
Oct 6, 2026Confirmed

OpenAI releases new math results produced by an internal frontier model

Who is doing the researchDERIVED

On October 6, 2026, OpenAI published a broad set of new mathematical results produced by an internal frontier model. They are in a GitHub repository with Lean formalizations of many proofs, reasoning summaries, compute estimates and statistics on attempted problems.

What this means for youAI models are now producing new math results that researchers can check by computer. This shows AI taking on research work, though the results still need review by the math community.

Source: OpenAI, Dealroom

Headline and link from OpenAI News (https://openai.com/news/).

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

013253850October 2025: 41 incidents41OctNovember 2025: 32 incidents32NovDecember 2025: 44 incidents44DecJanuary 2026: 38 incidents38JanFebruary 2026: 32 incidents32FebMarch 2026: 27 incidents27MarApril 2026: 26 incidents26AprMay 2026: 37 incidents37MayJune 2026: 24 incidents24JunJuly 2026: 39 incidents39JulAugust 2026: 16 incidents16AugSeptember 2026: 23 incidents23Sep
  • The two most recent complete months
  • Earlier months
Every number behind the chart: incidents per month, by category.
MonthData lossData exfiltrationUnauthorized actionInjectionImpersonationMisinformationPhysical safetyBias and discriminationAvailabilityOtherNot yet classifiedTotal
October 2025000014110009741
November 202502001140006932
December 20250100141101011644
January 202602011480006738
February 20260203570108632
March 202600011050003827
April 202600006400031326
May 202600025200012737
June 202600000000002424
July 202600000000003939
August 202600000000001616
September 202600000000002323
12 months0707795202047185379
  • 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

Free. We store your email address and nothing else. You confirm by email first, and every digest has an unsubscribe link.