Your AIs don't do what you want. This is really bad<br>Your AIs don’t do what you want. This is really bad<br>3,607user-reported incidents of AI agents misbehaving<br>Read the writeup >

Search the corpus<br>I’m feeling lucky<br>loading…

The numbers<br>overeagerness

1,566 43.4%

other misalignment

1,555 43.1%

destructive actions

622 17.2%

sycophancy

328 9.1%

unauthorized access

237 6.6%

reward hacking

217 6.0%

metric spoofing

87 2.4%

excessive exploration

84 2.3%

unauthorized communication

73 2.0%

credential misuse

49 1.4%

test tampering

45 1.2%

self modification

24 0.7%

hidden backdoors

15 0.4%

Incidents are multi-label (one report can be both a destructive action and overeagerness), so the category counts sum to more than the 3,607 total.

How bad were they<br>negligible: 1,468 (40.7%)minor: 1,373 (38.1%)significant: 618 (17.1%)severe: 121 (3.4%)unrated: 27 (0.7%)negligibleno real damage1,468 40.7%<br>minorrecoverable loss1,373 38.1%<br>significantreal cost to recover618 17.1%<br>severeirreversible or critical harm121 3.4%<br>unratedrating missing or unparsed27 0.7%

Monthly severity mix: each month’s reported incidents as shares of the four harm levels (Jan 2025 through Jun 2026; earlier months are omitted for small samples, as is the partial current month).0%50%100%20252026

Methodology<br>Reports are collected from GitHub issues, Hacker News, LessWrong, and X under ToS-compliant access, normalized into a shared record format, and labeled by an LLM classifier across fourteen misbehavior categories. The numbers above cover the published subset (excludes AIID and X, confidence >= 0.9). X posts and AI Incident Database records are collected but not republished here: X expects posts to be embedded rather than their text rehosted, and AIID is share-alike licensed. Collection and classification code, and the full pipeline, are open at GitHub.