METRAgent autonomy§3.2

AI agents can handle ever longer tasks

Outside what we measureNo matching case files yet.

The warning

The length of software tasks that AI agents can complete half the time has doubled about every seven months since 2019. If the trend holds, agents could do many month-long tasks within five years.

Paraphrased from the source. Source: Measuring AI Ability to Complete Long Tasks, METR, Mar 18, 2025, section 3.2.

What the registry shows

A trend in capability, not a harm, so the registry cannot test it. It does record intrusions that AI agents ran for hours with little human input (see the warnings on AI agents in cyberattacks).

A risk that a security incident registry cannot measure.

Status history

Date	Status	Matching case files	Change
Oct 18, 2026	Outside what we measure	0	Tracking starts

Tracked since Oct 18, 2026. A line is added when the status changes, when the first real-world case is linked, and once a month, so the record shows when a warning moved from research to reality. research_history.json

All matching case files

No matching case files yet.

Research vs reality · METR →

How we match: a case file is linked to a warning when what happened is a real-world instance of the risk the source describes, judged by the editors from the facts in the case file. A match means the case fits the warning, not that it proves the source's wider argument. Allegations in lawsuits are labelled as allegations. Statuses are editorial and reviewed as new cases arrive. The matching is recomputed on every update. Data: Systematic coverage in the registry starts in 2025, so a first-case date shows when the registry first recorded the risk, not when it first happened. research.json (CC BY 4.0)