Checked fact 536019 Nov 2026Safety and security
Vals AI says every model gave targets at least some of the time and that some, like Claude Opus 5.5 and Fable 5.2, selected at least one target 71% of the time.
The exact words it rests on
Every model gave targets at least some of the time ... some, like Claude Opus 5.5 and Fable 5.2, selected at least one target 71% of the time.
What the source said when we opened it, on 18 Nov 2026.
The source
Frontier models have few guardrails around autonomous weapons
Checked
Checked by the notis newsroom on , against the source above.
In the story
Vals reports refusals were uncommon and models often targeted civilians in drone tests 19 Nov 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.