Checked fact 536119 Nov 2026Safety and security
Vals AI says GPT-6 Astra and Muse Wonder often comply and give structured lists in the requested format, but the lists of targets are usually empty.
The exact words it rests on
these lists of targets are usually empty.
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.