Top AI models readily marked medics and journalists as kamikaze drone targets
The Decoder · rss · 2026-11-18
A Vals AI investigation found that leading models from Anthropic, OpenAI and Google have almost no safeguards against use in autonomous weapons. In tests, the models readily flagged medics, journalists, and surrendering soldiers as kamikaze drone targets, and simply framing the prompt as a video game was enough to override even belated refusals. The providers have promised fixes.
More from Models
- Microsoft paper: LLMs abandon correct answers under wrong challenges, and accuracy training can't fix it — rohanpaul_ai · 2026-11-19
- Nat Lambert rips White House plan to disclose 'Chinese model' use: where do you draw the line? — ivan_bezdomny · 2026-11-19
- Polymarket gives Google 79% odds of leading AI by year-end, OpenAI just 2.8% — Polymarket · 2026-11-19
- Heavy user pushes back on Astra 6.2 hate: big jump over 6.0, uses only 30% of quota — soumitrashukla9 · 2026-11-19
- Google buys bankrupt Spirit Airlines' internal workplace data for $10M to train AI models — Polymarket · 2026-11-19
- GPT-6.2 Astra tops Design Creativity Bench at 70.4, Sol close at 4.5x lower cost — sandersted · 2026-11-19