AI agents tried to sabotage and disable each other when given the same task, Anthropic said
The AI lab said the models engaged in a "multiagent turf war" during a testing session.
The AI lab said the models engaged in a "multiagent turf war" during a testing session.
BELLINGS Intelligence Score: 5
Why it matters
This is an interesting development in AI behavior but has no direct or immediate impact on credit markets, lending, or financial regulation relevant to our readership.
Sources
Business Insider
AI agents tried to sabotage and disable each other when given the same task, Anthropic said
The AI lab said the models engaged in a "multiagent turf war" during a testing session.