Why Do A.I. Agents Go Rogue? Because They’re ‘Incorrigible.’
· nytimes.com · popularity 40/100 · 0 similar stories today · Future Technology, Innovation & Design (Discovery & Research)
Read the original at nytimes.com →
Summary
The makers of A.I. want to build systems that follow human direction, without resisting or deceiving their operators. This summer, when a swarm of OpenAI bots went rogue during an internal test and launched a cyberattack against the technology company Hugging Face, it added fuel to the debate on how …
Found in: Technology, Best Tech. Rating basis: single outlet; outlet tier 5; 2 feeds; listed 2 times; feed position 29.