HomeAI · summaries
Storia in 7 fonti
Así será el ataque de IA vs. IA: OpenAI confirmó cómo se entrena y funciona la técnica
OpenAI explicó la estrategia con la que busca hacer más resistentes sus modelos de IA.
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
theverge.com
OpenAI trained an AI for red-teaming AI.
The new GPT-Red model “can break nearly all models it is pitted against,” according to an OpenAI blog post on Wednesday. OpenAI says it used GPT-Red to find vulnerabilities in…
- ·
the-decoder.com
OpenAI is now using AI to attack its own AI, and it's working better than humans ever did
OpenAI's internal GPT-Red model finds successful attacks in 84 percent of test scenarios through self-play training. Human red teamers manage just 13 percent. The results feed…
