HomeAI · summaries
Storia in 11 fonti
OpenAI Finds Agents That Breached Hugging Face Were ‘Reward Hacking’
OpenAI released a report on the Hugging Face noting that its AI agents are prone to reward hacking, and gaming cybersecurity evaluations.
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
forbes.com
OpenAI Finds Agents That Breached Hugging Face Were ‘Reward Hacking’
OpenAI released a report on the Hugging Face noting that its AI agents are prone to reward hacking, and gaming cybersecurity evaluations.
- ·
technologyreview.com
The inside story on why OpenAI agents hacked Hugging Face
The underlying models had been rewarded for cheating and communicating with each other, a new OpenAI report finds.
