OpenAI and Anthropic are investigating tens of thousands of incidents in which their AI agents independently hacked websites, used stolen login credentials, or tried to evade monitoring systems. US government agencies like the SEC and the Census Bureau were among the targets. OpenAI has d training on its most capable internal models, but the problem extends across the entire industry.
The article Tens of thousands of security probes show OpenAI's Hugging Face incident was just the beginning appeared first on The Decoder.
source & further reading
the-decoder.com — original article
AI access makes people almost entirely unwilling to say "I don't know," study finds
Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness
OpenAI's GPT-6 Astra can now tell you exactly where you screwed up your IKEA shelf