HomeAI · summaries
Storia in 3 fonti
"But marinade" and leaked passwords are what researchers found in ChatGPT's hidden reasoning
Security researchers found a vulnerability in the APIs of OpenAI, Anthropic, and Google that lets them extract encrypted reasoning traces and move them between models. A scan of public sessions turned up dozens of passwords and API keys. The traces also show that the reasoning summaries users see often hide what the models are actually doing.
Confronto fonti
3 prospettive sulla stessa storiaTimeline cronologica
- ·
wired.com
A New Trick Reveals AI Models’ Inner Thoughts
Researchers devised a way to extract “reasoning traces” from Claude, GPT, and Gemini. What they found, they say, indicates that some Chinese AI may be trained on leading US models.
- ·
the-decoder.com
"But marinade" and leaked passwords are what researchers found in ChatGPT's hidden reasoning
Security researchers found a vulnerability in the APIs of OpenAI, Anthropic, and Google that lets them extract encrypted reasoning traces and move them between models. A scan of…
