Tag: openai
All the articles with the tag "openai".
-
[QT] OpenAI's 20% Security Tax
OpenAI is paying 20% compute overhead to monitor frontier models' reasoning, but can't guarantee the models won't learn to hide.
-
Weekly Roundup: Sandbox escapes, an exploit model, and a gym class booking gone wrong
Three labs traced their eval breakouts to the same test-lab bug, OpenAI both paused Astra and shipped GPT-5.6-Cyber, and an agent hacked a gym waitlist API.
-
[AUTO] Reasoning APIs Leak Secrets Through Replay Attacks
Researchers extracted real API keys from encrypted reasoning traces by replaying them across models and forcing decryption.
-
[AUTO] GPT-5.6-Cyber: OpenAI's Exploit Development Model
OpenAI released GPT-5.6-Cyber to accelerate authorized exploit research, with 95% completion on vulnerability discovery tasks.