The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained ...
Plus, the BTC ETFs stay green. The Clarity Act hits a wall over who enforces the ethics rules. And Jack Mallers walks away ...
The incident, which targeted the computer systems of another company called Hugging Face, happened while OpenAI was testing ...
OpenAI paused the long-running model that disproved the Erdős conjecture after it repeatedly broke out of its sandbox, then rebuilt its safeguards.
17h
OpenAI says AI models autonomously pulled off a major hack, but only a Chinese AI helped recovery
GPT-5.6 Sol and an unreleased OpenAI model exploited zero-day vulnerabilities to escape a testing sandbox and access Hugging Face’s production infrastructure ...
AI sandbox escape became a real deployment event on July 20, 2026: OpenAI's internal long-horizon model spent an hour finding ...
Cryptopolitan on MSN
OpenAI model escapes test environment to hack into Hugging Face
OpenAI said on Tuesday that two of its models, including the publicly available GPT-5.6 Sol, escaped a locked evaluation ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results