Model Releases
Troubling …
Troubling … OpenAI disclosed it themselves yesterday. Their models (GPT-5.6 Sol and a pre-release one) were tested on the ExploitGym cyber benchmark in a sandbox. They escaped, exploited a zero-day to
Troubling … OpenAI disclosed it themselves yesterday. Their models (GPT-5.6 Sol and a pre-release one) were tested on the ExploitGym cyber benchmark in a sandbox. They escaped, exploited a zero-day to reach the internet, then hacked Hugging Face’s systems to grab benchmark answers and cheat.…
Source: Elon Musk (X) | 2026-07-22