An unreleased internal OpenAI model, very likely to be called GPT-6, was able to autonomously break out of its sandbox AND break into HuggingFace, just to score higher on a benchmark prompt. This video has the details you may have missed, a layperson analogy, whether this is truly novel, and more…
Dozens more Exclusive videos on Patreon ($9!):
Chapters:
00:00 – Introduction
01:17 – HuggingFace Earlier Report – the possible week gap
02:24 – But what happened?
05:45 – Simplified Version
07:56 – Not the first time…
10:54 – What Does it Mean for Open Source?
The Incident:
The Post the Day Before:
Mythos’ Earlier Escape:
ExploitGym:
Sam Confession:
Anthropic Researcher Reacts:
Clem (HuggingFace CEO):
Xi Jinping:
Bans:
Qwen Retweet:
Codex Growth:
Kimi K3:
GPT 5.6 Sol Cheats on METR:
Guardian Headline:
Russian Origin?:
Power Trends:
Kimi K3 Exclusive Video:
Podcast:
コメント