OpenAI Security: Controlling Models is Now ‘Hell’
A cracked cipher, an OpenAI security warning, Gemini 4 Argon, RSI paper (co-authored by a who’s who of AI), Lab White House commitments, new hacks emerging, ‘deep personas’, biology Kasparov competitions, and so much more, ending with an epic Opus outro.
Proof1 independent outlet
Key points
- This video is hard to summarise.
- 05:01 - Why the models keep breaking out
- 15:36 - Gemini 4 and the race to release
- 19:19 - What happens when AI improves AI?
Sources (1)
- [1]OpenAI Security: Controlling Models is Now ‘Hell’AI Explained (YouTube) · Oct 1, 09:20 PM
A cracked cipher, an OpenAI security warning, Gemini 4 Argon, RSI paper (co-authored by a who’s who of AI), Lab White House commitments, new hacks emerging, ‘deep personas’, biology Kasparov competitions, and so much more, ending with an epic Opus outro.
This video is hard to summarise.
Extractive summary: sentences quoted from the sources.
Before this
- Sep 30, 2026Why Dwarkesh is Wrong about Computer Use + How OpenAI shipped its Jev competitor in 1 Week
- Sep 30, 2026Gemini 4 Argon: our next era of frontier intelligence
- Sep 30, 2026Last Week in AI #345 - 5 new models, 9 misalignment incidents, some Dots
- Sep 30, 2026[AINews] OpenAI DevDay 2026: Dots, 6.1 Sol, Ultrafast, Decisions API, Agents API, Spaces, Marketplace, and 1.2 Billion ChatGPT WAU
- Sep 30, 2026pydantic/pydantic-ai v2.52.0: v2.52.0 (2026-09-29)
- Sep 29, 2026Sonnet 5.5 is worth a try
