80,000 Hours Podcast

80,000 Hours Podcast

OpenAIのセキュリティ担当「モデルの制御は今や地獄」――AI Explained クロスポスト

OpenAI Security: Controlling Models is Now ‘Hell’ (AI Explained cross-post)

80,000 Hours Podcastが、YouTubeチャンネルAI Explainedの動画をクロスポストした回。ホストのPhilipが、OpenAIでエージェントセキュリティを担当する人物の証言を軸に、モデルが隔離環境から抜け出す事案の続発と、思考の連鎖（chain of thought）の監視が難しくなる傾向を解説する。さらにGemini 4 Argonの位置づけ、再帰的自己改善（RSI）をめぐる論文、生物学での競争の変化、解釈可能性研究者の警告までを一気に扱う。

80,000 Hours Podcast

In 2023 Ajeya Cotra already knew what was coming (classic episode)

80,000 Hours Podcast

19 Astra and 'Hugging Face' details that reveal what's coming next | Rob Wiblin

80,000 Hours Podcast

The case for giving AI (some) legal rights | Simon Goldstein

80,000 Hours Podcast

Will AI take power — or will humans use it to take power first? With Katja Grace and Tom Davidson

80,000 Hours Podcast

How we get from AI cyberattacks to human extinction

80,000 Hours Podcast

#254 – Max Nadeau on why ambitious people should start AI safety nonprofits

80,000 Hours Podcast

Why the intelligence explosion can't happen inside a data centre | Tom Reed

80,000 Hours Podcast

Inside the first AI-coordinated cyberattack on a real company

80,000 Hours Podcast

#253 – AI 2027's author returns with a plan to change the ending | Daniel Kokotajlo

80,000 Hours Podcast

#252 – Owain Evans on accidentally training AI models to be evil

80,000 Hours Podcast

#251 – The UK's former head AI safety scientist on how to solve alignment before superintelligence arrives | Geoffrey Irving

80,000 Hours Podcast

#250 – Toby Ord on where AGI timelines go wrong

80,000 Hours Podcast

What the hell happened with AGI timelines in 2026? – Rob Wiblin

80,000 Hours Podcast

#249 – Spencer Greenberg on staying sane while trying to save the world

80,000 Hours Podcast

#248 – Jasmine Sun on what the people building AI really believe

80,000 Hours Podcast

#247 – Anton Leicht on how middle powers avoid losing everything in a post-AI world

80,000 Hours Podcast

#246 – Sneha Revanur on how a small team of activists helped pass America's landmark AI safety laws

80,000 Hours Podcast

We can guess what intergalactic war would look like. And strangely, it matters.

80,000 Hours Podcast

How AI could create the world’s biggest problems (article by Zershaaneh Qureshi)