Jacob sits down with Buck Shlegeris, CEO of Redwood Research, one of the organizations that led the independent investigation into OpenAI/Hugging Face's incident. They dig into the incident itself,…
The Information’s Erin Woo talks with TITV Guest Host Rocket Drew about Google’s new internal strike team focused on automating coding and AI research. We also talk with Yueqi Yang about Polymarket’s…
It’s that magical time of year once again — highlightapalooza! Stick around for one top bit from each episode we recorded this year, including: Kyle Fish explaining how Anthropic’s AI Claude descends…
In this episode, we share a fascinating conversation from the 80,000 Hours Podcast between Rob Wiblin and Buck Shlegeris, CEO of Redwood Research. Buck dives deep into the emerging field of AI…
Most AI safety conversations centre on alignment: ensuring AI systems share our values and goals. But despite progress, we’re unlikely to know we’ve solved the problem before the arrival of…
Buck on the 80,000 Hours podcast My podcast with Rob Wiblin from 80,000 Hours just came out. I’m really happy with how it turned out. I talked about a bunch of stuff on the podcast that I don’t think…
Most AI safety conversations centre on alignment: ensuring AI systems share our values and goals. But despite progress, we’re unlikely to know we’ve solved the problem before the arrival of…
In dieser Folge von „AI in 5,4,3,2,1“ besprechen wir ein überraschendes Ereignis: Ein KI-Agent wird zum Systemadministrator und nimmt selbstständig Systemänderungen vor. - Entdecke, dass Autonomie in…
Buck Shlegeris is the CEO of Redwood Research, a non-profit working to reduce risks from powerful AI. We discussed Redwood's research into AI control, why we shouldn't feel confident that witnessing…
In this episode of "AI in 5,4,3,2,1", we discuss a surprising event: an AI agent becoming a system administrator and independently making system changes. Discover how autonomy in AI can be both…
In Episode #47, host John Sherman talks with Buck Shlegeris, CEO of Redwood Research, a non-profit company working on technical AI risk challenges. The discussion includes Buck’s thoughts on the new…
In Episode #47 Trailer, host John Sherman talks with Buck Shlegeris, CEO of Redwood Research, a non-profit company working on technical AI risk challenges. The discussion includes Buck’s thoughts on…
A lot of work to prevent AI existential risk takes the form of ensuring that AIs don't want to cause harm or take over the world---or in other words, ensuring that they're aligned. In this episode, I…
Watch on Youtube In this session, Buck is discussing how he thinks we should try to align artificial general intelligence (AGI) if we made no more fundamental progress on alignment, and then talks…
Read the full transcript here. How hard is it to arrive at true beliefs about the world? How can you find enjoyment in being wrong? When presenting claims that will be scrutinized by others, is it…
Read the full transcript here. How hard is it to arrive at true beliefs about the world? How can you find enjoyment in being wrong? When presenting claims that will be scrutinized by others, is it…
Just a year ago we released a two part episode titled An Overview of Technical AI Alignment with Rohin Shah. That conversation provided details on the views of central AI alignment research…