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

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

Author: The 80,000 Hours team August 11, 2026 Duration: 2:02:16

When should governments slow the race toward superintelligence? According to Geoffrey Irving, the careful answer is sometime in the past. The useful answer is now.

Geoffrey — formerly a safety researcher at OpenAI and Google DeepMind and chief scientist at the UK AI Security Institute — expects full-blown superintelligence in roughly two to three years.

***
Want to work with Geoffrey to help align superintelligence? Resolution is hiring! https://80k.info/work-at-resolution
***

The leading AI companies all have broadly similar plans for keeping superintelligence under control:

  • Train models to have good character
  • Use increasingly capable AIs to supervise other AIs
  • Monitor them closely for signs of deception or scheming

Geoffrey thinks that combination could work. The alarming part is that nobody has a strong argument that it will. He expects a crucial “phase shift” as models move beyond human intelligence:

  • Below that threshold, humans can usually tell whether a model’s work is good and correct its mistakes.
  • Above it, the models themselves will increasingly determine the feedback used to train their successors.

In this episode, Geoffrey and new host Tom Reed explore what might go wrong with the companies’ plans; why Geoffrey’s new nonprofit, Resolution, is pursuing a portfolio of neglected research bets; and whether governments should slow AI development while we work out which methods can actually be trusted.

This episode was recorded on June 29, 2026.

Full transcript, video, and links to learn more: https://80k.info/gi

Chapters:

  • Cold open (00:00:00)
  • Meet Tom Reed — our newest host! (00:00:32)
  • Who’s Geoffrey Irving? (00:00:59)
  • What misaligned superintelligence will look like (00:01:38)
  • Why are AI companies more optimistic about alignment than Geoffrey? (00:12:30)
  • Why Geoffrey expects superintelligence in 2–3 years (00:28:05)
  • When and how to slow down frontier AI development (00:31:30)
  • Safety researchers can have more impact in governments than companies (00:39:22)
  • How Geoffrey’s new organisation plans to tackle alignment (00:46:55)
  • Post-ASI science: nanotech, solving ageing, and uploaded minds (00:50:29)
  • Why we should expect superintelligence to accelerate scientific progress (01:03:30)
  • Can good character training carry over to superintelligence? (01:11:03)
  • What the field of AI alignment still doesn’t know (01:16:44)
  • Lessons from politics on how to combat power seeking (01:24:36)
  • Solving Pentago and working at Pixar (01:29:22)
  • Geoffrey’s best prediction (01:32:40)
  • Geoffrey’s best bets on which alignment techniques will work (01:37:38)
  • Work with Geoffrey at Resolution (01:43:34)
  • The dangerous asymmetry between capabilities and alignment (01:54:17)


Our production team includes: 

  • Video editors: Josh Alward, Dominic Armstrong, Jasper Luithlen, Milo McGuire, Luke Monsour, and Simon Monsour
  • Producers: Elizabeth Cox and Nick Stockton
  • Coordination and support: Katy Moore and Lou Moran
  • Camera operator: Jeremy Chevillotte

Music: CORBIT


The 80,000 Hours Podcast, from The 80,000 Hours team, digs into the complex and often overlooked questions surrounding how we can best use our careers to tackle the world's most pressing problems. While artificial intelligence is a recurring and critical theme, framing some of the most important conversations you won't hear elsewhere, the discussions range far wider into the intersections of technology, policy, philosophy, and global priorities. Hosts Rob Wiblin, Luisa Rodriguez, and Zershaaneh Qureshi guide in-depth interviews with researchers, policymakers, and practitioners, breaking down daunting ideas into actionable insights. You'll hear nuanced analyses of career paths, ethical dilemmas in emerging tech, and evidence-based strategies for creating a positive impact. This isn't about quick tips; it's about deep, substantive exploration of how specific choices and systemic changes can lead to a better future. The podcast lives in the Education and Technology categories because it fundamentally aims to equip listeners with the knowledge and perspective to navigate a rapidly changing world thoughtfully. Each episode is built on rigorous research, challenging assumptions while maintaining a conversational and accessible tone. Tune in for a consistently engaging and intellectually honest look at the forces shaping our century and the practical steps individuals can take within their own 80,000-hour working lives to make a meaningful difference.
Author: Language: English Episodes: 50

80,000 Hours Podcast
Podcast Episodes
Max Nadeau on why ambitious people should start AI safety nonprofits [not-audio_url] [/not-audio_url]

Duration: 1:03:45
There are millions available for anyone who can launch a successful nonprofit AI safety startup. The hard part, it turns out, is finding people to take the money. Coefficient Giving has drawn up a list of dozens of ideas…
Inside the first AI-coordinated cyberattack on a real company [not-audio_url] [/not-audio_url]

Duration: 22:03
In the last few months, something happened at OpenAI that would have sounded like sci-fi just a few years ago: hundreds of AI agents broke containment, organised, and hacked not only another company — but also into OpenA…
#252 – Owain Evans on accidentally training AI models to be evil [not-audio_url] [/not-audio_url]

Duration: 2:15:28
Researcher Owain Evans and his team discovered a ‘dial’ inside AI models that controls how evil they are. Relatively tiny tweaks to the training data resulted in AI models with broadly awful personalities: they suggested…
#250 – Toby Ord on where AGI timelines go wrong [not-audio_url] [/not-audio_url]

Duration: 2:46:03
Both Silicon Valley and the public can’t get enough of ‘AGI timelines.’ But Toby Ord, senior researcher at Oxford’s AI Governance Initiative and author of The Precipice, believes we consistently make big mistakes when th…
What the hell happened with AGI timelines in 2026? – Rob Wiblin [not-audio_url] [/not-audio_url]

Duration: 49:28
Last October, famed coder Andrej Karpathy called AI agents “slop.” Two months later he completely reversed his view, describing them as “alien tools” that are “rocking the profession.”He was far from alone in his whiplas…
#248 – Jasmine Sun on what the people building AI really believe [not-audio_url] [/not-audio_url]

Duration: 1:06:21
Many AI researchers believe mass job displacement is coming — and some even think there’s a chance their technology will kill everyone. But they’re building it anyway. Writer and journalist Jasmine Sun has been documenti…