#226 – Holden Karnofsky on unexploited opportunities to make AI safer — and all his AGI takes

#226 – Holden Karnofsky on unexploited opportunities to make AI safer — and all his AGI takes

For years, working on AI safety usually meant theorising about the ‘alignment problem’ or trying to convince other people to give a damn. If you could find any way to help, the work was frustrating and low feedback.

According to Anthropic’s Holden Karnofsky, this situation has now reversed completely.

There are now large amounts of useful, concrete, shovel-ready projects with clear goals and deliverables. Holden thinks people haven’t appreciated the scale of the shift, and wants everyone to see the large range of ‘well-scoped object-level work’ they could personally help with, in both technical and non-technical areas.

Video, full transcript, and links to learn more: https://80k.info/hk25

In today’s interview, Holden — previously cofounder and CEO of Open Philanthropy (now Coefficient Giving) — lists 39 projects he’s excited to see happening, including:

  • Training deceptive AI models to study deception and how to detect it
  • Developing classifiers to block jailbreaking
  • Implementing security measures to stop ‘backdoors’ or ‘secret loyalties’ from being added to models in training
  • Developing policies on model welfare, AI-human relationships, and what instructions to give models
  • Training AIs to work as alignment researchers

And that’s all just stuff he’s happened to observe directly, which is probably only a small fraction of the options available.

Holden makes a case that, for many people, working at an AI company like Anthropic will be the best way to steer AGI in a positive direction. He notes there are “ways that you can reduce AI risk that you can only do if you’re a competitive frontier AI company.” At the same time, he believes external groups have their own advantages and can be equally impactful.

Critics worry that Anthropic’s efforts to stay at that frontier encourage competitive racing towards AGI — significantly or entirely offsetting any useful research they do. Holden thinks this seriously misunderstands the strategic situation we’re in — and explains his case in detail with host Rob Wiblin.

Chapters:

  • Cold open (00:00:00)
  • Holden is back! (00:02:26)
  • An AI Chernobyl we never notice (00:02:56)
  • Is rogue AI takeover easy or hard? (00:07:32)
  • The AGI race isn't a coordination failure (00:17:48)
  • What Holden now does at Anthropic (00:28:04)
  • The case for working at Anthropic (00:30:08)
  • Is Anthropic doing enough? (00:40:45)
  • Can we trust Anthropic, or any AI company? (00:43:40)
  • How can Anthropic compete while paying the “safety tax”? (00:49:14)
  • What, if anything, could prompt Anthropic to halt development of AGI? (00:56:11)
  • Holden's retrospective on responsible scaling policies (00:59:01)
  • Overrated work (01:14:27)
  • Concrete shovel-ready projects Holden is excited about (01:16:37)
  • Great things to do in technical AI safety (01:20:48)
  • Great things to do on AI welfare and AI relationships (01:28:18)
  • Great things to do in biosecurity and pandemic preparedness (01:35:11)
  • How to choose where to work (01:35:57)
  • Overrated AI risk: Cyberattacks (01:41:56)
  • Overrated AI risk: Persuasion (01:51:37)
  • Why AI R&D is the main thing to worry about (01:55:36)
  • The case that AI-enabled R&D wouldn't speed things up much (02:07:15)
  • AI-enabled human power grabs (02:11:10)
  • Main benefits of getting AGI right (02:23:07)
  • The world is handling AGI about as badly as possible (02:29:07)
  • Learning from targeting companies for public criticism in farm animal welfare (02:31:39)
  • Will Anthropic actually make any difference? (02:40:51)
  • “Misaligned” vs “misaligned and power-seeking” (02:55:12)
  • Success without dignity: how we could win despite being stupid (03:00:58)
  • Holden sees less dignity but has more hope (03:08:30)
  • Should we expect misaligned power-seeking by default? (03:15:58)
  • Will reinforcement learning make everything worse? (03:23:45)
  • Should we push for marginal improvements or big paradigm shifts? (03:28:58)
  • Should safety-focused people cluster or spread out? (03:31:35)
  • Is Anthropic vocal enough about strong regulation? (03:35:56)
  • Is Holden biased because of his financial stake in Anthropic? (03:39:26)
  • Have we learned clever governance structures don't work? (03:43:51)
  • Is Holden scared of AI bioweapons? (03:46:12)
  • Holden thinks AI companions are bad news (03:49:47)
  • Are AI companies too hawkish on China? (03:56:39)
  • The frontier of infosec: confidentiality vs integrity (04:00:51)
  • How often does AI work backfire? (04:03:38)
  • Is AI clearly more impactful to work in? (04:18:26)
  • What's the role of earning to give? (04:24:54)

This episode was recorded on July 25 and 28, 2025.

Video editing: Simon Monsour, Luke Monsour, Dominic Armstrong, and Milo McGuire
Audio engineering: Milo McGuire, Simon Monsour, and Dominic Armstrong
Music: CORBIT
Coordination, transcriptions, and web: Katy Moore

Jaksot(320)

#145 – Christopher Brown on why slavery abolition wasn't inevitable

#145 – Christopher Brown on why slavery abolition wasn't inevitable

In many ways, humanity seems to have become more humane and inclusive over time. While there’s still a lot of progress to be made, campaigns to give people of different genders, races, sexualities, et...

11 Helmi 20232h 42min

#144 – Athena Aktipis on why cancer is actually one of our universe's most fundamental phenomena

#144 – Athena Aktipis on why cancer is actually one of our universe's most fundamental phenomena

What’s the opposite of cancer?If you answered “cure,” “antidote,” or “antivenom” — you’ve obviously been reading the antonym section at www.merriam-webster.com/thesaurus/cancer.But today’s guest Athen...

26 Tammi 20233h 15min

#79 Classic episode - A.J. Jacobs on radical honesty, following the whole Bible, and reframing global problems as puzzles

#79 Classic episode - A.J. Jacobs on radical honesty, following the whole Bible, and reframing global problems as puzzles

Rebroadcast: this episode was originally released in June 2020. Today’s guest, New York Times bestselling author A.J. Jacobs, always hated Judge Judy. But after he found out that she was his seventh...

16 Tammi 20232h 35min

#81 Classic episode - Ben Garfinkel on scrutinising classic AI risk arguments

#81 Classic episode - Ben Garfinkel on scrutinising classic AI risk arguments

Rebroadcast: this episode was originally released in July 2020. 80,000 Hours, along with many other members of the effective altruism movement, has argued that helping to positively shape the develo...

9 Tammi 20232h 37min

#83 Classic episode - Jennifer Doleac on preventing crime without police and prisons

#83 Classic episode - Jennifer Doleac on preventing crime without police and prisons

Rebroadcast: this episode was originally released in July 2020. Today’s guest, Jennifer Doleac — Associate Professor of Economics at Texas A&M University, and Director of the Justice Tech Lab — is a...

4 Tammi 20232h 17min

#143 – Jeffrey Lewis on the most common misconceptions about nuclear weapons

#143 – Jeffrey Lewis on the most common misconceptions about nuclear weapons

America aims to avoid nuclear war by relying on the principle of 'mutually assured destruction,' right? Wrong. Or at least... not officially.As today's guest — Jeffrey Lewis, founder of Arms Control W...

29 Joulu 20222h 40min

#142 – John McWhorter on key lessons from linguistics, the virtue of creoles, and language extinction

#142 – John McWhorter on key lessons from linguistics, the virtue of creoles, and language extinction

John McWhorter is a linguistics professor at Columbia University specialising in research on creole languages.He's also a content-producing machine, never afraid to give his frank opinion on anything ...

20 Joulu 20221h 47min

#141 – Richard Ngo on large language models, OpenAI, and striving to make the future go well

#141 – Richard Ngo on large language models, OpenAI, and striving to make the future go well

Large language models like GPT-3, and now ChatGPT, are neural networks trained on a large fraction of all text available on the internet to do one thing: predict the next word in a passage. This simpl...

13 Joulu 20222h 44min

Suosittua kategoriassa Koulutus

rss-murhan-anatomia
psykopodiaa-podcast
rss-narsisti
voi-hyvin-meditaatiot-2
rss-vapaudu-voimaasi
rss-liian-kuuma-peruna
aamukahvilla
psykologia
dear-ladies
leveli
adhd-podi
kesken
rss-duodecim-lehti
avara-mieli
rahapuhetta
aloita-meditaatio
ihminen-tavattavissa-tommy-hellsten-instituutti
rss-tietoinen-yhteys-podcast-2
filocast-filosofian-perusteet
rss-luonnollinen-synnytys-podcast