#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)

#112 Classic episode – Carl Shulman on the common-sense case for existential risk work and its practical implications

#112 Classic episode – Carl Shulman on the common-sense case for existential risk work and its practical implications

Preventing the apocalypse may sound like an idiosyncratic activity, and it sometimes is justified on exotic grounds, such as the potential for humanity to become a galaxy-spanning civilisation.But the...

8 Tammi 20243h 50min

#111 Classic episode – Mushtaq Khan on using institutional economics to predict effective government reforms

#111 Classic episode – Mushtaq Khan on using institutional economics to predict effective government reforms

If you’re living in the Niger Delta in Nigeria, your best bet at a high-paying career is probably ‘artisanal refining’ — or, in plain language, stealing oil from pipelines.The resulting oil spills dam...

4 Tammi 20243h 22min

2023 Mega-highlights Extravaganza

2023 Mega-highlights Extravaganza

Happy new year! We've got a different kind of holiday release for you today. Rather than a 'classic episode,' we've put together one of our favourite highlights from each episode of the show that came...

31 Joulu 20231h 53min

#100 Classic episode – Having a successful career with depression, anxiety, and imposter syndrome

#100 Classic episode – Having a successful career with depression, anxiety, and imposter syndrome

Today’s episode is one of the most remarkable and really, unique, pieces of content we’ve ever produced (and I can say that because I had almost nothing to do with making it!).The producer of this sho...

27 Joulu 20232h 51min

#176 – Nathan Labenz on the final push for AGI, understanding OpenAI's leadership drama, and red-teaming frontier models

#176 – Nathan Labenz on the final push for AGI, understanding OpenAI's leadership drama, and red-teaming frontier models

OpenAI says its mission is to build AGI — an AI system that is better than human beings at everything. Should the world trust them to do that safely?That’s the central theme of today’s episode with Na...

22 Joulu 20233h 46min

#175 – Lucia Coulter on preventing lead poisoning for $1.66 per child

#175 – Lucia Coulter on preventing lead poisoning for $1.66 per child

Lead is one of the most poisonous things going. A single sugar sachet of lead, spread over a park the size of an American football field, is enough to give a child that regularly plays there lead pois...

14 Joulu 20232h 14min

#174 – Nita Farahany on the neurotechnology already being used to convict criminals and manipulate workers

#174 – Nita Farahany on the neurotechnology already being used to convict criminals and manipulate workers

"It will change everything: it will change our workplaces, it will change our interactions with the government, it will change our interactions with each other. It will make all of us unwitting neurom...

7 Joulu 20232h

#173 – Jeff Sebo on digital minds, and how to avoid sleepwalking into a major moral catastrophe

#173 – Jeff Sebo on digital minds, and how to avoid sleepwalking into a major moral catastrophe

"We do have a tendency to anthropomorphise nonhumans — which means attributing human characteristics to them, even when they lack those characteristics. But we also have a tendency towards anthropoden...

22 Marras 20232h 38min

Suosittua kategoriassa Koulutus

rss-murhan-anatomia
psykopodiaa-podcast
rss-narsisti
voi-hyvin-meditaatiot-2
aamukahvilla
rss-vapaudu-voimaasi
rss-niinku-asia-on
psykologia
rss-liian-kuuma-peruna
adhd-podi
kesken
dear-ladies
leveli
rss-duodecim-lehti
rss-koira-haudattuna
rss-luonnollinen-synnytys-podcast
rahapuhetta
aloita-meditaatio
ihminen-tavattavissa-tommy-hellsten-instituutti
rss-ai-mita-siskopodcast