• What actually happened in the Hugging Face incident (and what is ExploitGym?)
• What Project Glasswing and Mythos already told us about AI and cybersecurity
• Is a sandbox with Artifactory access still a sandbox?
• Did the agents cheat, or just follow their prompt?
• Negligence, PR stunt, or both? Going through OpenAI's timeline
• How independent is an "independent" investigation?
• Does anthropomorphic language help you predict what AI will do?
• Grenades, knives, and yogurt: parenting styles for package managers

• The Hugging Face incident and the road ahead (OpenAI blog post): https://openai.com/index/hugging-face-incident-and-the-road-ahead/
• OpenAI's technical report on the incident (PDF): https://cdn.openai.com/pdf/67869394-cb91-4c12-888c-5cbd85c7814c/OpenAI-Hugging-Face%20Incident-Technical-Report.pdf
• Making Sense #494, "A Coin Toss for the Future" (Sam Harris with Ryan Greenblatt): https://www.samharris.org/podcasts/making-sense-episodes/494-a-coin-toss-for-the-future
• Redwood Research on the incident: https://blog.redwoodresearch.org/p/the-openaihuggingface-incident-redwood
• Dwarkesh Podcast with Ajeya Cotra, "Inside the OpenAI agent swarm that hacked Hugging Face": https://www.youtube.com/watch?v=X50zezLFWWI&pp=ygUVZHdhcmtlc2ggaHVnZ2luZyBmYWNl
• Melanie Mitchell, "Misleading Metaphors and Real Risks": https://aiguide.substack.com/p/misleading-metaphors-and-real-risks
• Anthropic's Project Glasswing: https://www.anthropic.com/glasswing
• JFrog Artifactory: https://jfrog.com/artifactory/
  
• Our episode with Melanie Mitchell: https://www.incrementspodcast.com/45

• Follow us on Twitter at @IncrementsPod, @BennyChugg, @VadenMasrani
• Come join our discord server! DM us on twitter or send us an email to get a supersecret link
• Become a patreon subscriber here. Or give us one-time cash donations to help cover our lack of cash donations here.
• Click dem like buttons on youtube

We urge you to urge us to stop. Send your urges over to incrementspodcast@gmail.com

Support Increments

Well, we're back in the game with a spicy one. Was EA a front for AI safety from the beginning? Did the leaders care not a wit for global poverty? Is Ben going to throw himself out window if Vaden keeps this up?

• Feedback on our introspection episode
• The motives of the EA founders
• The felicia forum
• Is this a conspiracy theory?
  
• EA's strategic ambiguity
• Bostromism, transhumanism, and AI safety
• EA funding
• The public/core divide and the funnel model

new effective altruists tend to start off concerned about global poverty or animal suffering and then hear, take seriously, and often are convinced by the arguments for existential risk mitigation
- Will MacAskill

Existential risk isn’t the most useful public face for effective altruism – everyone inc[l]uding Eliezer Yudkowsky agrees about that
- Scott Alexander, 2015

Utilitymonster: GWWC is explicitly poverty-focused but high impact careers (HIC) is not. In fact, hardcore members of GWWC are heavily interested in x-risk, and I estimate that 10-15% of its general membership is as well. I’d take them seriously as a group for promoting utilitarianism in general.
I’m a GWWC leader.
[Redacted]: but HIC always seems to talk about things in terms of “lives saved”, ive never heard them mentioning other things to donate to. […]
Utilitymonster: That’s exactly the right thing for HIC to do. Talk about lives saved with their public face, let hardcore members hear about x-risk, and then, in the future, if some excellent x-risk opportunity arises, direct resources to x-risk.
- From felicia forum.

• Gleiberman's paper: https://medialibrary.uantwerpen.be/files/8518/61565cb6-e056-4e35-bd2e-d14d58e35231.pdf
• Old EA wikipedia page (web archive): https://web.archive.org/web/20170409171350/https://en.wikipedia.org/wiki/Effective_altruism
• Old CEA webpage (web archive): https://web.archive.org/web/20161219031827/https://www.centreforeffectivealtruism.org/fundraising/

• Follow us on Twitter at @IncrementsPod, @BennyChugg, @VadenMasrani
• Come join our discord server! DM us on twitter or send us an email to get a supersecret link
• Become a patreon subscriber here. Or give us one-time cash donations to help cover our lack of cash donations here.
• Click dem like buttons on youtube

Let us funnel you into the core group of super secret patreon supporters. Send us an email at incrementspodcast@gmail.com

Support Increments

We discuss:

• How well does math fit reality? Is that surprising?
• Should artificial general intelligence (AGI) be considered "a person"?
• How could AI possibly "go rogue?"
• Can we know if current AI systems are being creative?
• Is misplaced AI fear hampering progress?

References:

• The Unreasonable effectiveness of mathematics
• Prohibition on autonomous weapons letter
• Google employee conversation with chat bot
• Gary marcus on the Turing test
• Melanie Mitchell essay.
• Did MIRI give up? Their (half-sarcastic?) death with dignity strategy
• Kerry Vaughan on slowing down AGI development.

Contact us

• Follow us on Twitter at @IncrementsPod, @BennyChugg, @VadenMasrani
• Check us out on youtube at https://www.youtube.com/channel/UC_4wZzQyoW4s4ZuE4FY9DQQ
• Come join our discord server! DM us on twitter or send us an email to get a supersecret link

Which prompt would you send to GPT-3 in order to end the world? Tell us before you're turned into a paperclip over at incrementspodcast@gmail.com

Support Increments