Vika

Deep­Mind al­ign­ment team opinions on AGI ruin arguments

Pos­si­ble take­aways from the coro­n­avirus pan­demic for slow AI takeoff

[Linkpost] Some high-level thoughts on the Deep­Mind al­ign­ment team’s strategy

Strate­gic choice of identity

When dis­cussing AI risks, talk about ca­pa­bil­ities, not intelligence

Refin­ing the Sharp Left Turn threat model, part 1: claims and mechanisms

Op­ti­miza­tion Con­cepts in the Game of Life

Clas­sify­ing speci­fi­ca­tion prob­lems as var­i­ants of Good­hart’s Law

New or­ga­ni­za­tion—Fu­ture of Life In­sti­tute (FLI)

Speci­fi­ca­tion gam­ing: the flip side of AI ingenuity

Power-seek­ing can be prob­a­ble and pre­dic­tive for trained agents

Paradigms of AI al­ign­ment: com­po­nents and enablers

• Vika 22 Jul 2019 19:46 UTC

  53 points

  in reply to: paulfchristiano’s comment on: The AI Timelines Scam

  Definitely agree that the AI community is not biased towards short timelines. Long timelines are the dominant view, while the short timelines view is associated with hype. Many researchers are concerned about the field losing credibility (and funding) if the hype bubble bursts, and this is especially true for those who experienced the AI winters. They see the long timelines view as appropriately skeptical and more scientifically respectable.

  Some examples of statements that AGI is far away from high-profile AI researchers:

  Geoffrey Hinton: https://​​venturebeat.com/​​2018/​​12/​​17/​​geoffrey-hinton-and-demis-hassabis-agi-is-nowhere-close-to-being-a-reality/​​

  Yann LeCun: https://​​www.facebook.com/​​yann.lecun/​​posts/​​10153426023477143 https://​​futurism.com/​​conscious-ai-decades-away https://​​www.facebook.com/​​yann.lecun/​​posts/​​10153368458167143

  Yoshua Bengio: https://​​www.lesswrong.com/​​posts/​​4qPy8jwRxLg9qWLiG/​​yoshua-bengio-on-ai-progress-hype-and-risks

  Rodney Brooks: https://​​rodneybrooks.com/​​the-seven-deadly-sins-of-predicting-the-future-of-ai/​​ https://​​rodneybrooks.com/​​agi-has-been-delayed/​​

Mov­ing on from com­mu­nity living

Speci­fi­ca­tion gam­ing ex­am­ples in AI

New Deep­Mind AI Safety Re­search Blog

Refin­ing the Sharp Left Turn threat model, part 2: ap­ply­ing al­ign­ment techniques

To con­tribute to AI safety, con­sider do­ing AI research

Trade­off be­tween de­sir­able prop­er­ties for baseline choices in im­pact measures

Fu­ture of Life In­sti­tute ex­is­ten­tial risk news site