AI takeoff

TagLast edit: 16 Mar 2022 17:42 UTC by Pablo

AI takeoff is a hypothesized period of transition during which an advanced artificial intelligence acquires superhuman intellectual capacity.

What a compute-centric framework says about AI takeoff speeds

Tom_Davidson23 Jan 2023 4:09 UTC

189 points

7 comments16 min readEA link

(www.lesswrong.com)

Thoughts on Toby Ords AI Scaling Series

Srdjan Miletic4 Feb 2026 0:46 UTC

51 points

3 comments4 min readEA link

(www.dissent.blog)

Exponential AI takeoff is a myth

Christoph Hartmann 🔸31 May 2023 11:47 UTC

48 points

11 comments9 min readEA link

Evolution provides no evidence for the sharp left turn

Quintin Pope11 Apr 2023 18:48 UTC

43 points

2 comments15 min readEA link

The Goodhart Singularity

Vasco Grilo🔸18 May 2026 16:29 UTC

66 points

5 comments12 min readEA link

(meagreprotestanthistory.substack.com)

A compute-based framework for thinking about the future of AI

Matthew_Barnett31 May 2023 22:00 UTC

96 points

36 comments19 min readEA link

Two contrasting models of “intelligence” and future growth

Magnus Vinding24 Nov 2022 11:54 UTC

74 points

32 comments22 min readEA link

AGI Takeoff dynamics—Intelligence vs Quantity explosion

EdoArad🔸26 Jul 2023 9:20 UTC

14 points

0 comments2 min readEA link

(github.com)

Continuous doesn’t mean slow

Tom_Davidson10 May 2023 12:17 UTC

64 points

1 comment4 min readEA link

Announcing Epoch: A research organization investigating the road to Transformative AI

Jaime Sevilla27 Jun 2022 13:39 UTC

183 points

11 comments2 min readEA link

(epochai.org)

“Heretical Thoughts on AI” by Eli Dourado

𝕮𝖎𝖓𝖊𝖗𝖆19 Jan 2023 16:11 UTC

142 points

15 comments3 min readEA link

(www.elidourado.com)

Cyborg Periods: There will be multiple AI transitions

Jan_Kulveit22 Feb 2023 16:09 UTC

68 points

1 comment6 min readEA link

[meta on] The simplest case for AI catastrophe

Linch6 Feb 2026 0:19 UTC

23 points

2 comments1 min readEA link

(linch.substack.com)

Summary: Against the singularity hypothesis

Global Priorities Institute22 May 2024 11:05 UTC

47 points

16 comments4 min readEA link

(globalprioritiesinstitute.org)

The simple case for AI catastrophe, in four steps

Linch6 Feb 2026 17:38 UTC

17 points

2 comments10 min readEA link

(linch.substack.com)

There May Be Powerful AI Safety Levers in the Energy Sector

Benevolent_Rain28 May 2026 13:51 UTC

12 points

1 comment27 min readEA link

Vignettes Workshop (AI Impacts)

kokotajlod15 Jun 2021 11:02 UTC

43 points

5 comments1 min readEA link

Does AI Progress Have a Speed Limit?

Vasco Grilo🔸13 Jun 2025 16:22 UTC

21 points

1 comment19 min readEA link

(asteriskmag.com)

Continuity Assumptions

Jan_Kulveit13 Jun 2022 21:36 UTC

44 points

4 comments4 min readEA link

(www.alignmentforum.org)

How quickly AI could transform the world (Tom Davidson on The 80,000 Hours Podcast)

80000_Hours8 May 2023 13:23 UTC

82 points

3 comments17 min readEA link

Future Matters #8: Bing Chat, AI labs on safety, and pausing Future Matters

Pablo21 Mar 2023 14:50 UTC

81 points

5 comments24 min readEA link

How we could stumble into AI catastrophe

Holden Karnofsky16 Jan 2023 14:52 UTC

83 points

0 comments31 min readEA link

(www.cold-takes.com)

AI impacts and Paul Christiano on takeoff speeds

Crosspost2 Mar 2018 11:16 UTC

4 points

0 comments1 min readEA link

Shulman and Yudkowsky on AI progress

CarlShulman4 Dec 2021 11:37 UTC

46 points

0 comments20 min readEA link

“Slower tech development” can be about ordering, gradualness, or distance from now

MichaelA🔸14 Nov 2021 20:58 UTC

47 points

3 comments4 min readEA link

Success without dignity: a nearcasting story of avoiding catastrophe by luck

Holden Karnofsky15 Mar 2023 20:17 UTC

114 points

3 comments15 min readEA link

Where’s my ten minute AGI?

Vasco Grilo🔸19 May 2025 17:45 UTC

47 points

6 comments7 min readEA link

(epoch.ai)

Knowledge, Reasoning, and Superintelligence

Owen Cotton-Barratt26 Mar 2025 23:28 UTC

21 points

3 comments7 min readEA link

(strangecities.substack.com)

What is autonomy, and how does it lead to greater risk from AI?

Davidmanheim1 Aug 2023 8:06 UTC

10 points

0 comments6 min readEA link

(www.lesswrong.com)

AI 2027: What Superintelligence Looks Like (Linkpost)

Manuel Allgaier11 Apr 2025 10:31 UTC

51 points

3 comments42 min readEA link

(ai-2027.com)

Why I think AI take-off is relatively slow

Vasco Grilo🔸17 Aug 2025 9:11 UTC

29 points

0 comments3 min readEA link

(marginalrevolution.com)

Takeoff speeds presentation at Anthropic

Tom_Davidson4 Jun 2024 22:46 UTC

29 points

3 comments25 min readEA link

Yudkowsky and Christiano discuss “Takeoff Speeds”

EliezerYudkowsky22 Nov 2021 19:42 UTC

42 points

0 comments60 min readEA link

AI Could Defeat All Of Us Combined

Holden Karnofsky10 Jun 2022 23:25 UTC

144 points

14 comments17 min readEA link

Distinguishing ways AI can be “concentrated”

Matthew_Barnett21 Oct 2024 22:14 UTC

30 points

1 comment4 min readEA link

AI safety tax dynamics

Owen Cotton-Barratt23 Oct 2024 12:21 UTC

22 points

9 comments6 min readEA link

(strangecities.substack.com)

What role should evolutionary analogies play in understanding AI takeoff speeds?

anson11 Dec 2021 1:16 UTC

12 points

0 comments42 min readEA link

We should think about the pivotal act again. Here’s a better version of it.

Otto28 Aug 2025 9:29 UTC

3 points

1 comment3 min readEA link

What are the differences between a singularity, an intelligence explosion, and a hard takeoff?

Vishakha Agrawal3 Apr 2025 10:34 UTC

6 points

0 comments2 min readEA link

(aisafety.info)

Orienting to 3 year AGI timelines

Nikola22 Dec 2024 23:07 UTC

122 points

18 comments8 min readEA link

We don’t understand what happened with culture enough

Jan_Kulveit9 Oct 2023 14:56 UTC

29 points

2 comments6 min readEA link

Is research into recursive self-improvement becoming a safety hazard?

Mordechai Rorvig30 Jan 2026 18:15 UTC

1 point

0 comments2 min readEA link

(www.foommagazine.org)

Are Short AI Timelines Really Higher-Leverage?

Forethought23 Jan 2026 7:26 UTC

36 points

1 comment15 min readEA link

(www.forethought.org)

The Inequality We Might Want: Merit-Based Redistribution for the AI Transition

Andrei Navrotskii27 Nov 2025 10:51 UTC

7 points

1 comment12 min readEA link

Distinguish between inference scaling and “larger tasks use more compute”

Ryan Greenblatt11 Feb 2026 18:37 UTC

29 points

3 comments2 min readEA link

Will we get automated alignment research before an AI Takeoff?

Jan Wehner🔸22 Jan 2026 17:57 UTC

51 points

13 comments11 min readEA link

AI acceleration from a safety perspective: Trade-offs and considerations

mariushobbhahn19 Jan 2022 9:44 UTC

12 points

1 comment7 min readEA link

A (Slightly) Mechanistic Theory for Exponentially Increasing AI Time Horizons?

Oliver Sourbut25 May 2026 1:52 UTC

13 points

1 comment8 min readEA link

(www.oliversourbut.net)

Which questions can’t we punt?

Lizka23 Feb 2026 19:17 UTC

82 points

7 comments15 min readEA link

Rohin Shah on what it’s really like to run AGI safety at Google DeepMind (and where I disagree with ‘doomers’)

80000_Hours2 Jun 2026 18:10 UTC

14 points

0 comments15 min readEA link

Agent Economics: a BOTEC on feasibility

Margot Stakenborg6 Feb 2026 11:59 UTC

40 points

1 comment6 min readEA link

A Reply to MacAskill on “If Anyone Builds It, Everyone Dies”

RobBensinger27 Sep 2025 23:03 UTC

9 points

7 comments17 min readEA link

Exaggerating the risks (Part 20: AI 2027 timelines forecast, benchmarks and gaps) | Reflective Altruism

Unofficial Reflective Altruism Cross-Poster1 Jan 2026 23:32 UTC

14 points

6 comments18 min readEA link

(reflectivealtruism.com)

What would it take for AI to disempower us? Ryan Greenblatt on takeoff dynamics, rogue deployments, and alignment risks

80000_Hours8 Jul 2025 18:10 UTC

8 points

0 comments33 min readEA link

New video from Palisade Research: No One Understands Why AI Works

peterbarnett20 Feb 2026 20:28 UTC

10 points

0 comments1 min readEA link

(www.youtube.com)

AI & wisdom 2: growth and amortised optimisation

L Rudolf L29 Oct 2024 13:37 UTC

20 points

0 comments7 min readEA link

(rudolf.website)

A personal letter on transformative AI

George Rosenfeld25 May 2026 17:48 UTC

95 points

3 comments1 min readEA link

(multipliercg.substack.com)

Geoffrey Hinton on the Past, Present, and Future of AI

Stephen McAleese12 Oct 2024 16:41 UTC

5 points

1 comment18 min readEA link

A Critique of AI Takeover Scenarios

James Fodor31 Aug 2022 13:49 UTC

53 points

4 comments12 min readEA link

Hardening against AI takeover is difficult, but we should try

Otto5 Nov 2025 16:29 UTC

8 points

1 comment5 min readEA link

(www.existentialriskobservatory.org)

Summary of AGI Polls—and Questions

Denkenberger🔸7 Jan 2026 0:52 UTC

13 points

0 comments3 min readEA link

Epoch is hiring a Research Data Analyst

merilalama22 Nov 2022 17:34 UTC

21 points

0 comments4 min readEA link

(careers.rethinkpriorities.org)

Fundamental Risk

Ihor Ivliev26 Jun 2025 0:25 UTC

−5 points

0 comments1 min readEA link

Between Science Fiction and Emerging Reality: Are We Ready for Digital Persons?

Alex (Αλέξανδρος)13 Mar 2025 16:09 UTC

5 points

1 comment5 min readEA link

Yudkowsky and Soares’ Book Is Empty

Oscar Davies5 Dec 2025 22:06 UTC

1 point

8 comments7 min readEA link

Unveiling the American Public Opinion on AI Moratorium and Government Intervention: The Impact of Media Exposure

Otto8 May 2023 10:49 UTC

28 points

5 comments6 min readEA link

On Economics of A(S)I Agents

Margot Stakenborg7 Feb 2026 18:59 UTC

47 points

0 comments47 min readEA link

We Need Breadth-First AI Safety Plans

MichaelDickens1 Jun 2026 17:36 UTC

11 points

1 comment4 min readEA link

MIRI Conversations: Technology Forecasting & Gradualism (Distillation)

Callum McDougall13 Jul 2022 10:45 UTC

27 points

9 comments19 min readEA link

Incumbents Might Be Replaced During AI Takeoff, Including in Animal Agriculture

Hazo9 Jun 2026 18:59 UTC

35 points

1 comment6 min readEA link

Carving up the future

Niki Dupuis11 Mar 2026 22:33 UTC

27 points

2 comments4 min readEA link

(lovedoesnotscale.substack.com)

Sutskever Refuses to Answer the Q: How Will AGI Be Built? He Has No Answer

Oscar Davies4 Dec 2025 19:13 UTC

9 points

3 comments4 min readEA link

Self-sufficient AI

Ajeya6 Jan 2026 15:13 UTC

44 points

1 comment4 min readEA link

An interactive toy model for exploring AI’s effect on the labour market

Charles Dillon 🔸7 Jan 2026 12:57 UTC

10 points

0 comments7 min readEA link

An Analysis of Systemic Risk and Architectural Requirements for the Containment of Recursively Self-Improving AI

Ihor Ivliev17 Jun 2025 0:16 UTC

2 points

5 comments4 min readEA link

AI, Animals & Digital Minds NYC 2025: Retrospective

Jonah Woodward31 Oct 2025 3:09 UTC

43 points

5 comments6 min readEA link

Preparing for a Warning Shot

Noah Birnbaum5 Feb 2026 15:12 UTC

25 points

0 comments4 min readEA link

But AI is Different...

AgentMa🔸31 May 2026 2:39 UTC

11 points

1 comment3 min readEA link

(aipolicytakes.substack.com)

[Linkpost] On the Origins of Algorithmic Progress in AI

alexfogelson9 Jan 2026 19:46 UTC

25 points

0 comments1 min readEA link

(open.substack.com)

Idea: the intelligence explosion convention

Forethought5 Feb 2026 9:07 UTC

26 points

1 comment9 min readEA link

(www.forethought.org)

An Ontology of Representations: Limits of Universality

Margot Stakenborg12 Feb 2026 21:53 UTC

4 points

1 comment39 min readEA link

(www.lesswrong.com)

The V&V method—A step towards safer AGI

Yoav Hollander24 Jun 2025 15:57 UTC

1 point

0 comments1 min readEA link

(blog.foretellix.com)

Speculating on Secret Intelligence Explosions

calebp5 Jun 2025 13:55 UTC

21 points

5 comments8 min readEA link

Six milestones for AI automation

Ajeya3 Apr 2026 14:10 UTC

34 points

0 comments4 min readEA link

Benjamin Todd on why we’re updating our career advice for the strangest time in history

80000_Hours29 May 2026 13:50 UTC

8 points

0 comments12 min readEA link

(80000hours.org)

I underestimated AI capabilities (again)

Ajeya5 Mar 2026 19:15 UTC

64 points

4 comments5 min readEA link

Daniel Kokotajlo on AI 2027: Race Dynamics, Robot Economies, and the Narrow Path to a Good Future

80000_Hours21 Oct 2025 19:51 UTC

7 points

1 comment18 min readEA link

The Khayali Protocol

khayali2 Jun 2025 14:40 UTC

−8 points

0 comments3 min readEA link

Power laws in Speedrunning and Machine Learning

Jaime Sevilla24 Apr 2023 10:06 UTC

48 points

0 comments1 min readEA link

(arxiv.org)

The Singularity is a Veil of Ignorance

Ben Morrell30 May 2026 17:09 UTC

41 points

4 comments8 min readEA link

(theforwardpass.substack.com)

Addressing Objections to the Intelligence Explosion

Bentham's Bulldog30 Jan 2026 18:11 UTC

4 points

10 comments16 min readEA link

Evidence that Recent AI Gains are Mostly from Inference-Scaling

Toby_Ord2 Feb 2026 8:45 UTC

23 points

2 comments5 min readEA link

(www.tobyord.com)

Tetherware #2: What every human should know about our most likely AI future

Jáchym Fibír28 Feb 2025 11:25 UTC

3 points

0 comments11 min readEA link

(tetherware.substack.com)

Is anyone else also getting more worried about hard takeoff AGI scenarios?

JonCefalu9 Jan 2023 6:04 UTC

19 points

11 comments3 min readEA link

The case for multi-decade timelines [Linkpost]

Sharmake27 Apr 2025 20:34 UTC

50 points

9 comments11 min readEA link

When will AI automate all mental work, and how fast?

A.G.G. Liu31 May 2025 16:18 UTC

10 points

0 comments7 min readEA link

(youtu.be)

Ajeya Cotra on whether it’s crazy that every AI company’s safety plan is ‘use AI to make AI safe’

80000_Hours17 Feb 2026 19:09 UTC

35 points

1 comment15 min readEA link

Without Alignment, Is Longtermism (and Thus, EA) Just Noise?

Krimsey17 Oct 2025 20:05 UTC

3 points

1 comment3 min readEA link

#217 – The most important graph in AI right now (Beth Barnes on The 80,000 Hours Podcast)

80000_Hours2 Jun 2025 16:52 UTC

16 points

1 comment26 min readEA link

Inference Scaling Reshapes AI Governance

Toby_Ord2 Feb 2026 8:44 UTC

39 points

2 comments16 min readEA link

(www.tobyord.com)

Better than logarithmic returns to reasoning?

Oliver Sourbut30 Jul 2025 0:50 UTC

6 points

1 comment3 min readEA link

(www.oliversourbut.net)

Cooperation Is All You Need

Patrick Grünig2 Mar 2026 14:58 UTC

3 points

2 comments22 min readEA link

Un-unpluggability—can’t we just unplug it?

Oliver Sourbut15 May 2023 13:23 UTC

15 points

0 comments11 min readEA link

(www.oliversourbut.net)

The Industrial Explosion

rosehadshar26 Jun 2025 14:41 UTC

39 points

1 comment15 min readEA link

(www.forethought.org)

Could a company overpower nations?

Ajeya5 Jun 2026 15:02 UTC

22 points

0 comments2 min readEA link

(www.planned-obsolescence.org)

Will the Need to Retrain AI Models from Scratch Block a Software Intelligence Explosion?

Forethought28 Mar 2025 13:43 UTC

12 points

0 comments3 min readEA link

(www.forethought.org)

Are We Ready for Digital Persons?

Alex (Αλέξανδρος)3 Jun 2025 9:38 UTC

3 points

0 comments1 min readEA link

(www.linkedin.com)

Metaculus Predicts Weak AGI in 2 Years and AGI in 10

Chris Leong24 Mar 2023 19:43 UTC

27 points

12 comments1 min readEA link

Why I think it’s important to work on AI forecasting

Matthew_Barnett27 Feb 2023 21:24 UTC

179 points

10 comments10 min readEA link

How quick and big would a software intelligence explosion be?

Tom_Davidson5 Aug 2025 15:47 UTC

12 points

2 comments34 min readEA link

Asterisk Magazine Issue 03: AI

alejandro24 Jul 2023 15:53 UTC

34 points

3 comments1 min readEA link

(asteriskmag.com)

Takeoff speeds rule everything around me

Ajeya12 Feb 2026 15:19 UTC

48 points

1 comment3 min readEA link

AGI Battle Royale: Why “slow takeover” scenarios devolve into a chaotic multi-AGI fight to the death

titotal22 Sep 2022 15:00 UTC

55 points

12 comments15 min readEA link

By Strong Default, ASI Will End Liberal Democracy

MichaelDickens6 Apr 2026 23:43 UTC

42 points

1 comment3 min readEA link

AI Risk: Can We Thread the Needle? [Recorded Talk from EA Summit Vancouver ’25]

Evan R. Murphy2 Oct 2025 19:05 UTC

8 points

0 comments2 min readEA link

No comments.

AI takeoff

Further reading

Related entries