4h ago

Matthew Barnett posts analysis of Eliezer Yudkowsky's calibration on AI doom predictions centered on a 2016 statement about Turing test timelines before the end of the world

NathanpmYoung replies that the statement offers limited evidence on timelines.

0
Original post

To assess whether Eliezer Yudkowsky is calibrated on AI doom, it seems relevant that in 2016 he said he'd be "pretty shocked" if an AI could pass an unrestricted one-hour Turing test before the end of the world.

12:35 AM · May 23, 2026 View on X

@MatthewJBar @inductionheads im iffy on eliezer bc it's clear many of his priors were formed well before the transformer paradigm. he argues against "alignment by default" but in ways often entirely unrelated to transformers as they are post-2022

Matthew BarnettMatthew Barnett@MatthewJBar

To assess whether Eliezer Yudkowsky is calibrated on AI doom, it seems relevant that in 2016 he said he'd be "pretty shocked" if an AI could pass an unrestricted one-hour Turing test before the end of the world.

7:35 AM · May 23, 2026 · 6.7K Views
11:09 AM · May 23, 2026 · 54 Views

@Jsevillamol This prediction was how he operationalized one of the three central premises of his argument with Bryan Caplan about AI doom. I think it's relevant to his track record, even if not conclusive.

Jaime SevillaJaime Sevilla@Jsevillamol

@MatthewJBar He has previously owned this was a bad prediction, and has also has made some surprising claims that turned out to be correct eg >16% probability of IMO gold by 2025. I love holding people accountable as much as anyone, but let's not bash people based in a single example.

8:21 AM · May 23, 2026 · 968 Views
8:49 AM · May 23, 2026 · 672 Views

@MatthewJBar He has previously owned this was a bad prediction, and has also has made some surprising claims that turned out to be correct eg >16% probability of IMO gold by 2025.

I love holding people accountable as much as anyone, but let's not bash people based in a single example.

Matthew BarnettMatthew Barnett@MatthewJBar

To assess whether Eliezer Yudkowsky is calibrated on AI doom, it seems relevant that in 2016 he said he'd be "pretty shocked" if an AI could pass an unrestricted one-hour Turing test before the end of the world.

7:35 AM · May 23, 2026 · 6.7K Views
8:21 AM · May 23, 2026 · 968 Views

@MatthewJBar Seems like some evidence but not a lot.

Matthew BarnettMatthew Barnett@MatthewJBar

To assess whether Eliezer Yudkowsky is calibrated on AI doom, it seems relevant that in 2016 he said he'd be "pretty shocked" if an AI could pass an unrestricted one-hour Turing test before the end of the world.

7:35 AM · May 23, 2026 · 6.7K Views
7:41 AM · May 23, 2026 · 521 Views
Matthew Barnett posts analysis of Eliezer Yudkowsky's calibration on AI doom predictions centered on a 2016 statement about Turing test timelines before the end of the world · Digg