Tap a claim on the ring to put it at the centre.
← It may well be possible, and not that hard, to train AI that is very…
17 connected korrents · 17 moments from 15 Jul 2021 to 21 Oct 2026.
Everything filed under AI alignment
AI alignment
Everything filed under AI and science
AI and science
Everything filed under scaling laws
scaling laws
Everything filed under taste
taste
Everything filed under AGI
AGI
Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject
Read this korrent: It may well be possible, and not that hard, to train AI that is very good at science while staying shortsighted and not goal-directed.
It may well be possible, and not that hard, to train AI that is very good at science while staying shortsighted and not goal-directed.
Last stated 4 years ago
12 May 2023
AC
Ajeya Cotra — holds since 2023-05-12 — tap for who they are
Same subject: If AIs can now considerably improve the training of future AIs, this is very unlikely to end well. — tap to centre the map on it
If AIs can now considerably improve the training of future AIs, this is very unlikely to end well.
Last stated a month ago
21 Oct 2026
KP
Kelsey Piper — holds since 2026-10-21 — tap for who they are
Same subject: An end-to-end self-improving AI is probably possible, but it is not even desirable, because it is a hard-takeoff scenario. — tap to centre the map on it
An end-to-end self-improving AI is probably possible, but it is not even desirable, because it is a hard-takeoff scenario.
Last stated a year ago
23 Jul 2025
DH
Demis Hassabis — holds since 2025-07-23 — tap for who they are
Same subject: AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away. — tap to centre the map on it
AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away.
Last stated 3 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: The least verifiable part of AI research is the judgement call about what goes into the one big training run. — tap to centre the map on it
The least verifiable part of AI research is the judgement call about what goes into the one big training run.
Last stated 3 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: AI is only as good as the vision, taste and skill of the person directing it — tap to centre the map on it
AI is only as good as the vision, taste and skill of the person directing it
Last stated 2 years ago
8 Feb 2025
DK
Dan Koe — holds since 2025-02-08 — tap for who they are
Same subject: Nobody knows how to build superintelligent AI or whether it is possible, and if it is, it is many key technical innovations away. — tap to centre the map on it
Nobody knows how to build superintelligent AI or whether it is possible, and if it is, it is many key technical innovations away.
Last stated 2 months ago
10 Sept 2026
CN
Cal Newport — holds since 2026-09-10 — tap for who they are
Same subject: Control techniques can reasonably be expected to make early AIs that are not yet superintelligent helpful for a range of things they are good at. — tap to centre the map on it
Control techniques can reasonably be expected to make early AIs that are not yet superintelligent helpful for a range of things they are good at.
Last stated 9 months ago
17 Feb 2026
AC
Ajeya Cotra — holds since 2026-02-17 — tap for who they are
Same subject: Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down. — tap to centre the map on it
Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down.
Last stated 3 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: A compound's AI origin story is not by itself a reason to expect it to do better in the clinic. — tap to centre the map on it
A compound's AI origin story is not by itself a reason to expect it to do better in the clinic.
Last stated 3 years ago
13 May 2024
DL
Derek Lowe — holds since 2024-05-13 — tap for who they are
Same subject: A computational discovery platform does not make a biotech fast, because the thousand other steps of drug development are still the bottleneck. — tap to centre the map on it
A computational discovery platform does not make a biotech fast, because the thousand other steps of drug development are still the bottleneck.
Last stated 2 years ago
17 Sept 2024
AT
Alex Telford — holds since 2024-09-17 — tap for who they are
Same subject: A computational method can regularly predict protein structures with atomic accuracy even when no similar structure is known. — tap to centre the map on it
A computational method can regularly predict protein structures with atomic accuracy even when no similar structure is known.
Last stated 5 years ago
15 Jul 2021
DH
Demis Hassabis — holds since 2021-07-15 — tap for who they are
Same subject: Accelerating science will be one of the most stunningly positive outcomes of the push to AGI. — tap to centre the map on it
Accelerating science will be one of the most stunningly positive outcomes of the push to AGI.
Last stated 7 months ago
17 Apr 2026
KW
Kevin Weil — holds since 2026-04-17 — tap for who they are
Same subject: An AI that cannot work out new physics has not equalled human intelligence, let alone surpassed it, because humans have worked out new physics. — tap to centre the map on it
An AI that cannot work out new physics has not equalled human intelligence, let alone surpassed it, because humans have worked out new physics.
Last stated 3 years ago
9 Nov 2023
EM
Elon Musk — holds since 2023-11-09 — tap for who they are
Same subject: A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. — tap to centre the map on it
A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated.
Last stated 6 months ago
4 Jun 2026
AI
Alex Imas — holds since 2026-06-04 — tap for who they are
Same subject: Biology models are smaller than language models only because there is less data, not because biology is simpler. — tap to centre the map on it
Biology models are smaller than language models only because there is less data, not because biology is simpler.
Last stated 5 months ago
10 Jun 2026
MZ
Mark Zuckerberg — holds since 2026-06-10 — tap for who they are
Same subject: Digital biology is about to have its ChatGPT moment, on the back of multimodality, long context and synthetic data generation. — tap to centre the map on it
Digital biology is about to have its ChatGPT moment, on the back of multimodality, long context and synthetic data generation.
Last stated 10 months ago
8 Jan 2026
JH
Jensen Huang — holds since 2026-01-08 — tap for who they are
Same subject: In an intellectually dead research field, feeding AI decades of meaningless work only produces more meaningless output. — tap to centre the map on it
In an intellectually dead research field, feeding AI decades of meaningless work only produces more meaningless output.
Last stated 4 months ago
26 Jul 2026
PW
Peter Woit — holds since 2026-07-26 — tap for who they are
same subject or similar wording a cloud: claims about one subject, named for it bar: when it was last stated, on a scale from 2015 to today — full is today a face: someone who holds the claim — tap it for who they are
At the centre
It may well be possible, and not that hard, to train AI that is very good at science while staying shortsighted and not goal-directed.
Last stated 12 May 2023 · 4 years ago
Holds Ajeya Cotra
Read this korrent →
Similar wording
If AIs can now considerably improve the training of future AIs, this is very unlikely to end well.
Last stated 21 Oct 2026 · a month ago
Holds Kelsey Piper
Similar wording
An end-to-end self-improving AI is probably possible, but it is not even desirable, because it is a hard-takeoff scenario.
Last stated 23 Jul 2025 · a year ago
Holds Demis Hassabis
Similar wording
AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away.
Last stated 1 Sept 2026 · 3 months ago
Holds Ajeya Cotra
Similar wording
The least verifiable part of AI research is the judgement call about what goes into the one big training run.
Last stated 11 Aug 2026 · 3 months ago
Holds Ryan Greenblatt
Similar wording
AI is only as good as the vision, taste and skill of the person directing it
Last stated 8 Feb 2025 · 2 years ago
Holds Dan Koe
Similar wording
Nobody knows how to build superintelligent AI or whether it is possible, and if it is, it is many key technical innovations away.
Last stated 10 Sept 2026 · 2 months ago
Holds Cal Newport
Similar wording
Control techniques can reasonably be expected to make early AIs that are not yet superintelligent helpful for a range of things they are good at.
Last stated 17 Feb 2026 · 9 months ago
Holds Ajeya Cotra
Similar wording
Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down.
Last stated 11 Aug 2026 · 3 months ago
Holds Ryan Greenblatt
Same subject: AI and science
A compound's AI origin story is not by itself a reason to expect it to do better in the clinic.
Last stated 13 May 2024 · 3 years ago
Holds Derek Lowe
Same subject: AI and science
A computational discovery platform does not make a biotech fast, because the thousand other steps of drug development are still the bottleneck.
Last stated 17 Sept 2024 · 2 years ago
Holds Alex Telford
Same subject: AI and science
A computational method can regularly predict protein structures with atomic accuracy even when no similar structure is known.
Last stated 15 Jul 2021 · 5 years ago
Holds Demis Hassabis
Same subject: AGI
Accelerating science will be one of the most stunningly positive outcomes of the push to AGI.
Last stated 17 Apr 2026 · 7 months ago
Holds Kevin Weil
Same subject: AGI
An AI that cannot work out new physics has not equalled human intelligence, let alone surpassed it, because humans have worked out new physics.
Last stated 9 Nov 2023 · 3 years ago
Holds Elon Musk
Same subject: AGI
A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated.
Last stated 4 Jun 2026 · 6 months ago
Holds Alex Imas
Same subject: LLMs
Biology models are smaller than language models only because there is less data, not because biology is simpler.
Last stated 10 Jun 2026 · 5 months ago
Holds Mark Zuckerberg
Same subject: LLMs
Digital biology is about to have its ChatGPT moment, on the back of multimodality, long context and synthetic data generation.
Last stated 8 Jan 2026 · 10 months ago
Holds Jensen Huang
Same subject: LLMs
In an intellectually dead research field, feeding AI decades of meaningless work only produces more meaningless output.
Last stated 26 Jul 2026 · 4 months ago
Holds Peter Woit