Tap a claim on the ring to put it at the centre.
← People find pairwise comparisons of answers easier and more consistent to judge than absolute ratings
17 connected korrents · 17 moments from 2 Nov 2016 to 15 Oct 2026.
Everything filed under AI alignment
AI alignment
Everything filed under LLMs
LLMs
Everything filed under behavioural science
behavioural science
Everything filed under metascience
metascience
Everything filed under taste
taste
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: People find pairwise comparisons of answers easier and more consistent to judge than absolute ratings
People find pairwise comparisons of answers easier and more consistent to judge than absolute ratings
Last stated a year ago
22 Jun 2025
EY
Eugene Yan — holds since 2025-06-22 — tap for who they are
Same subject: Humans keep their place in AI as judges rather than authors, because telling which of two answers is better is far easier than writing a good one. — tap to centre the map on it
Humans keep their place in AI as judges rather than authors, because telling which of two answers is better is far easier than writing a good one.
Last stated 2 years ago
3 Feb 2025
NL
Nathan Lambert — holds since 2025-02-03 — tap for who they are
Same subject: Having two different teams investigate the same question and compare conclusions is even better evidence. — tap to centre the map on it
Having two different teams investigate the same question and compare conclusions is even better evidence.
Last stated 11 months ago
27 Dec 2025
NN
Neel Nanda — holds since 2025-12-27 — tap for who they are
Same subject: Running a model five times and keeping the best answer buys a higher benchmark score without buying a better model. — tap to centre the map on it
Running a model five times and keeping the best answer buys a higher benchmark score without buying a better model.
Last stated 5 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: Human preference rankings for RLHF are partly subjective, because raters with limited time cannot always check which answer is correct. — tap to centre the map on it
Human preference rankings for RLHF are partly subjective, because raters with limited time cannot always check which answer is correct.
Last stated 2 months ago
3 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-03 — tap for who they are
Same subject: On everyday high-stakes questions, a model's answer can now be trusted more than an expert human's. — tap to centre the map on it
On everyday high-stakes questions, a model's answer can now be trusted more than an expert human's.
Last stated 5 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: The main advantage of an LLM evaluator over human annotators is scalability, not higher accuracy. — tap to centre the map on it
The main advantage of an LLM evaluator over human annotators is scalability, not higher accuracy.
Last stated 12 months ago
23 Nov 2025
EY
Eugene Yan — holds since 2025-11-23 — tap for who they are
Same subject: Feeling you have a grip on AI by getting your skills in the right order and your review flow right is probably a lot of cope for the fact that the models are still inconsistent. — tap to centre the map on it
Feeling you have a grip on AI by getting your skills in the right order and your review flow right is probably a lot of cope for the fact that the models are still inconsistent.
Last stated 7 months ago
14 Apr 2026
BL
Brian Lovin — holds since 2026-04-14 — tap for who they are
Same subject: Longer answers are often correlated with answer correctness to a certain degree. — tap to centre the map on it
Longer answers are often correlated with answer correctness to a certain degree.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: The people at AI companies are no more likely to raise the alarm about AI dangers than people who were never at AI companies, or people who were previously at AI companies but have since quit. — tap to centre the map on it
The people at AI companies are no more likely to raise the alarm about AI dangers than people who were never at AI companies, or people who were previously at AI companies but have since quit.
Last stated a month ago
15 Oct 2026
SA
Scott Alexander — holds since 2026-10-15 — tap for who they are
Same subject: "Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment. — tap to centre the map on it
"Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment.
Last stated a month ago
9 Oct 2026
CR
Carl Rivera — holds since 2026-10-09 — tap for who they are
Same subject: A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies. — tap to centre the map on it
A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies.
Last stated a year ago
8 Jul 2025
RG
Ryan Greenblatt — holds since 2025-07-08 — tap for who they are
Same subject: A belief system combining cosmic stakes, privileged knowledge, personal vocation and an imperative to act can license extraordinary behavior when it conflicts with ordinary constraints. — tap to centre the map on it
A belief system combining cosmic stakes, privileged knowledge, personal vocation and an imperative to act can license extraordinary behavior when it conflicts with ordinary constraints.
Last stated 2 months ago
17 Sept 2026
VR
Venkatesh Rao — holds since 2026-09-17 — tap for who they are
Same subject: A belief that cannot be acted on, or whose actions carry no personal stakes, is more likely to be held for social reasons than because it is true. — tap to centre the map on it
A belief that cannot be acted on, or whose actions carry no personal stakes, is more likely to be held for social reasons than because it is true.
Last stated 10 years ago
2 Nov 2016
KS
Kevin Simler — holds since 2016-11-02 — tap for who they are
Same subject: A cancellation-reason drop-down measures list order rather than reasons: randomise the options and every one of them gets picked equally. — tap to centre the map on it
A cancellation-reason drop-down measures list order rather than reasons: randomise the options and every one of them gets picked equally.
Last stated 10 months ago
25 Jan 2026
JC
Jason Cohen — holds since 2026-01-25 — tap for who they are
Same subject: A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. — tap to centre the map on it
A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean.
Last stated 12 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A proposal to pace frontier AI development is unrealistic and mainly serves political control of AI. — tap to centre the map on it
A proposal to pace frontier AI development is unrealistic and mainly serves political control of AI.
Last stated 2 months ago
18 Sept 2026
BT
Ben Thompson — holds since 2026-09-18 — tap for who they are
Same subject: Abstract talk of AGI and superintelligence is too abstract; AI has to actually work. — tap to centre the map on it
Abstract talk of AGI and superintelligence is too abstract; AI has to actually work.
Last stated 2 years ago
26 Jan 2025
MA
Marc Andreessen — holds since 2025-01-26 — 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
People find pairwise comparisons of answers easier and more consistent to judge than absolute ratings
Last stated 22 Jun 2025 · a year ago
Holds Eugene Yan
Read this korrent →
Similar wording
Humans keep their place in AI as judges rather than authors, because telling which of two answers is better is far easier than writing a good one.
Last stated 3 Feb 2025 · 2 years ago
Holds Nathan Lambert
Similar wording
Having two different teams investigate the same question and compare conclusions is even better evidence.
Last stated 27 Dec 2025 · 11 months ago
Holds Neel Nanda
Similar wording
Running a model five times and keeping the best answer buys a higher benchmark score without buying a better model.
Last stated 26 Jun 2026 · 5 months ago
Holds Noam Brown
Similar wording
Human preference rankings for RLHF are partly subjective, because raters with limited time cannot always check which answer is correct.
Last stated 3 Oct 2026 · 2 months ago
Holds Sebastian Raschka
Similar wording
On everyday high-stakes questions, a model's answer can now be trusted more than an expert human's.
Last stated 26 Jun 2026 · 5 months ago
Holds Noam Brown
Similar wording
The main advantage of an LLM evaluator over human annotators is scalability, not higher accuracy.
Last stated 23 Nov 2025 · 12 months ago
Holds Eugene Yan
Similar wording
Feeling you have a grip on AI by getting your skills in the right order and your review flow right is probably a lot of cope for the fact that the models are still inconsistent.
Last stated 14 Apr 2026 · 7 months ago
Holds Brian Lovin
Similar wording
Longer answers are often correlated with answer correctness to a certain degree.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Same subject: AI alignment
The people at AI companies are no more likely to raise the alarm about AI dangers than people who were never at AI companies, or people who were previously at AI companies but have since quit.
Last stated 15 Oct 2026 · a month ago
Holds Scott Alexander
Same subject: AI alignment
"Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment.
Last stated 9 Oct 2026 · a month ago
Holds Carl Rivera
Same subject: AI alignment
A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies.
Last stated 8 Jul 2025 · a year ago
Holds Ryan Greenblatt
Same subject: behavioural science
A belief system combining cosmic stakes, privileged knowledge, personal vocation and an imperative to act can license extraordinary behavior when it conflicts with ordinary constraints.
Last stated 17 Sept 2026 · 2 months ago
Holds Venkatesh Rao
Same subject: behavioural science
A belief that cannot be acted on, or whose actions carry no personal stakes, is more likely to be held for social reasons than because it is true.
Last stated 2 Nov 2016 · 10 years ago
Holds Kevin Simler
Same subject: behavioural science
A cancellation-reason drop-down measures list order rather than reasons: randomise the options and every one of them gets picked equally.
Last stated 25 Jan 2026 · 10 months ago
Holds Jason Cohen
Same subject: AGI
A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean.
Last stated 25 Nov 2025 · 12 months ago
Holds Ilya Sutskever
Same subject: AGI
A proposal to pace frontier AI development is unrealistic and mainly serves political control of AI.
Last stated 18 Sept 2026 · 2 months ago
Holds Ben Thompson
Same subject: AGI
Abstract talk of AGI and superintelligence is too abstract; AI has to actually work.
Last stated 26 Jan 2025 · 2 years ago
Holds Marc Andreessen