Tap a claim on the ring to put it at the centre.
← Trying safety methods in practice reveals new ideas and failure modes,…
17 connected korrents · 16 moments from 6 Nov 2015 to 31 Oct 2026.
Everything filed under innovation
innovation
Everything filed under AI alignment
AI alignment
Everything filed under reinforcement learning
reinforcement learning
Everything filed under optimism
optimism
Everything filed under curiosity
curiosity
Everything filed under courage
courage
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: Trying safety methods in practice reveals new ideas and failure modes, and that empirical learning is not as widely understood as it should be.
Trying safety methods in practice reveals new ideas and failure modes, and that empirical learning is not as widely understood as it should be.
Last stated 3 years ago
8 Aug 2023
DA
Dario Amodei — holds since 2023-08-08 — tap for who they are
Same subject: ML researchers may be underrating how much pressure there will be to move to less safe training strategies once their advantage over safer ones becomes apparent. — tap to centre the map on it
ML researchers may be underrating how much pressure there will be to move to less safe training strategies once their advantage over safer ones becomes apparent.
Last stated 4 years ago
12 May 2023
AC
Ajeya Cotra — holds since 2023-05-12 — tap for who they are
Same subject: A new way of working should be tried on low-stakes work first, because when people try something new on something critical and it fails, they never try it again. — tap to centre the map on it
A new way of working should be tried on low-stakes work first, because when people try something new on something critical and it fails, they never try it again.
Last stated 3 years ago
17 Dec 2023
JF
Jason Fried — holds since 2023-12-17 — tap for who they are
Same subject: Reading the chain of thought is one of the best current safety techniques, though it will break at some point and needs close watching. — tap to centre the map on it
Reading the chain of thought is one of the best current safety techniques, though it will break at some point and needs close watching.
Last stated 11 months ago
27 Dec 2025
NN
Neel Nanda — holds since 2025-12-27 — tap for who they are
Same subject: To reward the instinct that a new idea is worth having, training would have to score the smallness of the concepts a solution needs, not just whether it solved the problem. — tap to centre the map on it
To reward the instinct that a new idea is worth having, training would have to score the smallness of the concepts a solution needs, not just whether it solved the problem.
Last stated 5 months ago
30 Jun 2026
GS
Grant Sanderson — holds since 2026-06-30 — tap for who they are
Same subject: Being empiricist about AI, safety and organisations is warranted because one is so often surprised. — tap to centre the map on it
Being empiricist about AI, safety and organisations is warranted because one is so often surprised.
Last stated 3 years ago
8 Aug 2023
DA
Dario Amodei — holds since 2023-08-08 — tap for who they are
Same subject: Treating surprising patterns as brute emergent facts is a mysterious and pessimistic view. — tap to centre the map on it
Treating surprising patterns as brute emergent facts is a mysterious and pessimistic view.
Last stated 3 weeks ago
31 Oct 2026
ML
Michael Levin — holds since 2026-10-31 — tap for who they are
Same subject: Easy experiments that will probably work are still worth doing, because a failure would be informative. — tap to centre the map on it
Easy experiments that will probably work are still worth doing, because a failure would be informative.
Last stated 11 months ago
20 Dec 2025
NN
Neel Nanda — holds since 2025-12-20 — tap for who they are
Same subject: Declining many-worlds because it extrapolates past what we can observe is methodologically respectable and still a failure of nerve. — tap to centre the map on it
Declining many-worlds because it extrapolates past what we can observe is methodologically respectable and still a failure of nerve.
Last stated 3 years ago
22 Apr 2024
SC
Sean Carroll — holds since 2024-04-22 — tap for who they are
Same subject: "Lots of anonymous people worked it out by trial and error" is never the real story of an invention: on closer investigation, identifiable people always turn out to be responsible. — tap to centre the map on it
"Lots of anonymous people worked it out by trial and error" is never the real story of an invention: on closer investigation, identifiable people always turn out to be responsible.
Last stated 3 years ago
25 Oct 2023
AH
Anton Howes — holds since 2023-10-25 — tap for who they are
Same subject: 3D printers that can print almost anything from a schematic are a real possibility within our lifetime. — tap to centre the map on it
3D printers that can print almost anything from a schematic are a real possibility within our lifetime.
Last stated 3 years ago
17 Nov 2023
NE
Nat Eliason — holds since 2023-11-17 — tap for who they are
Same subject: A benefit of reading biographies is seeing how an idea evolves over time. — tap to centre the map on it
A benefit of reading biographies is seeing how an idea evolves over time.
Last stated 7 months ago
12 Apr 2026
DS
David Senra — holds since 2026-04-12 — tap for who they are
Same subject: A person who works from a recipe, even an innovative one, starts from something that already exists. — tap to centre the map on it
A person who works from a recipe, even an innovative one, starts from something that already exists.
Last stated 11 years ago
6 Nov 2015
TU
Tim Urban — holds since 2015-11-06 — tap for who they are
Same subject: A system trained only on what is already known cannot produce genuine surprises, because a known thing stops being a surprise. — tap to centre the map on it
A system trained only on what is already known cannot produce genuine surprises, because a known thing stops being a surprise.
Last stated 2 months ago
18 Sept 2026
CD
Cory Doctorow — holds since 2026-09-18 — tap for who they are
Same subject: A too-faithful remake of an existing work squanders creative effort that could have made something new. — tap to centre the map on it
A too-faithful remake of an existing work squanders creative effort that could have made something new.
Last stated 3 months ago
4 Sept 2026
MW
Matt Webb — holds since 2026-09-04 — tap for who they are
Same subject: A minor bust in the AI industry would be a good thing, not a bad one. — tap to centre the map on it
A minor bust in the AI industry would be a good thing, not a bad one.
Last stated 2 months ago
18 Sept 2026
RS
Robin Sloan — holds since 2026-09-18 — tap for who they are
Same subject: AI capability progress in a given skill tends to arrive as a sudden phase change rather than as steady improvement. — tap to centre the map on it
AI capability progress in a given skill tends to arrive as a sudden phase change rather than as steady improvement.
Last stated 3 months ago
24 Aug 2026
JC
Jack Clark — holds since 2026-08-24 — tap for who they are
Same subject: AI progress comes from a simple, systematic way of improving models, not from researchers suddenly getting smarter. — tap to centre the map on it
AI progress comes from a simple, systematic way of improving models, not from researchers suddenly getting smarter.
Last stated a year ago
16 Jun 2025
JK
Jared Kaplan — holds since 2025-06-16 — 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
Trying safety methods in practice reveals new ideas and failure modes, and that empirical learning is not as widely understood as it should be.
Last stated 8 Aug 2023 · 3 years ago
Holds Dario Amodei
Read this korrent →
Similar wording
ML researchers may be underrating how much pressure there will be to move to less safe training strategies once their advantage over safer ones becomes apparent.
Last stated 12 May 2023 · 4 years ago
Holds Ajeya Cotra
Similar wording
A new way of working should be tried on low-stakes work first, because when people try something new on something critical and it fails, they never try it again.
Last stated 17 Dec 2023 · 3 years ago
Holds Jason Fried
Similar wording
Reading the chain of thought is one of the best current safety techniques, though it will break at some point and needs close watching.
Last stated 27 Dec 2025 · 11 months ago
Holds Neel Nanda
Similar wording
To reward the instinct that a new idea is worth having, training would have to score the smallness of the concepts a solution needs, not just whether it solved the problem.
Last stated 30 Jun 2026 · 5 months ago
Holds Grant Sanderson
Similar wording
Being empiricist about AI, safety and organisations is warranted because one is so often surprised.
Last stated 8 Aug 2023 · 3 years ago
Holds Dario Amodei
Similar wording
Treating surprising patterns as brute emergent facts is a mysterious and pessimistic view.
Last stated 31 Oct 2026 · 3 weeks ago
Holds Michael Levin
Similar wording
Easy experiments that will probably work are still worth doing, because a failure would be informative.
Last stated 20 Dec 2025 · 11 months ago
Holds Neel Nanda
Similar wording
Declining many-worlds because it extrapolates past what we can observe is methodologically respectable and still a failure of nerve.
Last stated 22 Apr 2024 · 3 years ago
Holds Sean Carroll
Same subject: innovation
"Lots of anonymous people worked it out by trial and error" is never the real story of an invention: on closer investigation, identifiable people always turn out to be responsible.
Last stated 25 Oct 2023 · 3 years ago
Holds Anton Howes
Same subject: innovation
3D printers that can print almost anything from a schematic are a real possibility within our lifetime.
Last stated 17 Nov 2023 · 3 years ago
Holds Nat Eliason
Same subject: innovation
A benefit of reading biographies is seeing how an idea evolves over time.
Last stated 12 Apr 2026 · 7 months ago
Holds David Senra
Same subject: creativity
A person who works from a recipe, even an innovative one, starts from something that already exists.
Last stated 6 Nov 2015 · 11 years ago
Holds Tim Urban
Same subject: creativity
A system trained only on what is already known cannot produce genuine surprises, because a known thing stops being a surprise.
Last stated 18 Sept 2026 · 2 months ago
Holds Cory Doctorow
Same subject: creativity
A too-faithful remake of an existing work squanders creative effort that could have made something new.
Last stated 4 Sept 2026 · 3 months ago
Holds Matt Webb
Same subject: LLMs
A minor bust in the AI industry would be a good thing, not a bad one.
Last stated 18 Sept 2026 · 2 months ago
Holds Robin Sloan
Same subject: LLMs
AI capability progress in a given skill tends to arrive as a sudden phase change rather than as steady improvement.
Last stated 24 Aug 2026 · 3 months ago
Holds Jack Clark
Same subject: LLMs
AI progress comes from a simple, systematic way of improving models, not from researchers suddenly getting smarter.
Last stated 16 Jun 2025 · a year ago
Holds Jared Kaplan