korrents

On the map

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 subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame 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 revealsnew ideas and failure modes, and thatempirical learning is not as widelyunderstood 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 underratinghow much pressure there will be tomove to less safe trainingstrategies once their advantage oversafer 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 triedon low-stakes work first, becausewhen people try something new onsomething 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 oneof the best current safetytechniques, though it will break atsome 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 newidea is worth having, training wouldhave to score the smallness of theconcepts a solution needs, not justwhether 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, safetyand organisations is warrantedbecause 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 asbrute emergent facts is a mysteriousand 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 probablywork are still worth doing, becausea 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 itextrapolates past what we canobserve is methodologicallyrespectable and still a failure ofnerve. 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 itout by trial and error" is never thereal story of an invention: oncloser investigation, identifiablepeople always turn out to beresponsible. 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 almostanything from a schematic are a realpossibility 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 isseeing how an idea evolves overtime. 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 fromsomething 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 isalready known cannot produce genuinesurprises, because a known thingstops 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 existingwork squanders creative effort thatcould 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 industrywould be a good thing, not a badone. 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 givenskill tends to arrive as a suddenphase change rather than as steadyimprovement. 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 suddenlygetting 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 wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2015 to today — full is todaya 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 →