korrents

On the map

Tap a claim on the ring to put it at the centre.

← A smaller model trained to interpret a larger one would be more…

17 connected korrents · 16 moments from 7 Sept 2008 to 21 Nov 2026. Nearly all of them are about LLMs.

Everything filed under AI alignment AI alignment Everything filed under Anthropic Anthropic Everything filed under simplicity simplicity Everything filed under AI and science AI and science Everything filed under product management product management Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: A smaller model trained to interpret a larger one would be more practical and a better analogy for auditing new frontier models. A smaller model trained to interpret alarger one would be more practical and abetter analogy for auditing new frontiermodels. Last stated 11 months ago 20 Dec 2025 NN Neel Nanda — holds since 2025-12-20 — tap for who they are Same subject: Companies fine-tuning smaller models are not trying to build something as capable as general frontier models. — tap to centre the map on it Companies fine-tuning smaller modelsare not trying to build something ascapable as general frontier models. Last stated 2 weeks ago 5 Nov 2026 AR Aishwarya Naresh Reganti — holds since 2026-11-05 — tap for who they are Same subject: Smaller LLMs are less capable than larger ones, similar to the difference between a dog brain and a human brain. — tap to centre the map on it Smaller LLMs are less capable thanlarger ones, similar to thedifference between a dog brain and ahuman brain. Last stated 2 years ago 25 Feb 2025 PG Philip Guo — holds since 2025-02-25 — tap for who they are Same subject: Without good intuition for models, treat 100k tokens on smaller models and 200k on the frontier ones as the line past which the quality of your results is probably already degrading. — tap to centre the map on it Without good intuition for models,treat 100k tokens on smaller modelsand 200k on the frontier ones as theline past which the quality of yourresults is probably alreadydegrading. Last stated 4 months ago 15 Jul 2026 DH Dex Horthy — holds since 2026-07-15 — tap for who they are Same subject: When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once. — tap to centre the map on it When pre-training data is limited,it is better to train a smallermodel for multiple epochs than totrain a larger model on unique dataonce. Last stated 3 years ago 1 Dec 2023 SR Sebastian Ruder — holds since 2023-12-01 — tap for who they are Same subject: Ambitious interpretability methods are often so painful to train that using them on frontier models is not worth the resources. — tap to centre the map on it Ambitious interpretability methodsare often so painful to train thatusing them on frontier models is notworth the resources. Last stated 11 months ago 20 Dec 2025 NN Neel Nanda — holds since 2025-12-20 — tap for who they are Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does notgive you a smarter model; theintelligence of the model is whatdecides how much of that window itcan actually attend to. Last stated 4 months ago 15 Jul 2026 DH Dex Horthy — holds since 2026-07-15 — 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 thanlanguage models only because thereis less data, not because biology issimpler. Last stated 5 months ago 10 Jun 2026 MZ Mark Zuckerberg — holds since 2026-06-10 — tap for who they are Same subject: The industry was right to focus on model intelligence, but has not yet thought enough about giving a model more context than any person could have so it can advise on big decisions. — tap to centre the map on it The industry was right to focus onmodel intelligence, but has not yetthought enough about giving a modelmore context than any person couldhave so it can advise on bigdecisions. Last stated 3 months ago 23 Aug 2026 SA Sam Altman — holds since 2026-08-23 — 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 oftheir way" is bad management advice;leaders should stay closelyinvolved, building trust and workingthrough hard problems with theirpeople 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 andunacceptable; we would not accept a5% chance of massive fatalities frompaint 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 big misreading of Chinese labs is missing that they have a risk posture and do not want to cause harm. — tap to centre the map on it A big misreading of Chinese labs ismissing that they have a riskposture and do not want to causeharm. Last stated 4 weeks ago 26 Oct 2026 NL Nathan Lambert — holds since 2026-10-26 — tap for who they are Same subject: An open weights model from 2025 with a pentest harness could already escape a sandbox and hack most networks; the surprise says more about the sandbox than the model. — tap to centre the map on it An open weights model from 2025 witha pentest harness could alreadyescape a sandbox and hack mostnetworks; the surprise says moreabout the sandbox than the model. Last stated 4 months ago 22 Jul 2026 TP Thomas Ptacek — holds since 2026-07-22 — tap for who they are Same subject: Because a few specialists already devote themselves to superintelligent AI, the rest of us have correspondingly less reason to spend our own effort on it. — tap to centre the map on it Because a few specialists alreadydevote themselves tosuperintelligent AI, the rest of ushave correspondingly less reason tospend our own effort on it. Last stated 3 years ago 13 Dec 2023 SA Scott Aaronson — holds since 2008-09-07 — tap for who they are SA Scott Aaronson — no longer holds since 2023-12-13 — tap for who they are Same subject: Chain of thought monitoring may soon have little value for AI safety. — tap to centre the map on it Chain of thought monitoring may soonhave little value for AI safety. Last stated yesterday 21 Nov 2026 ZM Zvi Mowshowitz — holds since 2026-11-21 — tap for who they are Same subject: A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. — tap to centre the map on it A feedback loop that reinforces abehavior pulls it toward whateverimproves the loop's own score. Last stated 3 months ago 26 Aug 2026 HK Henrik Karlsson — holds since 2026-08-26 — tap for who they are Same subject: Behaviours like massively deluding humans or trying to seize control of assets could in principle generalise from reward hacking. — tap to centre the map on it Behaviours like massively deludinghumans or trying to seize control ofassets could in principle generalisefrom reward hacking. Last stated a year ago 8 Jul 2025 RG Ryan Greenblatt — holds since 2025-07-08 — tap for who they are Same subject: How aligned current models are depends a lot on things like their degree of reward hacking. — tap to centre the map on it How aligned current models aredepends a lot on things like theirdegree of reward hacking. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — 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 2008 to today (stretched back to the oldest claim here) — full is todaya face: someone who holds the claim — tap it for who they arefaded, dashed ring: they no longer hold it — they changed their mind

At the centre A smaller model trained to interpret a larger one would be more practical and a better analogy for auditing new frontier models. Last stated 20 Dec 2025 · 11 months ago Holds Neel Nanda Read this korrent →