korrents

On the map

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

← The best interpretability deep dives combine several kinds of…

17 connected korrents · 13 moments from 13 Feb 2023 to 12 Nov 2026.

Everything filed under metascience metascience Everything filed under LLMs LLMs Everything filed under AI alignment AI alignment Everything filed under neural networks neural networks Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: The best interpretability deep dives combine several kinds of evidence, since no single technique is trustworthy enough on its own. The best interpretability deep divescombine several kinds of evidence, sinceno single technique is trustworthy enoughon its own. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — tap for who they are Same subject: No single interpretability technique is reliable enough alone to justify a verdict like a model being unsafe; decorrelated techniques are needed. — tap to centre the map on it No single interpretability techniqueis reliable enough alone to justifya verdict like a model being unsafe;decorrelated techniques are needed. Last stated 11 months ago 20 Dec 2025 NN Neel Nanda — holds since 2025-12-20 — tap for who they are Same subject: Complete reverse-engineering of neural networks is a less promising research direction than studying model biology and applying interpretability usefully — tap to centre the map on it Complete reverse-engineering ofneural networks is a less promisingresearch direction than studyingmodel biology and applyinginterpretability usefully Last stated a year ago 19 Aug 2025 NN Neel Nanda — holds since 2025-08-19 — tap for who they are Same subject: Auditing properties that do not shape a model's actions is probably doomed, and weight-based interpretability has not gone well. — tap to centre the map on it Auditing properties that do notshape a model's actions is probablydoomed, and weight-basedinterpretability has not gone well. Last stated 11 months ago 20 Dec 2025 NN Neel Nanda — holds since 2025-12-20 — tap for who they are Same subject: Crude, high-level interpretability probes might get us pretty far without a herculean bottom-up understanding of models. — tap to centre the map on it Crude, high-level interpretabilityprobes might get us pretty farwithout a herculean bottom-upunderstanding of models. Last stated 4 years ago 12 May 2023 AC Ajeya Cotra — holds since 2023-05-12 — tap for who they are Same subject: Interpretability agents are useful for evaluating techniques because they are reproducible in a way human researchers are not. — tap to centre the map on it Interpretability agents are usefulfor evaluating techniques becausethey are reproducible in a way humanresearchers are not. Last stated 11 months ago 20 Dec 2025 NN Neel Nanda — holds since 2025-12-20 — tap for who they are Same subject: The arguments for scalable end-to-end interpretability seem reasonable in theory, because the bitter lesson is powerful. — tap to centre the map on it The arguments for scalableend-to-end interpretability seemreasonable in theory, because thebitter lesson is powerful. Last stated 11 months ago 20 Dec 2025 NN Neel Nanda — holds since 2025-12-20 — 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: The poor explanatory quality of AI-generated proofs today will probably improve. — tap to centre the map on it The poor explanatory quality ofAI-generated proofs today willprobably improve. Last stated a month ago 16 Oct 2026 GS Grant Sanderson — holds since 2026-10-16 — tap for who they are Same subject: “Trust science” is a confused instruction: what deserves trust is the process, not any particular thing it has concluded so far. — tap to centre the map on it “Trust science” is a confusedinstruction: what deserves trust isthe process, not any particularthing it has concluded so far. Last stated 3 years ago 16 Aug 2023 JC Jason Crawford — holds since 2023-08-16 — tap for who they are Same subject: A Cochrane Systematic review of 11 trials found no evidence of benefit and a small signal of harm for mechanical CPR devices. — tap to centre the map on it A Cochrane Systematic review of 11trials found no evidence of benefitand a small signal of harm formechanical CPR devices. Last stated 3 months ago 17 Aug 2026 JM John Mandrola — holds since 2026-08-17 — tap for who they are Same subject: A follow-up clinical trial was unable to reproduce the earlier improvement in insulin sensitivity from blueberries. — tap to centre the map on it A follow-up clinical trial wasunable to reproduce the earlierimprovement in insulin sensitivityfrom blueberries. Last stated 2 months ago 6 Oct 2026 RP Rhonda Patrick — holds since 2026-10-06 — tap for who they are Same subject: A review process where authors decide whether and how to address comments without an editor is an unscientific sham. — tap to centre the map on it A review process where authorsdecide whether and how to addresscomments without an editor is anunscientific sham. Last stated a week ago 12 Nov 2026 AD Andrew Dessler — holds since 2026-11-12 — tap for who they are Same subject: Checking a paper's data and analysis is almost never done, though it may be the most important thing review could do. — tap to centre the map on it Checking a paper's data and analysisis almost never done, though it maybe the most important thing reviewcould do. Last stated 4 years ago 13 Feb 2023 AM Adam Mastroianni — holds since 2023-02-13 — tap for who they are Same subject: Economics journals have made large datasets and heavy statistics the price of making any causal claim at all, which has squeezed qualitative economic history out of the field. — tap to centre the map on it Economics journals have made largedatasets and heavy statistics theprice of making any causal claim atall, which has squeezed qualitativeeconomic history out of the field. Last stated a year ago 13 Oct 2025 AH Anton Howes — holds since 2025-10-13 — tap for who they are Same subject: No one should use the specific Saudi Arabian randomized trials on exercise for depression as evidence for medical treatments. — tap to centre the map on it No one should use the specific SaudiArabian randomized trials onexercise for depression as evidencefor medical treatments. Last stated 2 months ago 15 Sept 2026 GM Gideon Meyerowitz-Katz — holds since 2026-09-15 — tap for who they are Same subject: Several impactful studies regarding exercise for depression have serious issues that make them useless as evidence. — tap to centre the map on it Several impactful studies regardingexercise for depression have seriousissues that make them useless asevidence. Last stated 2 months ago 15 Sept 2026 GM Gideon Meyerowitz-Katz — holds since 2026-09-15 — tap for who they are Same subject: Studies that call ketogenic diets superior for fat loss are often misled by weight loss that is really body water. — tap to centre the map on it Studies that call ketogenic dietssuperior for fat loss are oftenmisled by weight loss that is reallybody water. Last stated a month ago 21 Oct 2026 LN Layne Norton — holds since 2026-10-21 — 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 The best interpretability deep dives combine several kinds of evidence, since no single technique is trustworthy enough on its own. Last stated 27 Dec 2025 · 11 months ago Holds Neel Nanda Read this korrent →