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 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: The best interpretability deep dives combine several kinds of evidence, since no single technique is trustworthy enough on its own.
The best interpretability deep dives combine several kinds of evidence, since no single technique is trustworthy enough on 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 technique is reliable enough alone to justify a 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 of neural networks is a less promising research direction than studying model biology and applying interpretability 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 not shape a model's actions is probably doomed, and weight-based interpretability 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 interpretability probes might get us pretty far without a herculean bottom-up understanding 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 useful for evaluating techniques because they are reproducible in a way human researchers 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 scalable end-to-end interpretability seem reasonable in theory, because the bitter 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 methods are often so painful to train that using them on frontier models is not worth 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 of AI-generated proofs today will probably 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 confused instruction: what deserves trust is the process, not any particular thing 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 11 trials found no evidence of benefit and a small signal of harm for mechanical 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 was unable to reproduce the earlier improvement in insulin sensitivity from 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 authors decide whether and how to address comments without an editor is an unscientific 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 analysis is almost never done, though it may be the most important thing review could 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 large datasets and heavy statistics the price of making any causal claim at all, which has squeezed qualitative economic 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 Saudi Arabian randomized trials on exercise for depression as evidence for 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 regarding exercise for depression have serious issues that make them useless as evidence.
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 diets superior for fat loss are often misled by weight loss that is really body 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 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