“The ML drug discovery startup trying really, really hard to not cheat” by Abhishaike Mahajan

episode

LessWrong (30+ Karma) not yet transcribed

▲ 0

Transcript

This episode hasn't been transcribed yet Upvotes decide what gets transcribed next — 0 so far. Sign in to upvote

More from LessWrong (30+ Karma)

“Claude Opus 4.5 Achieves 50%-Time Horizon Of Around 4 hrs 49 Mins” by Michaël Trazzi 3 min · 20 Dec 2025

All episodes from LessWrong (30+ Karma) →

Report any issue

Source

Recorded24 Dec 2025

Publisherfeeds.type3.audio ↗

Handlerec:14881269

Show notes

Introduction What I will describe below is a rough first approximation of what it is like to work in the field of machine-learning-assisted small-molecule design. Imagine that you are tasked with solving the following machine-learning problem: There are 116 billion balls of varying colors, textures, shapes, and sizes in front of you. Your job is to predict which balls will stick to a velcro strip. To help start you off, you’re given a training set of 10 million balls that have already been tested; which ones stuck and which ones didn’t. Your job is to predict the rest. You give it your best shot, train a very large transformer on 80% of the (X, Y) labels, and discover that you’ve achieved an AUC of .76 on a held out 20% set of validation balls. Not too shabby, especially given that you only had access to .008% of the total space of all balls. But, since you’re a good hypothetical scientist, you look more into what balls you did well on, and which balls you did not do well on. You do not immediately find any surprises; there is mostly uniform error across color, textures, shapes, and sizes, which are [...] ---Outline:(00:22) Introduction(05:34) Some of Leash's research(05:38) The BELKA result(16:18) The Hermes result(23:20) The train/test split result(29:39) The 'Clever Hans' result(37:08) Conclusion --- First published: December 23rd, 2025 Source: https://www.lesswrong.com/posts/vdBkJLNzgDSeXDyq8/the-ml-drug-discovery-startup-trying-really-really-hard-to --- Narrated by TYPE III AUDIO. ---Images from the article:Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.