Transformers Resist Their Own Architecture

·LessWrong··

This is the first entry in a sequence of posts which compare a mathematical theory of attention against trained transformers.Links: [GitHub repository]: The code for these experiments. [Original paper]: Geshkovski et al., the theory this investigation is built on[YouTube walkthrough]: a video going over the original paperBackgroundThese posts describe experiments building on the paper "A Mathematical Perspective on Transformers," by Geshkovski et al. This background is going to give the definiti...

Read full article →

Related Articles

The classifiers Anthropic puts in front of Fable are too zealous
karrot-kake · Hacker News · 6h ago
EU now one step away from reviving private message scanning rules
ggirelli · Hacker News · 10h ago
John Deere owners will get the right to repair equipment under FTC settlement
djoldman · Hacker News · 3h ago
SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence
mekpro · Hacker News · 10h ago
Decoding the obfuscated bash script on a Uniqlo t-shirt
speerer · Hacker News · 18h ago