The authors repeated 50 published findings on 20 models released between July 2024 and September 2026 from eight developers, then fitted how each effect changed with release date. By September 2026, 44% of the claims had expired, which…
In the News: November 3, 2026 (Extra 2)
A Stanford re-test finds 44% of 50 cited LLM findings expired on current models, while judges favoring their own answers did not fade.
Extra edition
Machine-readable
Download Markdown
Story
A Stanford re-test finds 44% of 50 cited LLM findings have expired, while self-preferring judges persist
Read story →
Revolut moves to self-hosted GLM
177 points and 153 comments at about 16:00 EST, posted at 09:53 EST. The thread links an X post summarizing a conference talk by a speaker it names as leading AI operations at Revolut. The talk itself was not read for this line, so it reports a discussion, not a finding, and the cost and productivity figures in the post are not repeated here.