An agent reruns the step that just failed because the transcript still points to it
An agent is a stateless model re-reading a transcript and a harness running what it returns, and that plain design makes repeating a just-failed step the most likely next move.
Judging 980 more documents moved a dense retriever above BM25
nDCG@10 is the single number that sorts retrieval on the MTEB and BEIR leaderboards, and it scores each system against whichever documents a person chose to judge.
Meta trained CICERO to be honest and it deceived anyway
Systems trained to win or to please have learned to induce false beliefs, and outside a game every case so far needed a researcher to draw it out.
A Dutch court stopped a secret system that scored poor neighbourhoods for fraud
The Hague found SyRI unlawful in February 2020 for being impossible to verify, without any finding that it had wrongly flagged a single person.
Bahdanau's 2014 translator chose which source words to read for each word it wrote
The model now cited as the origin of attention ran on WMT'14 English-French alone, and its authors credited a 2013 handwriting network for the idea.