NYU Center for Data Science

nyudatascience.bsky.social

05 October 2026 04:15

Can LLMs introspect? Anthropic said yes. However, CDS PhD student Shashwat Singh, CDS Associate Professor Tal Linzen (@tallinzen.bsky.social) & CDS Faculty Fellow Shauli Ravfogel (@shauli.bsky.social) found the evidence falls short. nyudatascience.medium.com/cds-research...

Andreas Grivas

andreasgrv.bsky.social

08 September 2026 19:33

Developing LLMs to be Large Plagiarism Machines is a choice "we cannot rule out that de-identified data derived from your usage of our products helped improve our models"

Dan Goodman

neural-reckoning.org

08 September 2026 19:32

If - as now seems likely - LLM companies are mining their logs for juicy problems, then that means that it's very likely that "secret" test sets don't stay secret for long. When looking at new models' performance on benchmarks that date from before that model, we shouldn't take results at face value

Eivinas Butkus

eivinas.bsky.social

22 July 2026 05:23

Do world models emerge in neural networks trained for prediction? Generative Adversarial Collaboration (GAC) at #CCN2026

John Morrison

johnmorrison.bsky.social

22 July 2026 05:23

This should be fun! I'll be talking about what it means for a neural network to have a world model (joint work with @raphaelmilliere.com) and presenting new evidence that the standard example, Othello-GPT, does not have one (joint work with @shauli.bsky.social among others).