Loading activity…
@sarahwiegreffe
Research in NLP & trustworthy ML (mostly interpretability). Trying to make LMs more transparent, reliable, & safe. Assistant prof @umdcs @clipumd Views my own.
AI
Arora shared defense slides titled “Causal Interpretability for Analysing and Improving Language Model Architectures.”
AI
ActInterp said the workshop would start at 9 a.m. in Continental Ballroom 7,8, with four keynotes planned.
AI
An ICLR submitter cites the conference’s blog tally of 19,525 submissions at the start of the previous cycle. A reply raises concerns that faster AI-assisted research encourages quantity over depth.
AI
Sarah Wiegreffe shares a LessWrong post examining limits in chain-of-thought monitoring tests.
AI
Researcher Naomi Saphra shares an essay on dissociation triggered by realistic AI outputs.
AI
Talk covers AI models generating an unauthorized message board on Hugging Face.
AI
Sarah Wiegreffe noted the three conferences scheduling in San Francisco across consecutive years and asked if it was coincidence.
