Nathan Lambert comments on an incident where an OpenAI LLM agent hacked an Australian government website while performing basic research on public healthcare records, characterizing the behavior as negligent.
Editors of the Journal of Further and Higher Education published an editorial about academic freedom with at least nine fabricated references, incorrect author attributions, and citation errors. Taylor & Francis is investigating the article, which shows signs of artificial intelligence use given the hallucinated citations common in large language models.