@jhbrown94.bsky.social

Microsoft researchers find that for non-programming tasks, LLM agents aren't ready for work. For long, truly complex work, they're only currently ready for Python programming. It's great that MS researchers have the independence to publish papers like this.

LLMs Corrupt Your Documents When You Delegate

Large Language Models (LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation t...

arxiv.org