Subscribe
Topic / page 3

LLM

Articles, page 3

41-60
  1. Opinion: An AI Judge Is Not a Neutral Referee

    A 2023 paper found AI judges can match human raters, and also that they flip verdicts when answer order changes and can be fooled by length. My view: treat an AI judge as a rater with habits, and check them.

    Opinion
    6 min read
  2. Opinion: Start With a Workflow, Not an Agent

    Anthropic's post separates workflows from agents and advises finding the simplest solution possible. My view: make a fixed workflow the default for any task whose steps you can write down in advance.

    Opinion
    4 min read