‹ BackHN Continuity

Thread

Show HN: How Stale Is Your AI? Release age and training cutoff for 20 models

85 points · 50 comments · joozio

  1. jasonjmcghee · · focus · HN ↗
    It still matters, but in the age of good reasoning, tool use, and web search, this is much less of a problem than it used to be.
    1. spindump8930 · · focus · HN ↗
      It can be quite hard to determine what needs a tool call or not. LLMs are not well calibrated to what they know and don't know, and tool calls can add latency and extra costs. There are lots of things that are "obvious" right until they aren't - especially political events and disasters.
      1. joozio · · focus · HN ↗

        [dead]

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.