Llms.txt and MCP didn't move the needle

(backpackforlaravel.com)

18 points | by moebrowne 47 minutes ago

3 comments

  • rcymerys 11 minutes ago
    Does anyone have any empirical evidence that llms.txt makes any difference?

    I've had multiple marketeers try to convince me that it's a must for a website, but the best "proof" they could give me were some LinkedIn posts from other marketing consultants. I've tried replicating a scenario where Claude/ChatGPT would look for this file, but without luck.

    • 0x696C6961 4 minutes ago
      It's just a token saving mechanism. My llms.txt are a text index/sitemap for the agent. AFAIK Claude doesn't look for this file, it needs to be explicitly instructed to.
  • antiloper 14 minutes ago
    This is one of the worst pieces of unedited LLM slop I've seen yet. At least read what it outputs instead of doing 1 sentence prompt -> ctrl+c ctrl+v -> publish...
    • StilesCrisis 7 minutes ago
      Usually I'm sensitive to this but it didn't register for me. What was the tell?
    • SomewhatLikely 3 minutes ago
      I didn't get that impression. It felt like lived experience to me. What made it feel like slop to you?
      • Forgeties79 0 minutes ago
        Read “What Didn’t Move the Needle” again and it’ll really pop out at you.
  • drbscl 11 minutes ago
    Why on earth would you make an MCP to let agents query your docs specifically?

    We’ve moved well past that, and even when docs MCPs were the best approach, everyone just used context7 or similar.

    • vorticalbox 3 minutes ago
      > Why on earth would you make an MCP to let agents query your docs specifically?

      because documenting your api in swagger is too much work?