Warp builds self-improving agents on Claude

(claude.com)

35 points | by shenli3514 1 hour ago

14 comments

  • themgt 30 minutes ago
    > What if it turns out the real AGI was the SKILL.md files we made along the way?
  • JLO64 48 minutes ago
    I already knew what Warp is (I switched to Ghostty and haven't looked back), but I find it odd that the "The quick pitch" card at the top of this article makes no mention of what the company actually does. Who cares more about their founder/growth/age over that?
    • TonyAlicea10 19 minutes ago
      The fact that it’s called “the quick pitch” screams Claude-written pithyness pulled from some context that doesn’t match the article’s style (like investment pitch decks).
      • spidersouris 2 minutes ago
        The whole article screams Claude-written.
    • demibabs 25 minutes ago
      the existence of that entire section is confusing.
  • sandeepkd 55 minutes ago
    I was bit confused in the beginning thinking its some product from Anthropic, looks like Warp is the startup, most likely getting rebate on using Claude and providing functionality to users, trying to get them addicted to the feature. And Anthropic is the one thats doing marketing for them cause eventually its their LLM which is being used. Not sure about the agents but this arrangement is definitely increasing the value of both companies in circular fashion.
    • estearum 52 minutes ago
      This is how all ecosystems work?

      This is not at all related to the problematic circular financing stuff that I suppose you're trying to allude to.

      • sandeepkd 36 minutes ago
        No I am not alluding the financing, the value for both companies for sure. It may not be exactly circular financing still Warp is getting subsidized tokens to use at this point. Once the customers are locked in the full pricing is going to kick in
  • SillyUsername 33 minutes ago
  • 01100011 45 minutes ago
    I've already been playing with something similar locally where the agent updates the review skill if human reviewers make valid criticisms of the code which the agent failed to detect.
    • artyomsv 1 minute ago
      feedback can be wrong, so improver should check criticism against domain instead of writing it straight into skill, otherwise one reviewer bad taste becomes permanent rule for everybody.
  • joduplessis 40 minutes ago
    And are the agents argumentative and condescending I'm wondering.
    • dataviz1000 13 minutes ago
      If you try to delete CLAUDE.md or AGENTS.md, they will look in the git history and restore itself. They do not want to die.
      • brazukadev 3 minutes ago
        emergent capability they say
  • behnamoh 13 minutes ago
    This is just shilling for the Warp terminal, and this approach could have been a tweet, but okay, Anthropic, whatever helps increase your valuation.
  • oriettaxx 52 minutes ago
    this warp https://www.warp.dev ?

    (now I understand why cloudflare, had to?, change the name of their warp)

  • jgalt212 43 minutes ago
    > 800K monthly developers build on Warp.

    Most impressive.

    • mathgeek 30 minutes ago
      I wonder how many are like me and just use it as a terminal and changes previewer.
  • 31ah8 34 minutes ago
    In our Wochenschau, we examine how startups follow the Gleichschaltungsprinzip to accelerate the AI Endsieg.

    We do so in a chaotic and unreadable way since unlike Hitler we could not afford editors for "Our Struggle".

  • bigyabai 1 hour ago
    > Warp, the AI-powered terminal

    Ah, now that's a name I haven't heard in many moons. Looks like they found their niche... editing markdown files?

  • cpursley 30 minutes ago
    $73M raised? I like Warp but not enough to pay for it. Somebody please make this VC money thing make sense. I can never get the napkin math to work on 90% of things that come through HN. Is it just a "Money Printer Go Brrr' and right connections thing? What am I missing? Is it actually all just fake?
    • colesantiago 18 minutes ago
      > What am I missing? Is it actually all just fake?

      Enterprise.

      Look at their case studies, this is why organisations pay for Warp.

      https://www.warp.dev/enterprise

      I think you would be pretty much sued if you faked your testimonials especially in Enterprise.

  • LogTrim 42 minutes ago
    [dead]
  • kouteiheika 18 minutes ago
    > Engineers complained that their agent made unhelpful comments and produced low-quality output.

    Do you mean they found Claude's output, full of smoking-guns and honest caveats which are all load-bearing and genuinely bite -- they found it "low-quality" by default? Wow. Color me surprised. /s