How the Claude Code team thinks about verification

(claude.dev)

34 points | by craigmart 1 hour ago

12 comments

  • OtherShrezzing 14 minutes ago
    This article feels like the result of having unlimited tokens at your disposal. It’s got some very expensive practices, where near-free practices would produce the same or better results.

    There’s a long section in the middle where the article describes per-change verification via skill files and “ask Claude to use the chrome-for-Claude tool” when checking if changes have introduced regressions.

    But there’s already tools which do this without spending tokens tokens. Playwright will achieve equal quality but deterministic results across the same verification attempts. It is write-once-use-often, so has a marginal cost near zero.

    • xnorswap 4 minutes ago
      I agree completely, there was a much better talk on this by Lauren Tan: https://www.youtube.com/watch?v=O_zcc6Xl12g

      A key pillar was introducing things like static analysis to provide cheap deterministic checks as the first goal and only then moving to other forms of verification.

    • bitlad 6 minutes ago
      They are living in the future.

      I think future AI cost will be as cheap as doing an API call in classic sense.

    • cyanydeez 8 minutes ago
      Chinese gonna beat anthropic because they gluttonous use of AI.
    • catchnear4321 4 minutes ago
      It behooves the token merchant to espouse the benefits of having more tokens.

      Not that it is an explicit, conscious direction, but it very much is one.

      You’re not wrong, in that free flowing tokens are enough to convince such a group it’s simply good advice.

  • girvo 48 minutes ago
    > With them, you can run dozens or hundreds in parallel.

    Im already spending my $2k usd per month in tokens with just one or two agents. How do they expect me to do that?

    • varispeed 0 minutes ago
      This is probably aimed at gullible governments to burn tokens using tax payer money.
    • thatsabadlook 33 minutes ago
      You should fire yourself and have your boss go all in on anthropic duh. If you are the boss then you either shouldn't have gone down this path, accept your code won't be verified, or shut your doors.
      • 4lb3rn 25 minutes ago
        Exactly this. I build large systems like erp, ipaas just from a Claude team with two premium licences. everything builds, verifies, deploys itself. I can track everything and implement features in a days. security and big fixing is background work. I would love to know what 2000$ worth of tokens do in your business.
  • nandanadileep29 36 minutes ago
    excellent content from the team. very concise and clear
  • runtarmac 9 minutes ago
    [flagged]
  • oceanrelay 43 minutes ago
    [flagged]
  • mohsen1 29 minutes ago
    Verification is the bottleneck and that's why we're building https://Proofline.sh

    Starting with infra evidence and soon expanding to application verification loops. This is a very exciting place to build and we're seeing great results once the verification loop is closed for the teams

    • beatrice-costa 20 minutes ago
      how is this different from a claude code verification loop?
  • dotdi 29 minutes ago
    > https://github.com/anthropics/claude-code/issues has over 16k open issues

    this u?

    • laichzeit0 23 minutes ago
      And 90k closed. Looks like it's doing a pretty good job.
      • ahsillyme 4 minutes ago
        Issues are automatically closed after being inactive for too long. It's also true that many issues that are filed there have nothing to do with Claude Code proper. To conclude, these numbers (either many open, or many closed, or any relationship between them) a-priori mean nothing either way.
      • orbital-decay 3 minutes ago
        Opening and closing GitHub issues does not necessarily mean doing some job.
      • catlifeonmars 6 minutes ago
        [delayed]
  • Ampersander 44 minutes ago
    Why is the team thinking? Their product should be doing that for them
    • Goto80 8 minutes ago
      Why is there a team? Their product should be the team. /s
  • inamorty 9 minutes ago
    Can they not afford someone with an engineering background?
    • FartyMcFarter 0 minutes ago
      They poached a lot of people from companies like Google that have solid engineering practices. I imagine it's a culture issue if anything, not a knowledge/background issue.
  • ForHackernews 24 minutes ago
    Ironic that this page loads partially styled with broken CSS:

    "The resource at “https://claude.dev/_next/static/chunks/241gnzjfqbp9f.css” preloaded with link preload was not used within a few seconds. Make sure all attributes of the preload tag are set correctly."

  • dude250711 1 hour ago
    > ...On the Claude Code team, the vast majority of our code (~90%) is written and reviewed by Claude...

    I am more interested in the remaining 10%.

  • mococa 15 minutes ago
    So a lot of slop...