‹ BackHN Continuity

Thread

AI coding has made CI a bottleneck, so we reworked ours to keep up

317 points · 408 comments · julian_digital

  1. torben-friis · · focus · HN ↗
    Here's my constant question:

    Everyone's going so fast that they keep hitting walls. Review, CI, product asking for things, whatever.

    Why have we not seen an improvements in products?

    While every post and thread feels like a 90's wall street office, the new android and iphone ship with fewer features than usual. No indie guys come up with a linux-sized alternative OS. Switch 2 remains unhacked. Windows takes 3 seconds to show the right click menu.

    Is everyone just running full speed in circles or something?

    1. the_sleaze_ · · focus · HN ↗
      We 100% have. I've seen significant improvements in many of the services I use.
      1. written-beyond · · focus · HN ↗
        Not doubting you, care to share what those improvements were?
        1. the_sleaze_ · · focus · HN ↗
          Gmail has a feature that uses ai to search emails.

          Cursor, Codex, Claude Code, Pi, Zed, Oh my Pi.

          The recent improvements and optimizations for Redis.

          Figma code, mcp and api.

          The recent improvements to Uv, Pnpm, and others with autoresearch loops.

          1. written-beyond · · focus · HN ↗
            We weren't asking which tools integrated LLMs, we specifically asked which got better by building them with LLMs.

            Cursor, Codex and Claude Code all have terrible desktop applications, which are a laggy mess on Windows.

            What improvements did UV do with auto research loops, I wasn't aware of that.

            1. the_sleaze_ · · focus · HN ↗
              You're arguing a distinction without a difference. I added those tools because we can agree they are almost entirely built by LLMs.

              > Cursor, Codex and Claude Code all have terrible desktop applications

              No they aren't - at least not anymore than any other cross platform focused program - and we're not here to bike shed about modern software.

              In fact they're pretty solid.

              I had more examples that you've yet to refute or even acknowledge. AI isn't inherently bad just like money isn't inherently evil. You're also allowed to not like something just cuz w/o a logical reason. I just don't have to agree with you.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.