‹ BackHN Continuity

Thread

MiMo v2.6

1130 points · 483 comments · volf_

  1. simonw · · focus · HN ↗
    Pelicans for Flash: <a href="https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Ff8a40b411544d0a7806003ef8c0d664e" rel="nofollow">https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=ht...

    Pelicans for Pro: <a href="https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F53688c39d37bcbf0cb1a98781c277cdb" rel="nofollow">https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=ht...

    1. handfuloflight · · focus · HN ↗
      How does this translate to coding performance, which is what most of HN cares about (...I assume)?
      1. simonw · · focus · HN ↗
        It means they&#x27;re good at writing SVGs, in particular SVGs of animals riding modes of transport!
      2. lanyard-textile · · focus · HN ↗
        I only visit HN for the pelicans, personally.
        1. lukewrites · · focus · HN ↗
          Yeah, I thought the &quot;N&quot; was for Nest
          1. machomaster · · focus · HN ↗
            Hungry Nibbler
      3. jofzar · · focus · HN ↗
        It&#x27;s incase you want to recreate this scene from who framed Roger rabbit in svg form, duh.

        <a href="https:&#x2F;&#x2F;simonwillison.net&#x2F;2026&#x2F;Sep&#x2F;18&#x2F;the-creative-spirit-of-who-framed-roger-rabbit&#x2F;" rel="nofollow">https:&#x2F;&#x2F;simonwillison.net&#x2F;2026&#x2F;Sep&#x2F;18&#x2F;the-creative-spirit-of...

        1. singularity2001 · · focus · HN ↗
          How dare people say neural networks generalize when it&#x27;s all clearly in the training data? &#x2F;ß
      4. pipsterwo · · focus · HN ↗
        Absurd to think pelicans translate to coding performance. I don&#x27;t care about coding! I need to generate a large volume of high quality pelican SVGs
        1. gpt5 · · focus · HN ↗
          Making SVGs is coding (of a very specific markup language). So it&#x27;s not actually absurd. We&#x27;ve also seen that more capable models are generally better at everything minus benchmark contamination (benchmaxxing) anomalities.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.