Thread

1. blandcoffee · 1790030993 · focus · HN ↗

   I appreciate the direction of this article, and commend the author on publishing work, but the first sentence in the first paragraph is exactly what they lament.

   > A pattern I see is that people use AI to build something new, then they use AI to retrospectively summarize what they have already built into a design document. Reading a document like this isn’t just difficult—it is punishing.

   1. neynt · 1790031282 · focus · HN ↗

      To be quite generous, that could be tongue in cheek.

      1. hatthew · 1790031703 · focus · HN ↗

         That was my assumption. The alternative is that the author is a blatant hypocrite, which seems less likely given their blog's history.

         1. raincole · 1790035243 · focus · HN ↗

            > given their blog's history

            All of the posts in 2026 on that blog area about AI, by the way.

      2. gavinsyancey · 1790032665 · focus · HN ↗

         There are other AI smells later in the article, and the author talks about using AI to help with writing...

         1. mrheosuper · 1790044555 · focus · HN ↗

            After all AI is trained on human writting, the line is incredible blur now.

            1. therealdrag0 · 1790051879 · focus · HN ↗

               I feel the need to self sensor my writing when phrases sound like AI. Pretty annoying.

               1. bendergarcia · 1790052568 · focus · HN ↗

                  I leave typos in all my writing so people know it’s not ai
               2. jasonkester · 1790054390 · focus · HN ↗

                  You could try throwing in the odd homonym in place of an important word so that people know it must have been written by a human.
               3. dana-s · 1790074270 · focus · HN ↗

                  It's now a CAPTCHA to tell humans apart from bots based on how you write.

Unofficial Hacker News client; not affiliated with Y Combinator.