James Endres Howelljameshowell@fediscience.org
Nov 7, 2026, 7:07 PM@cwebber's essay is SO GOOD. I am dismayed that I missed it.
https://dustycloud.org/blog/faulty-towers-vibe-sickness-and-the-vibe-bobsled/
Replies
slotosslotos@mastodon.com.plNov 7, 2026, 9:25 PM> It's simple. Generation is not the slow part of coding. Theory-building and review are.
To add to this, spending time writing code is where insights happen. I’m not losing time by not generating code I know the shape of, I’m switching to a menial task to let my brain do the parallel processing it can never do with the problem it attends to.
Nov 7, 2026, 9:30 PM@jameshowell Awesome, thx for sharing. Loved the bobsled analogy.
@cwebber- Øyvind Bugge SolheimOyvindbs@nerdculture.deNov 7, 2026, 9:55 PM
I love the vibe sickness-term. I use vibe coding because I don’t know how to code but when I encounter different kinds of «not slop but not not slop» it gets tiresome fast. Just the extreme amounts of text, saying something but not really saying anything is the worst. I don’t know how we can solve it and as cwebber writes, we are mostly just humming along down the bobsleigh track..
Nov 8, 2026, 12:10 PM@jameshowell @cwebber best part for me was the code review example from the PhD thesis. Will use that in my discussions from now on.