Chip ChristianSep 13, 2025
Per Axbom
Going from: "I wanted the computer to do this well-defined task, and it did it, and saved me some time because I can verify that what it did is aligned with my intent, and correct."

Going to: "I asked the computer random stuff and I'm 'obeying' without knowing why or how the output came about. I don't care much about understanding my own will anymore as long as the software says 'AI' on the label."
Sep 10, 2025 at 10:33amWeb
Show threadDave Winer ☕️Sep 10, 2025

@axbom

Well put. And the new computer encourages this by always leading to the next step, and it’s always wrong.

Show threadLars AnderssonSep 10, 2025
@axbom
Låter som en mycket dålig utveckling!
Show threadMark CrockerSep 14, 2025

@axbom this is why @pluralistic is writhing articles about "Reverse Centaurs". It wasn't until I saw the image in this article, https://pluralistic.net/2025/09/11/vulgar-thatcherism/#there-is-an-alternative , that the meme really stuck in my head though 🤣

#ReverseCentaur

Pluralistic: Reverse centaurs are the answer to the AI paradox (11 Sep 2025) – Pluralistic: Daily links from Cory Doctorow

Show threadPer AxbomSep 14, 2025
@mcrocker @pluralistic Good one. Thanks for the reminder to get back to reading his rss feed.
Show threadcraignicolSep 14, 2025
@mcrocker @axbom @pluralistic reminds me of the William Gibson quote about the future not being evenly distributed. Or indeed the main plot of The Time Machine, and how 130 years have passed and we still have the Morlocks and the Eloi. But instead of having to put them underground, we just hide them behind a computer screen and some fibre optic cable.
Show threadDJ Sexy FreshSep 14, 2025
@mcrocker @axbom @pluralistic the Eurorack sythnesizer wall on the left really gets me
Show threadeswillwalkerSep 14, 2025
@mcrocker @axbom @pluralistic “digital asbestos.” I love that metaphor.
Show threadAndThisIsMrsPeacock 🏳‍🌈Sep 15, 2025

@ELS @mcrocker @axbom @pluralistic One of my new tech quiz questions is to give them a problem, and then show them AI-generated code that solves that problem.

Then I ask them to evaluate the AI code: if its good/bad, efficient or not... sure you can use AI to write code, the skill I care about is if you can tell if the result is any good or not.

Show threadAndThisIsMrsPeacock 🏳‍🌈Sep 15, 2025

@ELS @mcrocker @axbom @pluralistic Which, weirdly, is the most effective interview questions I've ever had, because it tells me:

1. you do/not understand good/bad coding practices and can tell me when you see them,

2. you can use a modern tool but also accept the fact it may not always work right and,

3. you're able to use your brain to synthesize new tech output into your workflow without losing quality

Use of AI, for me, is actually a super great way to evaluate engineers.