Hacker News: ajrouvoet

New comment by ajrouvoet in "The Normalization of Inexplicable Failures"

ajrouvoet — Sun, 27 Sep 2026 17:18:21 +0000

Inexplicable has a range from “I can’t explain that” to “that is not in the realm of possibility”. Windows failures especially have been steadily moving from A (already pretty sad) to B in the past years and I’ve been thinking about how utterly unempowering that is. Tools stop being tools if they have a secret life of their own.

Excellent post!

New comment by ajrouvoet in "Python string literals are kinda funny"

ajrouvoet — Sat, 08 Aug 2026 20:08:00 +0000

It is baffling to me that Python seems to insist on reinventing language features and coming up with the most incomprehensible of designs. The whole dataclass and serialisation ecosystem comes to mind, as well as the evolution of typing.

The language exposes so much of its internals that even if the design were consistent, the ecosystem of (buggy) libs and tools makes it inconsistent.

New comment by ajrouvoet in "Converting Files into Minecraft Worlds"

ajrouvoet — Thu, 23 Jul 2026 19:50:36 +0000

Excellent and (it goes without saying) important work. My only suggestion is to edit a file by… playing Minecraft. Extra points if you make a meaningful edit in survival mode.

New comment by ajrouvoet in "Show HN: CodeAlmanac – Karpathy-style codebase wiki from your conversations"

ajrouvoet — Tue, 21 Jul 2026 20:39:21 +0000

Yes: the human provides the qualitative judgement and the agent provides the executive function.

New comment by ajrouvoet in "Show HN: CodeAlmanac – Karpathy-style codebase wiki from your conversations"

ajrouvoet — Tue, 21 Jul 2026 19:15:51 +0000

Do you mean that specifically those models perform badly without guidance or do all models need specific instructions for technical writing?

We have observed that it is a loss for teamwork that the sparring with AI is entirely lost when only the technical conclusion is recorded. I write to recover that for my team and an AI can use it to its advantage as a side effect.

It would be cool to have good tool support for this process, but I’d bet on support, not delegation in that case.

New comment by ajrouvoet in "Show HN: CodeAlmanac – Karpathy-style codebase wiki from your conversations"

ajrouvoet — Tue, 21 Jul 2026 18:35:00 +0000

Although I’d like this to work, I have not seen evidence that AIs extract good reusable knowledge from sessions without strong guidance.

I do R&D work in comp sci and usually write software and reports or papers in parallel. I have been using Opus in a controlled human-in-the-loop fashion to (significantly) speed up the work. While I’m at times surprised how high-level input steers output the right way, no high level ideas emerge from the AIs output. Many attempts to abstract from the concrete are wrong.

As a consequence, most writing is poor on content and form. It writes about the wrong things and crosses abstraction levels all the time. It cannot keep implementation details and conceptual leaps apart.

I don’t know what this means for the aim of this project to maintain important info for agents. Perhaps there are enough low-hanging fruits. That said, I’m skeptical that the resulting wiki is good documentation for human contributors.

New comment by ajrouvoet in "Why do people hate the tech industry? (2023)"

ajrouvoet — Wed, 15 Jul 2026 12:35:52 +0000

I think that just highlights how “empowerment” through tech is biased towards producers, which makes sense because that aligns with the usual business propositions.

For consumers, YT is not empowering. It fulfills a need, well enough to tie them to the platform. But it is obviously not set up to hand them any more power than to serve that goal. You want to shield yourself from wasting time here? Sorry, not sorry, our goal is to steal your attention and entertain you just enough that you keep scrolling.

New comment by ajrouvoet in "Show HN: Microsoft releases Flint, a visualization language for AI agents"

ajrouvoet — Wed, 08 Jul 2026 19:35:58 +0000

A well designed intermediary enables both validation and control over the output independent of the AI. This changes the interaction model between human and AI from delegation to collaboration.

New comment by ajrouvoet in "Behind the scenes with the Midjourney scanner [video]"

ajrouvoet — Mon, 06 Jul 2026 10:12:55 +0000

The announcement video has some quality that made it hard to shake the feeling that I’m watching a black mirror episode. Or a sequel to Ex Machina.

New comment by ajrouvoet in "Kotlin's rich errors: Native, typed errors without exceptions"

ajrouvoet — Fri, 23 Jan 2026 21:16:50 +0000

This last point is the key observation.

New comment by ajrouvoet in "Microsoft only lets you opt out of AI photo scanning 3x a year"

ajrouvoet — Sun, 12 Oct 2025 08:45:42 +0000

Meta just lost a court case against bits of freedom in the Netherlands, because their instagram setting to turn off the attention grabbing feed would reset every month or so. The court ruled that this infringed on the user’s freedom.

Source: https://www.dutchnews.nl/2025/10/court-tells-meta-to-give-du...

New comment by ajrouvoet in "Google, Meta and Microsoft to stop showing political ads in the EU"

ajrouvoet — Fri, 10 Oct 2025 20:49:48 +0000

Dutch newspaper Trouw also reported that their ad was rejected multiple times by Meta. After inquiry into this they found it was because it was about sustainability and hence considered “a political ad”.

(Paywalled) Source: https://www.trouw.nl/cultuur-media/advertenties-over-armoede...