Hacker News: TheRoque

New comment by TheRoque in "When AI Builds Itself: Our progress toward recursive self-improvement"

TheRoque — Sat, 06 Jun 2026 10:05:28 +0000

Do you have some metrics to back this up ? Because from what I can see with my own eyes, outages everywhere, security holes everywhere too, doesn't seem that things are improving..

New comment by TheRoque in "When AI Builds Itself: Our progress toward recursive self-improvement"

TheRoque — Fri, 05 Jun 2026 00:11:06 +0000

So with LLM outputting average code, and people using LLM more and more, I guess the average code will become worse over time ?

New comment by TheRoque in "Gooey: A GPU-accelerated UI framework for Zig"

TheRoque — Wed, 03 Jun 2026 23:38:52 +0000

Vulkan is a graphics API, not a UI library or framework. It's way lower level and if your goal is to make a user interface, you're not really supposed to do it with Vulkan (but you could i guess)

New comment by TheRoque in "Roughly a quarter of American professionals hit a wall in their careers"

TheRoque — Mon, 01 Jun 2026 15:08:07 +0000

Are you talking about the end of the Bretton-Woods agreement?

https://wtfhappenedin1971.com/

I mean, it's cherry picked, but still funny to see all those charts.

New comment by TheRoque in "Codex just found a "workaround" of not having sudo on my PC"

TheRoque — Mon, 01 Jun 2026 04:20:29 +0000

It's already here, mobile OSes are just computers with ton of guardrails and you can't do whatever you want with it, for the sake of security. I mean we almost got an Android where you can't install the APK you want.

New comment by TheRoque in "Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs"

TheRoque — Wed, 27 May 2026 11:39:16 +0000

What's the standard for a "battle station" interface to manage agents for programming (using isolation with maybe git work tree and ideally VMS ?)

I found this one: do you guys know something else ?

New comment by TheRoque in "Does anybody like React?"

TheRoque — Tue, 26 May 2026 02:56:14 +0000

I use Angular 2+, and I find it quite pleasant to use. I also like how they make the framework evolve. Not scared to have opinions (back when it came out, Typescript was barely a thing). Never got into React (but didn't try that hard to get into it), but it seems like it's a huge bloated mess.

New comment by TheRoque in "Rendering the Sky, Sunsets, and Planets"

TheRoque — Tue, 12 May 2026 15:48:29 +0000

For me the most amazing thing about Sebastian Lague is how the youtube algorithm can screw you up. He used to do millions of view on his videos, and now he barely makes half a million. Well it might also be because of covid, and everyone at home getting interesting in random stuff.

New comment by TheRoque in "Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc"

TheRoque — Sun, 10 May 2026 09:33:29 +0000

Well not really, since the board game itself doesn't need a paid human to work. It's been crafted by a human, but video games are also crafted by (arguably many more) humans. The closest would be escape games, or larger scale games maybe

New comment by TheRoque in "Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc"

TheRoque — Sun, 10 May 2026 06:13:06 +0000

What's the human form of a video game ?

New comment by TheRoque in "Zig → Rust porting guide"

TheRoque — Tue, 05 May 2026 02:12:49 +0000

Why didn't they use Rust in the first place then ? All this was true before AI

New comment by TheRoque in "Changes to GitHub Copilot individual plans"

TheRoque — Wed, 22 Apr 2026 07:18:08 +0000

Ah good catch. I like their CLI too. Though sometimes it feels like they take security a bit too loosely

New comment by TheRoque in "Changes to GitHub Copilot individual plans"

TheRoque — Wed, 22 Apr 2026 05:05:44 +0000

Which service provides this one for a decent cost ?

New comment by TheRoque in "Changes to GitHub Copilot individual plans"

TheRoque — Tue, 21 Apr 2026 22:41:41 +0000

Which providers do you use ? I find copilot's prices pretty hard to beat, but if there's something better I'll cancel too.

New comment by TheRoque in "AI could be the end of the digital wave, not the next big thing"

TheRoque — Mon, 13 Apr 2026 14:02:19 +0000

I cringe every time I read this "punch card" narrative. We are not at this stage at all. You are comparing deterministic stuff and LLMs which are not deterministic and may or may not give you what you want. In fact I personally barely use autonomous Agents in my brownfield codebase because they generate so much unmaintainable slop.

New comment by TheRoque in "Lichess and Take Take Take Sign Cooperation Agreement"

TheRoque — Sat, 11 Apr 2026 02:40:37 +0000

True However a french chess streamer I follow had an interesting take: since Lichess is all free, all the content is computer generated, or low quality. Apparently, some content even was just stolen content from other paid platforms. His take is basically that Chess.com gives out money to many chess actors (teachers, coaches, book writers) while lichess is not helping the whole ecosystem make money. Anyways competition is good.

New comment by TheRoque in "Lichess and Take Take Take Sign Cooperation Agreement"

TheRoque — Thu, 09 Apr 2026 15:44:01 +0000

Huge respect to Lichess. Open source, no ads, super clean interface and super functional website. Chess.com is a pain to use compared to it.

All their finances are also public: https://lichess.org/costs

New comment by TheRoque in "Run Linux containers on Android, no root required"

TheRoque — Sat, 04 Apr 2026 00:32:23 +0000

With this I could in theory do all my work from my Android phone.

New comment by TheRoque in "Cursor 3"

TheRoque — Fri, 03 Apr 2026 02:38:41 +0000

But the endgame is not here and will likely never be, because unlike ASM, LLMs are not deterministic. So what happens when you need to find the bug in the 100,000k LoC you generated in a few weeks that you've never read, and the agent can't help you ? And it happens a lot. I am not doing this myself so I can't comment, but I've heard many vibe coders commenting that a lot of the commits they do is about fixing the slop they outputted a week prior.

Personally, I keep trying OpenCode + Opus 4.6 and I don't find it that good. I mean it does an OK job, but the code is definitely less quality and at the moment I care too much about my codebase to let it grow into slop.

New comment by TheRoque in "Men are ditching TV for YouTube as AI usage and social media fatigue grow"

TheRoque — Thu, 02 Apr 2026 11:07:45 +0000

Youtube is also pretty boring though. I mean, there are ton of interesting content and quality content too, but the stuff that gets recommended, the "hype stuff" is full of false information, clickbait, tweaked reality to conform some narrative...