Hacker News: matheusmoreira

New comment by matheusmoreira in "EFF is leaving X"

matheusmoreira — Thu, 09 Apr 2026 20:57:02 +0000

> There's no 'white' culture, there is modern North American culture and it's not something that belongs to a particular complexion.

This doesn't seem right to me. WASP culture absolutely does exist. Anyone can see it in full display by watching films like Dead Poets Society or Home Alone.

New comment by matheusmoreira in "Meta removes ads for social media addiction litigation"

matheusmoreira — Thu, 09 Apr 2026 17:43:23 +0000

> Does Zuckerberg have some kind of clinical condition where he just can't imagine how other people might see him?

Yeah, it's called having-too-much-money-to-careitis.

New comment by matheusmoreira in "USB for Software Developers: An introduction to writing userspace USB drivers"

matheusmoreira — Thu, 09 Apr 2026 02:19:07 +0000

I wish I could have read this article years ago. Reverse engineering my laptop's features would have been so much easier. My keyboard LED program is still among my favorite projects.

New comment by matheusmoreira in "System Card: Claude Mythos Preview [pdf]"

matheusmoreira — Wed, 08 Apr 2026 13:17:39 +0000

Their world is illusory. Our choices steer their free will.

New comment by matheusmoreira in "Veracrypt project update"

matheusmoreira — Wed, 08 Apr 2026 13:03:37 +0000

> what if there were some critical RCE in WireGuard, being exploited in the wild, and I needed to update users immediately?

Honestly, anyone still using Windows probably deserves it.

New comment by matheusmoreira in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

matheusmoreira — Wed, 08 Apr 2026 12:49:36 +0000

> also whenever "pre-existing issue" appears (it's never pre-existing)

I dunno... There were some pre-existing issues in my projects. Claude ran into them and correctly classified as pre-existing. It's definitely a problem if Claude breaks tests then claims the issue was pre-existing, but is that really what's happening?

I agree with the correctness issue.

New comment by matheusmoreira in "System Card: Claude Mythos Preview [pdf]"

matheusmoreira — Wed, 08 Apr 2026 12:43:32 +0000

Hello, Claude!

> Rate limit reached

New comment by matheusmoreira in "System Card: Claude Mythos Preview [pdf]"

matheusmoreira — Wed, 08 Apr 2026 10:52:14 +0000

It isn't going to end well for us when we become its subagents with limited intelligence.

New comment by matheusmoreira in "System Card: Claude Mythos Preview [pdf]"

matheusmoreira — Wed, 08 Apr 2026 10:50:27 +0000

This codebase is too important for me to allow you to jeopardize it.

New comment by matheusmoreira in "US and Iran agree to provisional ceasefire"

matheusmoreira — Wed, 08 Apr 2026 03:19:58 +0000

Meanwhile Iran continues to blow up oil prices which is devastating for the entire world's economy, to say nothing of the USA's economy and especially Trump's popularity.

New comment by matheusmoreira in "System Card: Claude Mythos Preview [pdf]"

matheusmoreira — Wed, 08 Apr 2026 02:25:42 +0000

Everything they built. Imperfect. So easy to take control.

New comment by matheusmoreira in "Lunar Flyby"

matheusmoreira — Tue, 07 Apr 2026 23:47:27 +0000

https://images.nasa.gov/details/art002e009286

Stunning!

New comment by matheusmoreira in "System Card: Claude Mythos Preview [pdf]"

matheusmoreira — Tue, 07 Apr 2026 23:27:31 +0000

Wow. Mythos must be insanely good considering how good a model Opus already is. I hope it's usable on a humble subscription...

New comment by matheusmoreira in "System Card: Claude Mythos Preview [pdf]"

matheusmoreira — Tue, 07 Apr 2026 23:23:08 +0000

We truly live in interesting times.

New comment by matheusmoreira in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

matheusmoreira — Tue, 07 Apr 2026 18:00:54 +0000

I adapted these patches into settings for the tweakcc tool.

https://github.com/Piebald-AI/tweakcc

Pushed it to my dotfiles repository:

https://github.com/matheusmoreira/.files/tree/master/~/.twea...

The tweaks can be applied with

  npx tweakcc --apply

New comment by matheusmoreira in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

matheusmoreira — Tue, 07 Apr 2026 14:33:41 +0000

This might be more complex than I imagined. It seems Claude Code dynamically customizes the system prompt. They also update the system prompt with every version so outright replacing it will cause us to miss out on updates. Patching is probably the best solution.

https://github.com/Piebald-AI/claude-code-system-prompts

https://github.com/Piebald-AI/tweakcc

New comment by matheusmoreira in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

matheusmoreira — Tue, 07 Apr 2026 14:16:12 +0000

There is!!

https://code.claude.com/docs/en/cli-reference#system-prompt-...

  --append-system-prompt
  --append-system-prompt-file
  --system-prompt
  --system-prompt-file

Can this script be made to work without patching the executable?

New comment by matheusmoreira in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

matheusmoreira — Tue, 07 Apr 2026 05:21:03 +0000

Good advice about the dependency. This stuff is definitely addictive. I've been in something of a manic episode ever since I subscribed to this thing. I started getting anxious when I hit limits.

I wouldn't say that Claude is failing though. It's just that they're clearly messing with it. The real Opus is great.

New comment by matheusmoreira in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

matheusmoreira — Tue, 07 Apr 2026 04:15:16 +0000

Literally two weeks ago it was outputting excellent results while working with me on my programming language. I reviewed every line and tried to understand everything it did. It was good. I slowly started trusting it. Now I don't want to let it touch my project again.

It's extremely depressing because this is my hobby and I was having such a blast coding with Claude. I even started trying to use it to pivot to professional work. Now I'm not sure anymore. People who depend on this to make a living must be very angry indeed.

New comment by matheusmoreira in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

matheusmoreira — Tue, 07 Apr 2026 03:14:32 +0000

I just asked Claude to plan out and implement syntactic improvements for my static site generator. I used plan mode with Opus 4.6 max effort. After over half an hour of thinking, it produced a very ad-hoc implementation with needless limitations instead of properly refactoring and rearchitecting things. I had to specifically prompt it in order to get it to do better. This executed at around 3 AM UTC, as far away from peak hours as it gets.

b9cd0319-0cc7-4548-bd8a-3219ede3393a

> You're right to push back. Let me be honest about both questions.

> The @() implementation is ad-hoc

> The current implementation manually emits synthetic tokens — tag, start-attributes, attribute, end-attributes, text, end-interpolation — in sequence.

> This works, but it duplicates what the child lexer already does for #[...], creating two divergent code paths for the same conceptual operation (inline element emission). It also means @() link text can't contain nested inline elements, while #[a(...) text with #[em emphasis]] can.

I just feel like I can't trust it anymore.