Hacker News: cageface

New comment by cageface in "Actively exploited sandbox RCE in all Chromium versions"

cageface — Sun, 06 Sep 2026 00:42:44 +0000

Do you have any citations for this? Not that I doubt you but I’d like to read more about it.

New comment by cageface in "A week of using Codex more than Claude"

cageface — Sun, 23 Aug 2026 00:32:06 +0000

The new concise output style they just released definitely helps with Opus 5 in general.

New comment by cageface in "A week of using Codex more than Claude"

cageface — Sun, 23 Aug 2026 00:30:37 +0000

I’ve been getting good results from using Sol for planning and Luna for everything else. At current rates it barely scratches my weekly quota.

Makes me wonder if the current Luna prices are sustainable.

New comment by cageface in "Flutter 3.47"

cageface — Thu, 13 Aug 2026 06:59:15 +0000

Just my own apps. Getting good performance out of SwiftUI on Mac is quite difficult. Loads of footguns.

New comment by cageface in "Flutter 3.47"

cageface — Thu, 13 Aug 2026 00:55:49 +0000

I’ve had good experiences with Flutter too. It’s actually much easier to build a performant macOS app with flutter than with SwiftUI.

New comment by cageface in "App Store Rejection of the Week: Dark Hours"

cageface — Sat, 08 Aug 2026 00:28:59 +0000

This is true but if you want to monetize it then there are similar review hurdles you're going to have to clear.

New comment by cageface in "GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance"

cageface — Sun, 05 Jul 2026 06:52:19 +0000

Verified this locally myself. Thanks for the concrete test. I guess it's time to give Claude another try.

New comment by cageface in "An update on recent Claude Code quality reports"

cageface — Thu, 23 Apr 2026 22:42:27 +0000

Codex does better if you ask it to take screenshots and critique its own UI work and iterate. It rarely one-shots something I like but it can get there in steps.

New comment by cageface in "John Ternus to become Apple CEO"

cageface — Mon, 20 Apr 2026 23:12:58 +0000

In the US. In many other countries it's borderline useless.

New comment by cageface in "Thoughts and feelings around Claude Design"

cageface — Sun, 19 Apr 2026 02:21:04 +0000

LLMs tend to do better with component libraries like shadcn or daisy than writing raw CSS in my experience.

New comment by cageface in "Anonymous request-token comparisons from Opus 4.6 and Opus 4.7"

cageface — Sun, 19 Apr 2026 01:21:00 +0000

The pro plan is useless. You need at least the 5x max plan to get any real work done.

That said I find the GPT plans much better value.

New comment by cageface in "Android CLI: Build Android apps 3x faster using any agent"

cageface — Fri, 17 Apr 2026 08:39:38 +0000

If you think Android tooling is subpar wait until you try iOS.

New comment by cageface in "Claude Opus 4.7"

cageface — Fri, 17 Apr 2026 08:35:02 +0000

I've had exactly the opposite experience. Getting great results using GPT for hours every day since 5.3. You need to put the effort level on at least high though.

Every time I hand off a task to Opus to see if it's gotten better I'm disappointed. At least 4.7 seems to have realized I have skill files again though.

New comment by cageface in "Claude Opus 4.7"

cageface — Fri, 17 Apr 2026 08:29:35 +0000

On at least high effort level I find GPT 5.4 easily beats Opus 4.6 in code generation and debugging issues.

New comment by cageface in "What is jj and why should I care?"

cageface — Tue, 14 Apr 2026 15:06:40 +0000

Unless you need to work with a repo that uses submodules or lfs.

New comment by cageface in "How Google got its groove back and edged ahead of OpenAI"

cageface — Thu, 08 Jan 2026 11:56:03 +0000

That hasn’t been my experience. I agree Opus has the edge but it’s not by that much and I still sometimes get better results from Gemini, especially when debugging issues.

Claude Code is much better than Gemini CLI though.

New comment by cageface in "Why didn't AI “join the workforce” in 2025?"

cageface — Tue, 06 Jan 2026 14:09:34 +0000

I really don't know how effective LLMs are at that but also that puts you in an extremely narrow niche of development, so you should keep that in mind when making much more general claims about how useful they are.

New comment by cageface in "Why didn't AI “join the workforce” in 2025?"

cageface — Tue, 06 Jan 2026 14:05:45 +0000

Why is that the real metric? If you can turn a 1x dev into a 2x dev that's a huge deal, especially if you can also turn the original 2x dev into a 4x dev.

And far from "churning out code" my work is better with LLMs. Better tested, better documented, and better organized because now I can do refactors that just would have taken too much time before. And more performant too because I can explore more optimization paths than I had time to before.

Refusing to use LLMs now is like refusing to use compilers 20 years ago. It might be justified in some specific cases but it's a bad default stance.

New comment by cageface in "Why didn't AI “join the workforce” in 2025?"

cageface — Tue, 06 Jan 2026 12:22:40 +0000

C, Swift, Typescript, audio dsp, robotics etc.

People always want to claim what they’re doing is so complex and esoteric that AI can’t touch it. This is dangerous hubris.

New comment by cageface in "Why didn't AI “join the workforce” in 2025?"

cageface — Tue, 06 Jan 2026 10:00:22 +0000

The denial on this topic is genuinely surreal. I've knocked out entire features in a single prompt that took me days in the past.

I guess I should be happy that so many of my colleagues are willing to remove themselves from the competitive job pool with these kinds of attitudes.