Hacker News: tomashubelbauer

New comment by tomashubelbauer in "Singapore introduces caning for boys who bully others at school"

tomashubelbauer — Fri, 08 May 2026 11:33:34 +0000

I googled this and I didn't even have to scroll the search results before I found an article about a perverted teacher abusing a teenager this way.

New comment by tomashubelbauer in "Ask HN: How much trouble do you have with GitHub?"

tomashubelbauer — Wed, 06 May 2026 16:53:19 +0000

I stopped checking failure emails from GitHub Actions unless they happens half a dozen times or so a day because I get more false negatives (GitHub Actions issue not my workflow issue) than legitimate notifications I can act on. I'm from Europe too.

New comment by tomashubelbauer in "Mozilla's opposition to Chrome's Prompt API"

tomashubelbauer — Thu, 30 Apr 2026 10:45:33 +0000

IME young people mostly hate AI.

New comment by tomashubelbauer in "Website streamed live directly from a model"

tomashubelbauer — Wed, 22 Apr 2026 20:56:00 +0000

I asked it about designing a 12 V solar system for a garden shed and it got everything but the broadest of strokes wrong. It figured out there should be a solar panel, a solar charge controller, a battery and some loads, but the wiring was non-sensical and when I drilled in on the solar charge controller settings etc. it completely fell apart. Absolute non-starter for any information you plan on depending on, but good entertainment value and impressive execution.

New comment by tomashubelbauer in "I ported Mac OS X to the Nintendo Wii"

tomashubelbauer — Thu, 09 Apr 2026 08:57:08 +0000

Which was very cool and accessible as a kid, I have fond memories of it.

New comment by tomashubelbauer in "Ollama is now powered by MLX on Apple Silicon in preview"

tomashubelbauer — Tue, 31 Mar 2026 07:46:16 +0000

I'd like to coin the term "user agent" for this

New comment by tomashubelbauer in "It took four years until 2011’s iOS 5 gave everyone an emoji keyboard"

tomashubelbauer — Fri, 06 Mar 2026 17:08:07 +0000

Decorative emojis in headings and lists help me skim documents faster than I'd otherwise be able to.

New comment by tomashubelbauer in "Google Workspace CLI"

tomashubelbauer — Thu, 05 Mar 2026 12:19:20 +0000

Same story here, I installed it and ran `gwc auth setup` only to find I needed to install a `gloud` CLI by hand. That led me to this link with install instructions: https://cloud.google.com/sdk/docs/install. Unmistakeable Google DX strikes again.

New comment by tomashubelbauer in "Decision trees – the unreasonable power of nested decision rules"

tomashubelbauer — Sun, 01 Mar 2026 11:57:41 +0000

Made me think of https://github.com/xoreaxeaxeax/movfuscator. Would be definitely cool to see it realized even if it would be incredibly impractical (probably).

New comment by tomashubelbauer in "Claude Code Remote Control"

tomashubelbauer — Wed, 25 Feb 2026 15:13:52 +0000

In theory, comments on Hacker News should advance discussion and meet a certain quality bar lest they be downvoted to make room for the ones that meet the criteria. I am not sure if this ever was true in practice, it certainly seems to have waned in the years I have been a reader of this forum (see one of the many pelican on a bike comments on any AI model release thread), but I'd expect some people still try to vote with this in mind.

Being sarcastic doesn't lower the bar for a comment to meet to not get downvoted, so I wouldn't go thinking people miss the sarcasm without first considering whether the comment adds to the discussion when wondering why a comment is downvoted.

New comment by tomashubelbauer in "Pi – A minimal terminal coding harness"

tomashubelbauer — Wed, 25 Feb 2026 14:19:10 +0000

IME CLAUDE.md rarely gets fully honored. I've left HN comments before about how I had to convert some CLAUDE.md instructions to pre-commit deterministic checks due to how often they were ignored. My guesstimate is that it is about 70 % reliable. That's with Opus 4.5. I've since switched to GPT-5.2 and now GPT-5.3 Codex and use Codex CLI, Pi and OpenCode, not CC, so maybe things have changed with a new system prompt or with the introduction of Opus 4.6.

New comment by tomashubelbauer in "Claude Code Remote Control"

tomashubelbauer — Wed, 25 Feb 2026 12:54:18 +0000

TIL that HA notifications can have associated actions. I have the exact same setup as you, except I only receive the notification and then walk over to the laptop to unblock the agent feeling like a human tool call. This will improve my workflow, thank you.

New comment by tomashubelbauer in "Pi – A minimal terminal coding harness"

tomashubelbauer — Wed, 25 Feb 2026 09:13:37 +0000

Not the person you replied to, but I'll stress the point that it is not just what you can add that Claude Code doesn't offer, but also what you don't need to add that Claude Code does offer that you don't want.

I dislike many things about Claude Code, but I'll pick subagents as one example. Don't want to use them? Tough luck. (AFAIK, it's been a while since I used CC, maybe it is configurable now or was always and I never discovered that.)

With Pi, I just didn't install an extension for that, which I suspect exists, but I have a choice of never finding out.

New comment by tomashubelbauer in "The JavaScript Oxidation Compiler"

tomashubelbauer — Mon, 23 Feb 2026 10:28:09 +0000

> running oxfmt without any arguments recursively scans directory tree from the current directory for all .js and .ts files and silently reformats them

I've got to say this is what I would have expected and wanted to happen. I'd say it is wise to not run tools designed to edit files on files you don't have a backup for (like Git) without doing a dry-run or a small scope experiment first.

New comment by tomashubelbauer in "Claws are now a new layer on top of LLM agents"

tomashubelbauer — Sat, 21 Feb 2026 18:28:25 +0000

I also built the equivalent of OpenClaw myself sometime when it was still called Clawdbot and I'm confused how LLMs can be both heralds of the era of personal apps and everyone at the same time be using the same vibe coded personal LLM assistant someone else made, much less it being worth an OpenAI acquisition. I agree building one yourself is very fun.

New comment by tomashubelbauer in "Evaluating AGENTS.md: are they helpful for coding agents?"

tomashubelbauer — Tue, 17 Feb 2026 08:14:30 +0000

Just this morning I have run across an even narrower case of how AGENTS.md (in this case with GPT-5.3 Codex) can be completely ignored even if filled with explicit instructions.

I have a line there that says Codex should never use Node APIs where Bun APIs exist for the same thing. Routinely, Claude Code and now Codex would ignore this.

I just replaced that rule with a TypeScript-compiler-powered AST based deterministic rule. Now the agent can attempt to commit code with banned Node API usage and the pre-commit script will fail, so it is forced to get it right.

I've found myself migrating more and more of my AGENTS.md instructions to compiler-based checks like these - where possible. I feel as though this shouldn't be needed if the models were good, but it seems to be and I guess the deterministic nature of these checks is better than relying on the LLM's questionable respect of the rules.

New comment by tomashubelbauer in "uBlock filter list to hide all YouTube Shorts"

tomashubelbauer — Sat, 14 Feb 2026 23:33:21 +0000

I'm disappointed that even Signal does this when asking you for access to your contacts.

New comment by tomashubelbauer in "GPT-5.3-Codex"

tomashubelbauer — Thu, 05 Feb 2026 18:41:10 +0000

I agree, I was confused about where 5.3 non Codex was. 5.2-Codex disappointed me enough that I won't be giving 5.3 Codex a try, but I'm looking forward to trying 5.3 non Codex with Pi.

New comment by tomashubelbauer in "The Codex App"

tomashubelbauer — Wed, 04 Feb 2026 08:48:10 +0000

Yeah I meant it more like it is not intuitive to my why OpenAI would fumble it this hard. They have got to have tested it internally and seen that it sucked, especially compared to GPT-5.2

New comment by tomashubelbauer in "Qwen3-Coder-Next"

tomashubelbauer — Tue, 03 Feb 2026 19:55:04 +0000

It sucks and I wish it were different, but it is not so different from trying to get support at Meta or Google. If I was an AI grifter I could probably just DM a person on Twitter and get this sorted, but as a paying customer, it's wisest to go where they actually want my money.