Hacker News: bontaq

New comment by bontaq in "GLM 5.2 Is Out"

bontaq — Sat, 13 Jun 2026 17:16:53 +0000

I think Z.ai rushed a bit for release, for example GLM 5.2 is only available under the coding plan right now and they didn't do a big write up. Not even some charts and graphs about its performance!

This is around when people were predicting a new GLM to come out, so a couple corners clipped in order to catch the moment. I'm using it right now and it seems decent, but I haven't done heavy work with it yet. The expanded context window is great.

New comment by bontaq in "Every Frame Perfect"

bontaq — Sat, 13 Jun 2026 16:51:00 +0000

Starting from a literal bandwidth costs perspective definitely won't get you there. I'd start by trying to feel personally annoyed by things like that. Then maybe try to feel more annoyed, since you know it'll touch every customer forever.

In that bandwidth case I'd be annoyed by the waste which kind of pervades software already, and it'd feel great to know at least we countered it a little bit.

New comment by bontaq in "Ask HN: Why is the HN crowd so anti-AI?"

bontaq — Sat, 06 Jun 2026 07:33:20 +0000

That's well said and where I ended up as well. This whole thing did reveal that a lot of people really never enjoyed programming at all and only saw it as some irritating necessity. I don't really like that crowds presumption that everyone else disliked it too.

For me working through the programming part is the understanding and solving. Programming languages are pretty beautiful and encourage different ways of thinking. Hopefully we can understand it and contribute.

New comment by bontaq in "Claude for Small Business"

bontaq — Thu, 14 May 2026 04:33:03 +0000

It's a fascinating angle they've taken to give Claude your payroll. I guess we've reached this part of the AI race and they're running ahead of people realizing what it can do.

New comment by bontaq in "If AI writes your code, why use Python?"

bontaq — Tue, 12 May 2026 05:27:36 +0000

LLMs get ridiculous with elixir, especially with the repl, runtime, and ability to hot reload / directly test functions. It's really surprising to me it hasn't caught on more but I guess you have to see it to believe it.

New comment by bontaq in "The West forgot how to make things, now it’s forgetting how to code"

bontaq — Sun, 26 Apr 2026 14:19:23 +0000

This is a funny point. People don't want to read LLM code either, so who knows where that puts us.

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

bontaq — Fri, 24 Apr 2026 04:13:48 +0000

If there was an exponential cost, I would expect to see some sort of pricing based on that. I would also expect to see it taking exponentially longer to process a prompt. I don't believe LLMs work like that. The "scary quadratic" referenced in what you linked seems to be pointing out that cache reads increase as your conversation continues?

If I'm running a database keeping track of a conversation, and each time it writes the entire history of the conversation instead of appending a message, are we calling that O(N^2) now?

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

bontaq — Thu, 23 Apr 2026 22:08:49 +0000

How's that O(N^2)? How's it O(N) with caching? Does a 3 turn conversation cost 3 times as much with no caching, or 9 times as much?

New comment by bontaq in "If America's so rich, how'd it get so sad?"

bontaq — Thu, 23 Apr 2026 19:06:07 +0000

My mom said, "whatever we built isn't working anymore," and I think that captures most of the sentiment. It's also funny to see the "the economy is roaring!" "incomes are up!". Great, have they increased by as much as inflation? Can I afford a home?

Work has if anything gotten worse in general. Remote's gone. Pay's less. ADHD maximum AI use required. Nobody can take a break. Pressure's on. 1.5 trillion more to the military. What are we even building? For what?

Is it any wonder at all?

New comment by bontaq in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

bontaq — Sat, 04 Apr 2026 00:06:08 +0000

This is my big question too. It seems by intent it's to kill it, including ACP, but I don't know.

New comment by bontaq in "Goodbye to Sora"

bontaq — Tue, 24 Mar 2026 23:17:30 +0000

Dunno, from the WSJ scoop: "CEO Sam Altman announced the changes to staff on Tuesday, writing that the company would wind down products that use its video models. In addition to the consumer app, OpenAI is also discontinuing a version of Sora for developers and won’t support video functionality inside ChatGPT, either."

https://www.wsj.com/tech/ai/openai-set-to-discontinue-sora-v...

https://archive.ph/cKWkf#selection-907.0-907.291

New comment by bontaq in "Anthropic bans OAuth tokens (including Agent SDK) in 3P tools"

bontaq — Wed, 18 Feb 2026 19:45:08 +0000

I don't get it, now I can't use Tidewave or Zed or Agent Shell in Emacs with my Claude Code plan? Why would they do this? It makes my subscription so much less worthwhile.

New comment by bontaq in "Predicting OpenAI's ad strategy"

bontaq — Mon, 19 Jan 2026 04:45:12 +0000

More than an extension, imagine us having good enough, fast enough, vision models that you never even see a real website. Maybe the whole OS in Microsoft's case if they keep putting more ads in. It will be a level of inefficiency inconceivable but really something.

New comment by bontaq in "Please just try HTMX"

bontaq — Thu, 18 Dec 2025 16:23:38 +0000

I'm a big fan of it for building micro websites with LLMs, since it can keep pretty much the entire thing in context (even including the docs) it seems to perform pretty well.

New comment by bontaq in "Ask HN: Builders vs. Mercenaries – does this distinction make sense?"

bontaq — Thu, 20 Nov 2025 07:17:17 +0000

I'd say you identified a difference with modern names. This split has certainly grown wider in the "code is cheap" AI era and changed meaning.

I'm firmly in the camp of actually enjoying programming. To me it was interesting to hear that some people actually don't like it all, and it's much nicer to have something "just do it".

Over my career I've leant much more heavily into programming as the art.

I wouldn't even say "how do you balance" is too much of a problem, as we all can vary between needs, you know?

New comment by bontaq in "Show HN: I Built an Animated UI Library for React Lovers"

bontaq — Thu, 20 Nov 2025 06:00:25 +0000

Sorry, but there's some things you could do better:

- display the components in a clean way on landing

- a landing that asks to pay without seeing anything does not make sense

- 25% conversion boost is meaningless

- absolute nonsense with a free 107 page ebook

New comment by bontaq in "Ask HN: What are some modern technologies that you refuse to adopt?"

bontaq — Thu, 20 Nov 2025 05:30:40 +0000

Any new editor, airplanes, tablets, smart watches (as mentioned by catstor), VR, e-readers (though these are actually very good, mine just died).

It's not any particular reason, they don't seem to improve my life much? The e-reader was best for sure.

New comment by bontaq in "Building more with GPT-5.1-Codex-Max"

bontaq — Thu, 20 Nov 2025 04:35:14 +0000

I've found really hammering it with *important*, all caps, "NEVER", etc finally made it start using the tidewave MCP for elixir development well. It felt really heavy handed but it worked.

For an idea of how heavy handed it was, this is my claude.md (with some explanatory text before): https://gist.github.com/bontaq/77b56d90b30e29c84c53c86d7fe05...

New comment by bontaq in "Workday to acquire Pipedream"

bontaq — Thu, 20 Nov 2025 04:25:56 +0000

I really hope they remain open source, but overall this seems like a bad sign

New comment by bontaq in "Measuring political bias in Claude"

bontaq — Thu, 20 Nov 2025 04:24:13 +0000

mostly sys admin things but yeah