Hacker News: bontaq

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

New comment by bontaq in "Ask HN: What Are You Working On? (Nov 2025)"

bontaq — Mon, 10 Nov 2025 00:32:09 +0000

I'm working on an AI-controlled VPS. It makes a lot of sense to let them run with full permissions.

https://www.zo.computer/

New comment by bontaq in "Claude Code can debug low-level cryptography"

bontaq — Sun, 02 Nov 2025 20:15:58 +0000

I would say a lot of people are only posting their positive experiences. Stating negative things about AI is mildly career-dangerous at the moment where as the opposite looks good. I found the results from using it on a complicated code base are similar to yours, but it is very good at slapping things on until it works.

If you're not watching it like a hawk it will solve a problem in a way that is inconsistent and, importantly, not integrated into the system. Which makes sense, it's been trained to generate code, and it will.

New comment by bontaq in "AI Startup Founders Tout a Winning Formula–No Booze, No Sleep, No Fun"

bontaq — Mon, 15 Sep 2025 01:47:13 +0000

As far as I could tell, by reading the article, it is supposed the be culture of the company. The culture of the company of course applies to people they hire. Do you understand that?

New comment by bontaq in "AI Startup Founders Tout a Winning Formula–No Booze, No Sleep, No Fun"

bontaq — Fri, 12 Sep 2025 13:38:28 +0000

Seems generally worse for the world if we want to force everyone to work 24/7 with no joy or interests outside of work. Ah well. Do you think they can recognize it? I don't think any of these companies will have anything interesting to say, last ten years, or improve lives.

It mostly looks like an act to me, a cargo cult where if they offer up enough "work" they'll be rewarded, disregarding any usefulness.

New comment by bontaq in "Avoiding skill atrophy in the age of AI"

bontaq — Sat, 26 Apr 2025 20:29:20 +0000

I imagine one'd have much more time to create things that matter to them as well, or at least the option to pursue such things. Kind of an odd potshot on op's part.

New comment by bontaq in "Functors, Applicatives, and Monads"

bontaq — Sun, 30 Mar 2025 21:39:11 +0000

I've seen this opinion before but disagree with it. There are maybe five names to learn. They relate to the actual concepts, allowing you to expand your knowledge.

New comment by bontaq in "Maybe This Is Too Cool"

bontaq — Fri, 31 May 2024 11:53:54 +0000

Strange, it was at the top of mine and now I don't see it on the first five pages. Guess it got evaporated.

New comment by bontaq in "Labor unions are pushing hard for better pay and hours – and winning"

bontaq — Sun, 27 Aug 2023 22:43:49 +0000

The part I've been trying to explain to coworkers is that the union isn't just for software engineers at the company, but for the support staff as well. We have it good but I have seen support and sales staff get bullied pretty hard.

Sure you might not even get a raise with a union, but perhaps those same benefits of remote work when needed, unlimited vacation, and an hour lunch can be extended to every worker at the company.

The most expensive workers teaming up with the least expensive to give them more power is a good thing, I think.

New comment by bontaq in "We can't all use AI. Someone has to generate the training data"

bontaq — Wed, 15 Mar 2023 07:32:55 +0000

This is entirely my thesis on why they'll win. Of course google wishes they could ignore all attribution.

They are slighting the law just like airbnb and uber did. They offer a better form of consumption. This is disruption at it's finest, and it will be in the courts forever.