Hacker News: golergka

New comment by golergka in "If you thought the code writing speed was your problem; you have bigger problems"

golergka — Tue, 17 Mar 2026 19:53:32 +0000

attempt != release to customer

when you're building a feature and have different ideas how to go about it, it's incredibly valuable to build them all, compare, and then build another, clean implementation based on all the insights

I used to do it before, but pretty rarely, only for the most important stuff. now I do it for basically everything. and while 2-4 agents are working on building these options, I have time to work on something else.

New comment by golergka in "Launch HN: Voygr (YC W26) – A better maps API for agents and AI apps"

golergka — Tue, 17 Mar 2026 01:01:07 +0000

what's your plan to get all this data and maintain it?

New comment by golergka in "Apideck CLI – An AI-agent interface with much lower context consumption than MCP"

golergka — Tue, 17 Mar 2026 00:58:01 +0000

it's not about the tokens. agents can script clis.

New comment by golergka in "GitHub should charge everyone $1 more per month to fund open source"

golergka — Thu, 15 Jan 2026 04:39:47 +0000

> Imagine the incredible programs, websites, games, crafts, artworks, animations, performances, literature, journalism, hobby clubs, support groups, community organizations that would spring into existence if we all just had more bandwidth for them while having our baseline needs met.

If people find these things useful, they can actually pay for them. If you can't find people who value it enough to pay for it, then may be it's not as valuable as you think it is.

New comment by golergka in "If AI replaces workers, should it also pay taxes?"

golergka — Mon, 15 Dec 2025 18:22:46 +0000

Most of the capital is owned (through pension funds and then different investment funds) by completely ordinary people who put their completely ordinary savings into it and get completely ordinary pensions out of it.

So you are effectively suggesting to forcibly take their money from them and then give it back, but through a corrupt and bureaucratic system of the state.

New comment by golergka in "Bringing Sexy Back. Internet surveillance has killed eroticism"

golergka — Sat, 29 Nov 2025 03:57:37 +0000

CEO profession is a magnet for male psychopaths, and social worker for female ones.

New comment by golergka in "We're losing our voice to LLMs"

golergka — Thu, 27 Nov 2025 19:39:46 +0000

Anything you could automate you could do yourself. What’s the benefit?

New comment by golergka in "Google Antigravity"

golergka — Tue, 18 Nov 2025 17:22:32 +0000

As somebody who worked on two IDEs which didn't fork VSCode but still used Monaco for code editing views, I think forking VSCode is almost always the right solutions for a new IDE. You get extensions, familiarity and most importantly, don't waste valuable time on the boring stuff which VSCode has already implemented.

Nothing bad with using code other people made open. Our whole industry is built on this.

New comment by golergka in "OpenAI says over a million people talk to ChatGPT about suicide weekly"

golergka — Wed, 29 Oct 2025 00:59:37 +0000

Obsidian.

New comment by golergka in "OpenAI says over a million people talk to ChatGPT about suicide weekly"

golergka — Tue, 28 Oct 2025 04:15:24 +0000

ChatGPT/Claude can be absolutely brilliant in supportive, every day therapy, in my experience. BUT there are few caveats: I'm in therapy for a long time already (500+ hours), I don't trust it with important judgements or advice that goes counter to what I or my therapists think, and I also give Claude access to my diary with MCP, which makes it much better at figuring the context of what I'm talking about.

Also, please keep in mind "supportive, every day". It's talking through stuff that I already know about, not seeking some new insights and revelations. Just shooting the shit with an entity which is booted with well defined ideas from you, your real human therapist and can give you very predictable, just common sense reactions that can still help when it's 2am and you have nobody to talk to, and all of your friends have already heard this exact talk about these exact problems 10 times already.

New comment by golergka in "Andrej Karpathy – It will take a decade to work through the issues with agents"

golergka — Sat, 18 Oct 2025 04:42:55 +0000

Wha if you asked the blind man to play the role of helpful assistant

New comment by golergka in "Ireland is making basic income for artists program permanent"

golergka — Wed, 15 Oct 2025 19:08:38 +0000

So effectively what you're saying is that institutions are willing to reward her with attention, but people are not willing to pay for her art after all?

New comment by golergka in "Apple Vision Pro upgraded with M5 chip"

golergka — Wed, 15 Oct 2025 18:22:49 +0000

Looks like this version finally works like an ultrawide external monitor.

New comment by golergka in "Claude Code 2.0"

golergka — Tue, 30 Sep 2025 02:25:55 +0000

Especially when you work with a language where an unfinished refactoring with give you the type error.

New comment by golergka in "Ishkur's Guide to Electronic Music"

golergka — Sun, 28 Sep 2025 05:53:16 +0000

As a DJ, the endgame is building a set from a variety of different kinds of music which still sounds great together but doesn’t all follow the same boring formula. And it’s pretty great.

New comment by golergka in "A shift in developer culture is impacting innovation and creativity"

golergka — Fri, 19 Sep 2025 18:18:02 +0000

Ironically, LLMs are exactly what drives a lot of curiosity and learning without a purpose. I see it all the time on twitter — people getting chatbots into weird mental states, toying around with different systems on top of them, jailbreaking. More for the fun of the game than anything else.

You can't keep that curiosity and at the same time see one of the most wonderful and awe-inspiring technologies of the last decades as something threatening.

New comment by golergka in "Using Claude Code SDK to reduce E2E test time"

golergka — Tue, 09 Sep 2025 16:49:32 +0000

Just run them on every commit in develop branch after the PR is merged. Then you can always roll back or revert the merge and leave it to the PR author to fix it.

New comment by golergka in "Using Claude Code SDK to reduce E2E test time"

golergka — Sat, 06 Sep 2025 19:01:24 +0000

All E2E tests should run before deploy. Probably on every commit on develop branch, even. But there really is no need to run all E2E suite on every PR. In this case, the failure mode of this system, where PR automation failed to flag a breakage, is acceptable if it’s rare enough, so probabilistic solutions are OK.

New comment by golergka in "Why Everybody Is Losing Money On AI"

golergka — Fri, 05 Sep 2025 17:29:41 +0000

> OpenAI spent 50% of its revenue on inference compute costs alone

This means that they operate existing models with very healthy 50% profit margin, that’s excellent unit economics actually. Losing money by investing more into R&D that you make is not the same as burning it by selling a dollar for 90 cents.

Allegation: I had sex with Y while she was intoxicated

golergka — Thu, 04 Sep 2025 18:02:24 +0000

Article URL: https://pretty.direct/alcohol

Comments URL: https://news.ycombinator.com/item?id=45130230

Points: 6

# Comments: 3