Hacker News: sturza

New comment by sturza in "The founder's playbook: Building an AI-native startup"

sturza — Wed, 17 Jun 2026 12:52:26 +0000

The difference is the destination. Me crunching code with llms vs you doing the same thing will lead both of us to different places(let’s say equally fast for the sake of the conversation). What will set us apart in the end is who will actually sell it, and that’s llm-independent.

New comment by sturza in "The founder's playbook: Building an AI-native startup"

sturza — Wed, 17 Jun 2026 08:32:36 +0000

“everyone”. it’s there, it’s accessible, it’s “cheap”. acceleration will depend on the operator capability. if the final product will make a diff in the real world, it will ALWAYS depend on the entrepreneur, not the tools used.

New comment by sturza in "The founder's playbook: Building an AI-native startup"

sturza — Wed, 17 Jun 2026 08:18:54 +0000

Assumption: now everyone can do more of the above. The final line is still selling. So everyone will get to the sales part, FASTER. Triage will still happen at this stage, regardless of AI. You won’t be able to avoid this triage, regardless of how fast you get there.

Double your Codex / Claude Code productivity and output

sturza — Sun, 14 Jun 2026 12:30:40 +0000

Article URL: https://github.com/tanweai/pua

Comments URL: https://news.ycombinator.com/item?id=48526597

Points: 3

# Comments: 0

New comment by sturza in "The Eternal Sloptember"

sturza — Mon, 25 May 2026 04:40:19 +0000

What i meant was: your experience might not be representative of the coding models capabilities. At least based on the poor examples in the post, you’re just scratching the surface of learning how to extract value from them, and, as i understand, you gave up and shared your experience. Given that you fully understand how an LLM works(and you do) it might also be that you’re using it outside training data. Not all code is equally represented(quality/quantity) in the training data, like there’s not the same amount of latin text as opposed to english text there(it’s all gravy to an LLM). You also suggested that manual might be faster and better quality - in MY experience, this is just you (using search through prompts), using it wrong.

Edit: added gravy pun

New comment by sturza in "The Eternal Sloptember"

sturza — Sun, 24 May 2026 19:36:36 +0000

You're using it wrong.

Tell HN: I found the perfect way to get maximum Claude Code quality

sturza — Fri, 17 Apr 2026 08:11:48 +0000

I always ask in the prompt: "don't use subagents". It's slower, but better quality. Opus is set to max effort. I ask Codex to eval, and it finds significantly less shit.

Comments URL: https://news.ycombinator.com/item?id=47803611

Points: 2

# Comments: 0

New comment by sturza in "Ask HN: Should AI credits be refunded on mistakes?"

sturza — Wed, 08 Apr 2026 11:29:41 +0000

Do you pay your employer when you introduce bugs? I think you're lucky if you get usable output which you don't consider a mistake. Also, you might be mistaken if you think that you pay for a deterministic service.

edit: typo

New comment by sturza in "I replaced grep-based code exploration with a knowledge graph – 10x less token"

sturza — Tue, 03 Mar 2026 16:17:39 +0000

Any accuracy measurements?

New comment by sturza in "iOS 27 'Rave' Update to Clean Up Code, Could Boost Battery Life"

sturza — Mon, 16 Feb 2026 15:32:46 +0000

I'm sticking with Sonoma as long as they still provide security updates, then i go +1, hoping to skip the whole liquid glass phase.

Craft Agents - Work with agents, with the UX they deserve

sturza — Mon, 02 Feb 2026 08:51:52 +0000

Article URL: https://agents.craft.do

Comments URL: https://news.ycombinator.com/item?id=46853843

Points: 4

# Comments: 1

New comment by sturza in "Formula One Handovers and Handovers From Surgery to Intensive Care (2008) [pdf]"

sturza — Sat, 13 Dec 2025 09:03:00 +0000

It was an anecdote or a story shared on HN eariler this year.

New comment by sturza in "How do solo founders get their first pilot users for a complex B2B product?"

sturza — Tue, 09 Dec 2025 21:15:05 +0000

If you built it FOR someone(a business), you are already on the wrong path. You should have built it WITH someone(a business) and you'd already have feedback and real world usage. Maybe next time around start with a real problem (confirmed by a business) rather than how you want the world to work.

New comment by sturza in "Signal knows who you're talking to (2023)"

sturza — Sun, 23 Nov 2025 10:50:39 +0000

The critique of metadata being hard is fair, the claim that sealed sender is “totally useless” is not. It’s a small, incremental hardening step in a very messy design space, not a magic invisibility cloak, and judging it as the latter sets the bar unrealistically high for anything that still wants to be a drop-in WhatsApp replacement.

New comment by sturza in "Cognitive and mental health correlates of short-form video use"

sturza — Wed, 19 Nov 2025 21:02:52 +0000

attention is all they want

New comment by sturza in "Why movies just don't feel "real" anymore"

sturza — Mon, 17 Nov 2025 06:55:55 +0000

It's about the new trend of shallow DoF in new movies vs old ones.

Gemini 3

sturza — Thu, 13 Nov 2025 15:46:44 +0000

Article URL: https://twitter.com/patelnamra573/status/1988951796442862017

Comments URL: https://news.ycombinator.com/item?id=45916270

Points: 2

# Comments: 0

New comment by sturza in "WriterdeckOS"

sturza — Sun, 09 Nov 2025 08:32:43 +0000

I use a regular 3kg 17” macbook pro from ~2007. Beautiful keyboard, good enough resolution, wifi off(not much use on the internet anyway). Still modern ux and good trackpad.

New comment by sturza in "Ask HN: What made you become an IT/programmer?"

sturza — Fri, 05 Sep 2025 06:15:35 +0000

The original iPhone.

New comment by sturza in "Ask HN: How much are you guys paying for AI coding tools monthly?"

sturza — Mon, 01 Sep 2025 12:01:29 +0000

100-700$. more when actively building, less when maintaining.