Hacker News: fullstackwife

New comment by fullstackwife in "OpenCiv3: Open-source, cross-platform reimagining of Civilization III"

fullstackwife — Sat, 07 Feb 2026 07:25:45 +0000

Why not build it as a web app and play via browser?

New comment by fullstackwife in "Ask HN: How to avoid skill atrophy in LLM-assisted programming era?"

fullstackwife — Tue, 27 Jan 2026 20:05:25 +0000

Your technical skills are shaped by market demand, and they always have been.

New comment by fullstackwife in "Open Chaos: A self-evolving open-source project"

fullstackwife — Sat, 10 Jan 2026 20:28:36 +0000

Should votes get invalidated after major change in the ongoing PR?

New comment by fullstackwife in "AI employees don't pay taxes"

fullstackwife — Tue, 30 Dec 2025 00:04:26 +0000

for example driverless taxis, which is an application of AI that most of us really want

New comment by fullstackwife in "AI employees don't pay taxes"

fullstackwife — Mon, 29 Dec 2025 23:45:31 +0000

Since when "AI" exclusively implies LLMs only?

New comment by fullstackwife in "Gemini 3 Flash: Frontier intelligence built for speed"

fullstackwife — Wed, 17 Dec 2025 16:51:41 +0000

cost of e2e task resolution should be cheaper, even if single inference cost is higher, you need fewer loops to solve a problem now

New comment by fullstackwife in "Has the cost of building software dropped 90%?"

fullstackwife — Mon, 08 Dec 2025 22:28:21 +0000

human process is the understanding that the mistakes will make people die

New comment by fullstackwife in "Has the cost of building software dropped 90%?"

fullstackwife — Mon, 08 Dec 2025 22:13:32 +0000

yeah, in practice: would you like to onboard a Boeing 747 where some of the bugs were patched by some agents,

what is the percentage risk of malfunction you are going to accept as a passenger?

New comment by fullstackwife in "Ask HN: What has been your experience with Agentic Coding?"

fullstackwife — Tue, 02 Dec 2025 22:34:36 +0000

What works: delegating non ambiguous tasks, let them happen in async, while supported by harness of preexisting automated tests, and established project conventions

What does NOT work: I have no idea how to do sth, and I hope agentic coding will solve my problem.

Think "Eisenhower matrix":

- X: Ambigous <-> Trivial

- Y: Can wait <-> Urgent

Urgent&Ambigous => Agentic Coding is useless, and an act of desperation

Can wait and at least non amibogus => Agentic Coding is perfect fit

New comment by fullstackwife in "How I influence tech company politics as a staff software engineer"

fullstackwife — Sat, 04 Oct 2025 19:42:23 +0000

Think chefs at top restaurants for example: washing hands is something obvious, no need to get any customer infected with fecal bacteria in order to convince the restaurant management for investing into soap (hygiene takes time, you could serve additional customer!)

It is one of career progression milestones for a programmer when they can set a bar for their craftsmanship themselves. Successful SWE is someone who got hired at a team which does not require this kind of education. A team where this type of engineering hygiene is obvious like breathing.

New comment by fullstackwife in "Things managers do that leaders never would"

fullstackwife — Sat, 20 Sep 2025 05:58:32 +0000

Argumentum ad hominem - seriously, team! we can do better than that!

New comment by fullstackwife in "AI models need a virtual machine"

fullstackwife — Sat, 30 Aug 2025 19:22:23 +0000

"Workflow" is the aspect we should try to eliminate, and a LLM+VM combo allows you to do that. Workflow means you provide tools to the LLM, and ask to make use of them to achieve the goal. This works well already, but it fails whenever an unusual problem appears that is not covered by your predefined set of tools. Another issue is that the workflow based approach is always linear even if it is a DAG, or even if you have some kind of loop.

The next step is to not provide any tools to the LLM, and ask it to invent them on-the-fly. Some problems need to be brute-forced.

New comment by fullstackwife in "Ask HN: Do You Believe in Aliens?"

fullstackwife — Wed, 27 Aug 2025 07:05:31 +0000

Just thinking opposite direction: if you were to spawn a new planet with life somewhere in the universe, how would you do that? Micro manage every detail, or rather prepare proper conditions, and see what happens? Wouldn't the "proper conditions" eventually look like series of coincidences?

New comment by fullstackwife in "MCP Gateway and Registry"

fullstackwife — Mon, 25 Aug 2025 08:12:03 +0000

For many years we were fine with running DLLs, Java .class deps, npm modules, brew packages etc. why do you think we need so much isolation for left-pad class mcp tools?

New comment by fullstackwife in "How to build a coding agent"

fullstackwife — Sun, 24 Aug 2025 09:11:10 +0000

Exactly my approach to gaining knowledge and learning through building your own(`npx genaicode`). When I was presenting my work on a local meetup I got this exact question: "why u building this instead of just using Cursor". The answer is explained in this article(tl;dr; transformative experience), even though some parts of it are already outdated or will be outdated very soon as the technology is making progress every day.

New comment by fullstackwife in "Solution for Managing LLM Prompts"

fullstackwife — Sun, 17 Aug 2025 19:51:06 +0000

This is a very fast moving environment, my prompts from 2024 were created for that reality, and should be removed later in 2025. For example all the CoT techniques are anachronic now. But this also means a new architecture of the surrounding app, for example instead of chat UX we want to have more of async processing, when the focus is to do the job correctly instead of responding to the user with some message.

So the solution is to assume that at some point we will need a major rewrite, because current architecture does not allow us to make use of the modern model potential, and modifying prompts is not enough.

New comment by fullstackwife in "Claudia – Desktop companion for Claude code"

fullstackwife — Sun, 17 Aug 2025 19:47:30 +0000

Video promises what it should: a dopamine shot!

New comment by fullstackwife in "Ask HN: What are you working on this weekend?"

fullstackwife — Sat, 09 Aug 2025 12:47:45 +0000

Using GH Copilot Agent to vibe code a LLM+Docker omnitool for my coding assistant: https://github.com/gtanczyk/genaicode/pull/25

The idea is to give it a task, let it do whatever it decides and expect to produce a result *inside container*. I'm still exploring this idea whether it makes sense, and is cost effective.

New comment by fullstackwife in "Cursor CLI"

fullstackwife — Thu, 07 Aug 2025 22:42:58 +0000

The concept of JS framework which allows you to rapidly develop an app has the same underlying vibe as coding agent

New comment by fullstackwife in "GPT-5"

fullstackwife — Thu, 07 Aug 2025 17:17:03 +0000

Does that even work? it required passport, personal details, what else?