Hacker News: keithnz

New comment by keithnz in "Microsoft hasn't had a coherent GUI strategy since Petzold"

keithnz — Mon, 06 Apr 2026 03:24:35 +0000

funny thing is, with AI, it's become really easy to put win32 apps together, and they load fast and are super responsive!

New comment by keithnz in "Ubuntu now requires more RAM than Windows 11"

keithnz — Sun, 05 Apr 2026 12:44:54 +0000

windows always optimistically loads a lot, almost no matter how much ram you have

New comment by keithnz in "NASA’s Artemis II Crew Launches to the Moon"

keithnz — Thu, 02 Apr 2026 00:54:13 +0000

given you are new, check out HNs guidelines https://news.ycombinator.com/newsguidelines.html

New comment by keithnz in "Do your own writing"

keithnz — Tue, 31 Mar 2026 01:03:14 +0000

I usually create a document/folder with my thinking on what I want to do, any background information that is relevant, conversations on the topic, technical manuals, links etc. Then enter a conversation and explore the problem space and do something very similar to what you are doing.

New comment by keithnz in "Do your own writing"

keithnz — Tue, 31 Mar 2026 00:57:33 +0000

not at all, it's very productive.

New comment by keithnz in "Do your own writing"

keithnz — Mon, 30 Mar 2026 20:01:13 +0000

I'm finding AI great to have a conversation with to flesh out ideas, with the added benefit it can summarize everything at the end

New comment by keithnz in "Take better notes, by hand"

keithnz — Mon, 30 Mar 2026 18:39:56 +0000

I haven't used pen and paper for note taking for years and years now. I used to keep a lot of notes in markdown organized into folders (used obsidian for a bit but was just easier to do in Vim). These days I don't take that many notes, usually only to capture key points/decisions in discussions but usually are pretty short lived. I find things get captured in other forms such that notes aren't really needed that much anymore.

New comment by keithnz in "Health NZ staff told to stop using ChatGPT to write clinical notes"

keithnz — Wed, 25 Mar 2026 22:23:18 +0000

FYI, AI adoption in health in NZ is moving forward, for example https://www.rnz.co.nz/news/national/589774/emergency-doctors...

This is just about not using free/public AI tools.

Trump administration will pay $1B in taxpayer funds to not build wind farms

keithnz — Tue, 24 Mar 2026 21:37:07 +0000

Article URL: https://www.cnn.com/2026/03/23/climate/trump-totalenergies-offshore-wind-cancellation

Comments URL: https://news.ycombinator.com/item?id=47509758

Points: 4

# Comments: 1

New comment by keithnz in "GitHub is once again down"

keithnz — Tue, 24 Mar 2026 21:13:58 +0000

No? Azures been rock solid for us.

New comment by keithnz in "Is anybody else bored of talking about AI?"

keithnz — Tue, 24 Mar 2026 21:09:47 +0000

No, well, I still enjoy the articles. The thing that always surprises me is the negativity in comment threads. I'm genuinely quite excited about AI based development. Yesterday I was playing around with developing a marketing plan for a market gap where we could leverage our product and finding what features in our product would need changing/adding to improve our offering. Quite interesting results!

New comment by keithnz in "Claude Code Cheat Sheet"

keithnz — Tue, 24 Mar 2026 01:05:12 +0000

just use claudes help, if you want to know keybinds, just do /keybinds (which is not in the cheat sheet)

New comment by keithnz in "Claude Code Cheat Sheet"

keithnz — Tue, 24 Mar 2026 01:03:19 +0000

it doesn't need to exist, its all in claudes help, and easily discoverable.

New comment by keithnz in "Claude Code Cheat Sheet"

keithnz — Tue, 24 Mar 2026 01:01:47 +0000

not really, mostly its self explanatory, it has poweruser things that are discoverable within a few minutes of reading the help. Weirdly the cheat sheet is actually missing things that you can find inside claudes help like /keybinds .

New comment by keithnz in "Ask HN: How do you deal with people who trust LLMs?"

keithnz — Thu, 19 Mar 2026 02:04:27 +0000

tell them what to prompt the AI with to get the correct results. I've seen a number youtube shorts lately doing this, where some scientist gets "refuted" by some random person based on an LLM result, they then sit with the LLM and ask the same question, get the same wrong answer, then follow it up with a clarifying question, which then the LLM realizes its mistake and gives a better answer.

New comment by keithnz in "[dead]"

keithnz — Wed, 18 Mar 2026 23:42:04 +0000

always worth knowing when you are in the P00

New comment by keithnz in "The pleasures of poor product design"

keithnz — Wed, 18 Mar 2026 02:15:44 +0000

given the title, so may software developers must be living in bliss! /s

New comment by keithnz in "Toward automated verification of unreviewed AI-generated code"

keithnz — Tue, 17 Mar 2026 20:52:28 +0000

I've been working on a "vibe coded" project to create a open source TUI sql query tool a bit like DataGrip, with autocomplete, syntax highlighting, schema introspection, vim mode/non vim, allows MCP mode so an agent can help with queries/get results, editing rows, etc. It's mostly an experiment into how to build software from scratch via an Agent without looking at the code (other than to see what decisions its making) and I wanted something reasonably complicated so the requirements evolve / change over time. There are a couple of issues I find, many bugs are unspecified edge cases especially because many of the features "combo" together, and the other issue is it's hard for it to maintain consistency across the UI. You start setting up a lot more context for cross cutting concerns, reviewing itself, and testing. The tool itself is actually really useful and it is my main tool for querying our dbs now. Most of the problem I find are due to "sloppy" prompting (or just not thinking through the edge cases), and a lack of project wide guidance for dealing with the architecture of the system to maintain consistency across the same concerns.

New comment by keithnz in "Ask HN: How is AI-assisted coding going for you professionally?"

keithnz — Sun, 15 Mar 2026 22:22:48 +0000

Pretty good, we have a huge number of projects, some more modern than others. For the older legacy systems, it's been hugely useful. Not perfect, needs a bit more babysitting, but a lot easier to deal with than doing it solo. For the newer things, they can mostly be done solely by AI, so more time spent just speccing / designing the system than coding. But every week we are working out better and batter ways of working with AI, so it's an evolving process at the moment

New comment by keithnz in "Emacs and Vim in the Age of AI"

keithnz — Sat, 14 Mar 2026 11:24:51 +0000

gdorsi , it's not that hard to swap really, because the goal, designing systems, just got easier. I feel AI lets you be a system engineer way better as you can quickly iterate. I have the same kinds of goals in mind, just can do it a heck of a lot quicker.