Hacker News: pglevy

New comment by pglevy in "Axios compromised on NPM – Malicious versions drop remote access trojan"

pglevy — Tue, 31 Mar 2026 07:07:36 +0000

I was thinking about this as a bull case for human developers. Seems if you're worried enough to do this you're not going to have LLMs write the new code.

New comment by pglevy in "Ask HN: What are you working on? (February 2026)"

pglevy — Mon, 09 Feb 2026 12:44:09 +0000

Just tried out Opus 4.6 to make a ground-up new version of a perennial side project: static site podcast player.

For this one I focused on loading speed and reducing interaction with repo. So it processes the images (converting to webp) and loads the feed list from a Gist. Also used the "frontend-design" skill. From brief to ready-to-use took about a couple hours.

https://github.com/pglevy/typod

New comment by pglevy in "Management as AI superpower: Thriving in a world of agentic AI"

pglevy — Tue, 27 Jan 2026 17:34:18 +0000

> I think many people have the skills they need, or can learn them, in order to work with AI agents - they are management 101 skills.

I like his thinking but many professional managers are not good at management. So I'm not sure about the assumption that "many people" can easily pick this up.

New comment by pglevy in "AI is a horse (2024)"

pglevy — Fri, 23 Jan 2026 17:49:48 +0000

Moped for the mind has a nice ring to it

New comment by pglevy in "Show HN: Figma-use – CLI to control Figma for AI agents"

pglevy — Sun, 18 Jan 2026 15:26:28 +0000

I'm curious to understand more about your use case. I've been working on getting fellow designers out of Figma since it's easier to express intent in code now using LLMs.

New comment by pglevy in "First impressions of Claude Cowork"

pglevy — Fri, 16 Jan 2026 03:27:43 +0000

He literally brings up a concern he calls the "lethal trifecta" when it's even remotely relevant.

New comment by pglevy in "Show HN: Minimalist editor that lives in browser, stores everything in the URL"

pglevy — Wed, 24 Dec 2025 21:16:37 +0000

Thanks for sharing! I tried a similar content-in-url approach for a family grocery list app but I couldn't get the url that short. (It worked but it was a bit cumbersome sharing over Whatsapp.) Will see what I can learn from this!

New comment by pglevy in "Incomplete list of mistakes in the design of CSS"

pglevy — Thu, 11 Dec 2025 13:21:26 +0000

At least one person. https://tonsky.me/blog/centering/

New comment by pglevy in "AI should only run as fast as we can catch up"

pglevy — Tue, 09 Dec 2025 00:34:18 +0000

I've been thinking about something like this from a UI perspective. I'm a UX designer working on a product with a fairly legacy codebase. We're vibe coding prototypes and moving towards making it easier for devs to bring in new components. We have a hard enough time verifying the UI quality as it is. And having more devs vibing on frontend code is probably going to make it a lot worse. I'm thinking about something like having agents regularly traversing the code to identify non-approved components (and either fixing or flagging them). Maybe with this we won't fall further behind with verification debt than we already are.

New comment by pglevy in "Ask HN: What are you working on? (October 2025)"

pglevy — Mon, 13 Oct 2025 03:01:36 +0000

For context, I'm a UX Designer at a low-code company. LLMs are great at cranking out prototypes using well-known React component libraries. But lesser known low-code syntax takes more work. We made an MCP server that helps a lot, but what I'm working on now is a set of steering docs to generate components and prototypes that are "backwards compatible" with our bespoke front end language. This way our vibe prototyping has our default look out of the box and translates more directly to production code. https://github.com/pglevy/sail-zero

New comment by pglevy in "To AI or not to AI"

pglevy — Mon, 29 Sep 2025 16:46:28 +0000

Our low-code expression language is not well-represented in the pre-training data. So as a baseline we get lots of syntax errors and really bad-looking UIs. But we're getting much better results by setting up our design system documentation as an MCP server. Our docs include curated guidance and code samples, so when the LLM uses the server, it's able to more competently search for things and call the relevant tools. With this small but high-quality dataset, it also looks better than some of our experiments with fine tuning. I imagine this could work for other docs use cases that are more dynamic (ie, we're actively updating the docs so having the LLM call APIs for what it needs seems more appropriate than a static RAG setup).

New comment by pglevy in "Scammed out of $130K via fake Google call, spoofed Google email and auth sync"

pglevy — Tue, 16 Sep 2025 21:12:37 +0000

> I answered.

I never answer the phone.

New comment by pglevy in "Don't Build Multi-Agents"

pglevy — Tue, 02 Sep 2025 02:39:23 +0000

Not an engineer but I think this is where my mind was going after reading the post. Seems like what will be useful is continuously generated "decision documentation." So the system has access to what has come before in a dynamic way. (Like some mix of RAG with knowledge graph + MCP?) Maybe even pre-outlining "decisions to be made," so if an agent is checking in, it could see there is something that needs to be figured out but hasn't been done yet.

New comment by pglevy in "What makes Claude Code so damn good"

pglevy — Sun, 24 Aug 2025 14:34:57 +0000

Mine is a much simpler use case but sharing in case it's useful. I wanted to be able to quickly generate and iterate on user flows during design collaboration. So I use some boilerplate HTML/CSS and have the LLM generate an "outline" (basically a config file) and then generate the HTML from that. This way I can make quick adjustments in the outline and just have it refresh the code when needed to avoid too much back forth with the chat.

Overall, it has been working pretty well. I did make a tweak I haven't pushed yet to make it always writes the outline to a file first (instead of just terminal). And I've also started adding slash commands to the instructions so I can type things like "/create some flow" and then just "/refresh" (instead of "pardon me, would you mind refreshing that flow now?").

https://github.com/pglevy/breadboarding-kit

New comment by pglevy in "Claude Opus 4 and 4.1 can now end a rare subset of conversations"

pglevy — Fri, 15 Aug 2025 22:13:17 +0000

But not Sonnet?

New comment by pglevy in "Show HN: Nia – MCP server that gives more docs and repos to coding agents"

pglevy — Fri, 25 Jul 2025 11:40:05 +0000

My use case is a little different (mostly prototyping and building design ops tools) but +1 to this flow.

At this point, I typically do an LLM-readme at the branch level to document both planning and progress. At the project level I've started having it dump (and organize) everything in a work-focused Obsidian vault. This way I end up with cross-project resources in one place, it doesn't bloat my repos, and it can be used by other agents from where it is.

New comment by pglevy in "Show HN: Any-LLM – Lightweight router to access any LLM Provider"

pglevy — Tue, 22 Jul 2025 20:57:04 +0000

How does this differ from this project? https://github.com/simonw/llm

New comment by pglevy in "Building a Mac app with Claude code"

pglevy — Sun, 06 Jul 2025 17:21:16 +0000

This way of putting it resonates with me: unlocking the value of fuzzy knowledge.

New comment by pglevy in "A 37-year-old wanting to learn computer science"

pglevy — Sat, 05 Jul 2025 19:25:56 +0000

That's fair. It depends on the goal. I'm not trying to change careers. And I didn't get that sense from original poster. I'm mostly interested in prototyping or addressing niche productivity issues. But I feel I learn quite a bit from seeing what the LLM does and asking follow up questions or looking things up. I've been around software dev a lot so that helps with knowing what to ask sometimes. My main point is if someone is interested in building software, they should start building as soon as possible. Don't feel you have learn everything first.

New comment by pglevy in "A 37-year-old wanting to learn computer science"

pglevy — Sat, 05 Jul 2025 17:04:38 +0000

What I took away from your post was not that you want to learn computer science but that you want to build things with software. If so, now is a really exciting time because it's never been easier for people without a CS background to go from idea to working software.

As a UX designer, I've worked with developers for a long time, so I've picked up knowledge along the way. I've read some books and merged some PRs at work but nothing that would qualify me as a developer.

What am I'm having a lot fun with right now though is building with LLMs. If I have an idea, I'll just throw it into Replit or Claude Code to see what it comes up with and then decide if I want to pursue it further.

My 2 cents: learn by building. Start working down your list of ideas and dig deeper into questions and topics that come up. Will probably keep things more interesting than slogging through a course.