Hacker News: patleeman

New comment by patleeman in "Ask HN: How do you manage skills files?"

patleeman — Mon, 07 Sep 2026 04:10:03 +0000

I use an agent plugin spec repo. Codex is already compatible with it and it supports skills + MCP definitions.

https://agent-plugins.org/

New comment by patleeman in "Fucc Boi Bench"

patleeman — Thu, 03 Sep 2026 02:55:54 +0000

did you actually look at the site?

Fucc Boi Bench

patleeman — Thu, 03 Sep 2026 02:52:41 +0000

Article URL: https://www.fuccboibench.com/index.html

Comments URL: https://news.ycombinator.com/item?id=49545421

Points: 2

# Comments: 3

Self-extensible software is here and its amazing

patleeman — Tue, 02 Jun 2026 20:57:52 +0000

Article URL: https://slopfluencer.com/posts/2026_06_02-self-extensible-software/

Comments URL: https://news.ycombinator.com/item?id=48376177

Points: 3

# Comments: 1

New comment by patleeman in "I've Sold Out"

patleeman — Wed, 08 Apr 2026 11:07:09 +0000

I’m not disappointed. It seems philosophically the teams are aligned and Pi as a project can continue and be supported. It’s a better outcome than most could expect.

Task Factory: A lean manufacturing inspired task queue for AI coding

patleeman — Tue, 17 Feb 2026 13:54:56 +0000

Article URL: https://github.com/patleeman/task-factory

Comments URL: https://news.ycombinator.com/item?id=47047501

Points: 1

# Comments: 0

New comment by patleeman in "Qntm's Power Tower Toy"

patleeman — Wed, 24 Dec 2025 21:09:12 +0000

I loved this book. The audiobook is available on spotify and was a great listen.

New comment by patleeman in "MCP Is Not Good, Yet"

patleeman — Wed, 07 May 2025 11:33:59 +0000

I’ve been diving into MCP the last few days and it feels quite messy.

It took an embarrassingly long time for me to figure out what the difference is between a client, server, and host are. Oh and servers can also be processes that you run locally and clients can spin up the server for you but you need to provide the NPX or UVX command.

The problem it’s supposed to solve is quite real, tools are annoying to build and share so I get that. Looking forward to it getting better but it’s not at the point where any dev can come in and connect things up with a nice dev experience yet.

New comment by patleeman in "Run DeepSeek R1 Dynamic 1.58-bit"

patleeman — Tue, 28 Jan 2025 22:33:12 +0000

Incredible work by the Unsloth brothers again. It’s really cool to see bitnet quantization implemented like this.

New comment by patleeman in "Fine-Tuning LLMs to 1.58bit"

patleeman — Wed, 18 Sep 2024 17:51:31 +0000

That's awesome. The original discussion of bitnet made it seem like you needed to train a model from scratch but its neat they were able to adapt an existing model. This is quite exciting.

New comment by patleeman in "Dropbox Acquires Reclaim.ai"

patleeman — Tue, 20 Aug 2024 18:48:20 +0000

Yeah, its kind of a bummer. Dropbox doesn't really have a cohesive vision for their productivity suite? Dropbox Paper doesn't seem to have progressed and there haven't been any other notable new products released.

New comment by patleeman in "LLM that can call multiple tool APIs with one request"

patleeman — Tue, 18 Jun 2024 19:50:05 +0000

Very curious if anybody else is working on a DSL that's meant for LLMs to output?

Has anyone seen anyone using this approach? Any resources available?

New comment by patleeman in "LLM that can call multiple tool APIs with one request"

patleeman — Tue, 18 Jun 2024 19:45:51 +0000

Domain Specific Language

New comment by patleeman in "Rabbit R1 source code [part 1]"

patleeman — Tue, 23 Apr 2024 22:18:55 +0000

Can somebody translate this?

New comment by patleeman in "Effective Neovim: An Instant IDE [video]"

patleeman — Mon, 06 Nov 2023 15:10:01 +0000

Yeah, I've been meaning to spend more time on it, but I've been switching around to different editors a lot lately, so the constant jumping around means I'm trying to keep my vim keybinds as vanilla as possible.

New comment by patleeman in "Effective Neovim: An Instant IDE [video]"

patleeman — Mon, 06 Nov 2023 15:08:34 +0000

Yeah, this is the biggest thing I miss from neovim.

New comment by patleeman in "Effective Neovim: An Instant IDE [video]"

patleeman — Sun, 05 Nov 2023 15:25:08 +0000

I recently forced myself to learn vim motions and it's been paying off pretty well. Once it clicked I found myself wanting vim motions everywhere.

I went deep and set up a neovim config, forcing myself to use neovim full time. However my new role requires me to use Intellij and I didn't want to spend hours upon hours figuring out how to replicate the java support in Neovim (and no, it isn't just installing the LSP, my work has some pretty specific intellij setup).

At this point I'm just using Intellij and VSCode with their respective vim plugins and I'm getting about 80% of the utility that I did with pure neovim. The one thing I really love about neovim is that it really forces you to keep your hands on the keyboard and you learn the keybinds very well because otherwise you just can't do the thing you wanted to! I find myself using the mouse a lot in VSCode and Intellij because they give you really handy buttons to click on.

I could probably go pure keyboard if I just sat down and learned all the various keybinds, but who has time for that?

New comment by patleeman in "Telling AI model to “take a deep breath” causes math scores to soar in study"

patleeman — Wed, 20 Sep 2023 02:29:15 +0000

The actual prompt is just a chain of thought prompt and the headline is just clickbait.

Also in the article, the author gets COT wrong.

> What "reasoning" they do (and "reasoning" is a contentious term among some, though it is readily used as a term of art in AI) is borrowed from a massive data set of language phrases scraped from books and the web. That includes things like Q&A forums, which include many examples of "let's take a deep breath" or "think step by step" before showing more carefully reasoned solutions. Those phrases may help the LLM tap into better answers or produce better examples of reasoning or solving problems from the data set it absorbed into its neural network weights.

Chain of thought has nothing to do with “tapping into better answers”. It’s simply asking the model to break up the output into smaller tasks and gives it more time and space to reason.

COT is not new or novel. Hell, it’s even listed in one of the guides in Open AI’s prompt guides as a strategy to improve prompts.

The Grug Brained Manager

patleeman — Thu, 07 Sep 2023 14:35:12 +0000

Article URL: https://patricklee.nyc/blog/the-grug-brained-manager/

Comments URL: https://news.ycombinator.com/item?id=37419500

Points: 2

# Comments: 0

New comment by patleeman in "Google’s AI-powered notes app is now called NotebookLM, and it’s launching today"

patleeman — Wed, 12 Jul 2023 23:49:44 +0000

Why bother adopting the tool when Google invariably kills it off in a few years anyways?