Hacker News: gavmor

New comment by gavmor in "How I use LLMs to learn complex topics"

gavmor — Mon, 10 Aug 2026 10:23:43 +0000

I don't know anything about investing, but I know a lot about naivete. :)

New comment by gavmor in "How I use LLMs to learn complex topics"

gavmor — Sun, 09 Aug 2026 20:46:38 +0000

Or is it just an unproven attempt? Seems like a pretty straightforward value proposition. Caveat emptor.

New comment by gavmor in "A Rant About “Technology” (2005)"

gavmor — Sun, 02 Aug 2026 16:46:46 +0000

It takes place on another planet, and isn't alien biology "science" speculation, enough?

Besides, it's not even her best work.

Looking forward to reading your story! You might consider Ted Chiang.

New comment by gavmor in "The Religion of Speed"

gavmor — Fri, 31 Jul 2026 06:21:41 +0000

I like setting arbitrary project milestones or timelines. They don't have to kill the project, but it's good to cast efforts in relief against external developments.

New comment by gavmor in "Superlogical"

gavmor — Thu, 30 Jul 2026 04:35:46 +0000

My daily driver is Agent of Empires (https://github.com/agent-of-empires/agent-of-empires)

New comment by gavmor in "Htmx 4.0, the first JavaScript library to release exclusively on the Game Boy"

gavmor — Sun, 26 Jul 2026 17:16:14 +0000

I just started experimenting with GSX and GSXUI

https://github.com/gsxhq/gsxui

https://github.com/jackielii/structpages is what I might call a framework that GSX sits nicely in.

Also one ai haven't tried: Templ.

https://github.com/a-h/templ

New comment by gavmor in "Claude Cookbook"

gavmor — Fri, 24 Jul 2026 14:37:33 +0000

"DRY" and "KISS" are, possibly, the least interesting principles to which a software designer might adhere.

New comment by gavmor in "Minecraft: Java Edition now uses SDL3"

gavmor — Sun, 19 Jul 2026 16:38:24 +0000

I'm sure it already can with the right mod/plugin.

New comment by gavmor in "Show HN: LoopGain – Stop agent loops with control theory, not max_iterations"

gavmor — Sun, 19 Jul 2026 16:29:25 +0000

I've got an application for this. Will try and get some benchmarks in the next few weeks. We're definitely attempting to converge on a quality inference without wasting tokens/time.

For now, we're passing the first pass to the humans, and that's roughly 80 for 20, but to get the last 20 without blowing up our token spend? This might be the approach.

Thanks for the write up comment, btw.

New comment by gavmor in "1,300 Beautiful Wildlife Illustrations from the 19th Century Now Restored"

gavmor — Thu, 16 Jul 2026 14:18:47 +0000

The artwork "as it was created" is unavailable. The only options are Rougeoux or the ravages of time.

New comment by gavmor in "Qwen-AgentWorld: Language World Models for General Agents"

gavmor — Wed, 24 Jun 2026 05:39:27 +0000

A regular LLM acts as a "policy," mapping a current state to a specific action (states → actions). Their new LLM acts as a "world model," mapping a current state and a chosen action to a predicted future state ((states, actions) → subsequent states). Instead of deciding "what to do," its explicit objective is to predict the exact environment observation that will result from the interaction history and the agent's current action.

I assumed at first that it was trained on synthetic data, but they actually went and deployed real physical hosts and virtual machines (e.g. Ubuntu, macOS, and Android) and browsers. They ran agentic systems on these continuously and recorded the actual, real-world interactions.

So it's an LLM that infers next state, or outcome,as structured data e.g. literal HTML code, UI view hierarchies, or accessibility trees.

New comment by gavmor in "Beyond All Reason (Free Total Annihilation Inspired RTS)"

gavmor — Sun, 21 Jun 2026 20:04:00 +0000

The cold takes themselves are a fantastic proof of the care and attention the devs put into this game, as well as the depths of their design philosophy.

New comment by gavmor in "Prefer duplication over the wrong abstraction (2016)"

gavmor — Sun, 21 Jun 2026 18:38:02 +0000

> Almost nobody optimizes compiled assembly code.

Compiled assembly code is not an input to the next compilation; source code is an input to the LLM's next inference.

Sure, maybe "prompts are the code," but you must realize that code is also the prompt.

New comment by gavmor in "Code duplication is far cheaper than the wrong abstraction (2016)"

gavmor — Sun, 21 Jun 2026 16:51:47 +0000

Well sooner or later I would expect a developer who intimately understands their code base to feel compelled to start refactoring and extracting fitting, meaningful well-leveraged abstractions.

New comment by gavmor in "Cirrus: ATProto Personal Data Server That Runs on Cloudflare Workers"

gavmor — Sat, 20 Jun 2026 13:07:17 +0000

Migrating to a workerd container is an option.

New comment by gavmor in "Show HN: Metiq: a real time 3D globe for 100 public datasets"

gavmor — Sat, 20 Jun 2026 12:59:29 +0000

What's the data doing that's so sluggish? Is it being correlated/transformed, or is it just so many points of light are blocking each frame?

New comment by gavmor in "Show HN: Metiq: a real time 3D globe for 100 public datasets"

gavmor — Fri, 19 Jun 2026 22:20:19 +0000

I wonder if Mollweide or Atlantis projections wouldn't be more performant?

New comment by gavmor in "But yak shaving is fun (2019)"

gavmor — Tue, 16 Jun 2026 17:58:24 +0000

Riding horseback saves time over walking but it's harder to smell the roses along the way. Nevertheless, millions now ride horses recreationally.

New comment by gavmor in "I Am Not a Reverse Centaur"

gavmor — Fri, 12 Jun 2026 20:25:03 +0000

Who gets a sense of accomplishment from cheering for their home team?

New comment by gavmor in "Meta confirms 1000s of Instagram accounts were hacked by abusing its AI chatbot"

gavmor — Sun, 07 Jun 2026 04:13:33 +0000

The overall system that allowed this implementation is accountable. So why put such a fine point on it so as to exculpate the LLM?