Hacker News: loh

New comment by loh in "Claude Fable 5.1 and Claude Mythos 5.1"

loh — Wed, 02 Sep 2026 10:44:24 +0000

I agree with you here, but to make it clear what I meant, I'll reiterate what I said in a sibling comment: I wasn't referring to the current state of Opus 5 (or even Fable 5.1) output. I was referring to possible future information density (vocabulary and sentence structure) that LLMs may evolve to use.

New comment by loh in "Claude Fable 5.1 and Claude Mythos 5.1"

loh — Wed, 02 Sep 2026 10:40:23 +0000

I wasn't referring to the current state of Opus 5 output. I was referring to possible future information density (vocabulary and sentence structure) that LLMs may evolve to use.

New comment by loh in "Claude Fable 5.1 and Claude Mythos 5.1"

loh — Wed, 02 Sep 2026 03:28:34 +0000

If this kind of "AI-speak" becomes ubiquitous and humans reading it becomes the norm (whether to guide AI or other reasons), I'd imagine future generations (of humans) who grow up with it will be able to understand and work with it much better than we do. Future humans' brains will probably be wired a bit differently, similar to multilingual speakers of today. We may even see "AI language" classes become a common part of school curriculums. Although, I think AI will probably advance enough that most people will never even need to communicate on "its level", but it's probably a good idea to keep humans in the loop either way, and in which case, understanding the more advanced "AI vocabulary" might be useful.

New comment by loh in "Show HN: Molecule.dev is an AI-first composable package ecosystem"

loh — Thu, 20 Aug 2026 21:03:10 +0000

TL;DR: Revived my dead startup with AI and open sourced 99% of it.

For a bit of background here, I built Molecule.dev back in 2021 before AI was really a thing. It worked by allowing you to select the stack, libraries, and features you wanted, and then it would cherry pick a series of carefully crafted git commits to produce a fully functional app and API based on your selection. The idea was to provide polished code (using best practices at the time) that easily fit into common workflows of professional teams to help them quickly scale. It was probably too ambitious for the time, so after failing to find product-market fit fast enough, I very dangerously ran out of runway and had to scrap it.

Fast forward to early 2026... Opus 4.5 was out and after playing around with it a bit, it became clear that the original vision of decoupled, easily swappable stacks, features, and integrations was now possible. Long story short, I pointed Opus at Molecule v1's codebase and explained the design patterns, where I wanted to go with it, and have been grinding away at it nonstop ever since.

Turns out that v1's cherry-pickable architecture translates pretty well to code that weak LLMs can understand and work with. This makes it possible to very cheaply integrate/swap full-stack features and functionality common to almost every app, end-to-end, and the result is polished, predictable, and works immediately... so people no longer need to waste a bunch of time and tokens generating/testing/fixing semi-random unpolished code for core functionality. As you might expect, the AI generated code within Molecule's own packages isn't always the best, but I'm certain that we will solve that problem with more time and tokens, as the Molecule "bond" pattern helps enforce better code and architecture.

The goal here is to help people (tech savvy or not) build higher quality software faster and cheaper, allowing them to focus on solving real problems instead of dealing with the mundane work that makes the last 10% of building a real app such an unexpected pain. Hopefully it will help reduce the "AI slop" type apps by giving people more time and energy to build things that are more unique but still provide all of the common functionality we expect from polished software. Ideally, some years from now, no one (not even LLMs) will need to think about how some common core functionality should be implemented. We should be able to look back and say "problem solved".

There is still a lot to do (with some really cool/useful stuff planned for the future!) and it's definitely rough around the edges at the moment, but I figured I'd go ahead and share v2 as a proof of concept.

Show HN: Molecule.dev is an AI-first composable package ecosystem

loh — Thu, 20 Aug 2026 21:00:07 +0000

Article URL: https://github.com/molecule-dev/molecule

Comments URL: https://news.ycombinator.com/item?id=49380202

Points: 2

# Comments: 1

Lhv.ai – Estonian bank AI integration via MCP

loh — Wed, 15 Jul 2026 23:41:29 +0000

Article URL: https://lhv.ai/

Comments URL: https://news.ycombinator.com/item?id=48928679

Points: 2

# Comments: 0

New comment by loh in "Show HN: Performative-UI – A react component library of design tropes"

loh — Mon, 08 Jun 2026 21:02:23 +0000

Actually quite good for a meme library! Unironically considering using some of this, or pulling some inspiration from it at least.

Also, I'm curious as to when the animated gradient text started being a popular thing. I started doing it back in 2021 or so. I think I was inspired by some of Apple's webpages at the time.

Coffee appears to rewire the gut-brain connection

loh — Mon, 04 May 2026 02:15:32 +0000

Article URL: https://www.sciencedaily.com/releases/2026/05/260502233911.htm

Comments URL: https://news.ycombinator.com/item?id=48003888

Points: 19

# Comments: 15

5G and 6G networks could help devices run AI without needing powerful chips

loh — Sun, 15 Feb 2026 21:55:27 +0000

Article URL: https://pratt.duke.edu/news/using-the-physics-of-radio-waves-to-empower-smarter-edge-devices/

Comments URL: https://news.ycombinator.com/item?id=47028028

Points: 1

# Comments: 0

Shape-shifting molecules as future AI hardware

loh — Wed, 21 Jan 2026 12:50:28 +0000

Article URL: https://www.sciencedaily.com/releases/2026/01/260101160857.htm

Comments URL: https://news.ycombinator.com/item?id=46704995

Points: 1

# Comments: 0

New comment by loh in "Ask HN: Do you have any evidence that agentic coding works?"

loh — Wed, 21 Jan 2026 12:47:52 +0000

Not really, no, at least not with Claude. It seems to already understand the UE5 way of doing things, but there were a couple of edge cases for new features beyond its cutoff date where I had to refer Claude to the UE5 documentation. Once it read the documentation however, it understood and continued without issue. Also, for any compilation errors, I just copy and paste the error messages into Claude Code and it usually fixes it immediately.

New comment by loh in "Ask HN: Do you have any evidence that agentic coding works?"

loh — Wed, 21 Jan 2026 11:25:54 +0000

Just for fun, I built a first person shooter game in UE5 from scratch using agentic coding. I've only spent a couple of months on it in my free time so far, and it isn't complete yet, but it's close enough that I could definitely release an early access version with another month or so of work. The most time consuming tasks have actually been tasks that agentic coding hasn't been able to help out with, like animations and mapping. The game is mostly written in C++ and sometimes the agent makes some bad decisions, but with a bit of extra guidance and being smart about my git commits so that I can revert and try again if necessary, I've always been able to make it work the way I want. I most definitely would not have been able to build this on my own in any reasonable amount of time.

FWIW it seems like it heavily depends on the agent + model you're using. I've had the most success with Claude Code (Sonnet), and only tried Opus 4.5 for more complex things. I've also tried Codex which didn't seem very good by comparison, plus a handful of other local models (Qwen3, GLM, Minimax, etc.) through OpenCode, Roo, and Cline that I'm able to run on my 128 GB M4 Max. The local ones can work for very simple agentic tasks, albeit quite slow.

Researchers Show Today's Quantum Computers Can Reliably Study Complex Physics

loh — Tue, 20 Jan 2026 20:10:56 +0000

Article URL: https://thequantuminsider.com/2026/01/20/researchers-show-todays-quantum-computers-can-reliably-study-complex-physics/

Comments URL: https://news.ycombinator.com/item?id=46697129

Points: 3

# Comments: 0

Normal Computing tapes-out first thermodynamic chip (2025)

loh — Tue, 20 Jan 2026 19:59:54 +0000

Article URL: https://www.datacenterdynamics.com/en/news/normal-computing-tapes-out-worlds-first-thermodynamic-chip-for-energy-efficient-ai-workloads/

Comments URL: https://news.ycombinator.com/item?id=46696990

Points: 2

# Comments: 0

Predictions for Embodied AI and Robotics in 2026

loh — Tue, 20 Jan 2026 17:41:54 +0000

Article URL: https://dtsbourg.me/en/articles/predictions-embodied-ai

Comments URL: https://news.ycombinator.com/item?id=46695076

Points: 2

# Comments: 0

Artificial neurons that replicate biological function

loh — Tue, 20 Jan 2026 17:10:40 +0000

Article URL: https://viterbischool.usc.edu/news/2025/10/artificial-neurons-developed-by-usc-team-replicate-biological-function-for-improved-computer-chips/

Comments URL: https://news.ycombinator.com/item?id=46694510

Points: 2

# Comments: 0

New comment by loh in "Run LLMs on Apple Neural Engine (ANE)"

loh — Sat, 03 May 2025 23:27:30 +0000

Yeah, I looked all over for a comparison and couldn't find anything in the repo, on their social media, etc. I saw some other comments here that said it's supposed to be "15.8 fp16 ops compared to 14.7 fp32 ops" but that isn't really enough to go on. Maybe when I have the time I'll install their TestFlight app and do some comparisons myself.

New comment by loh in "GPT4 is 8 x 220B params = 1.7T params"

loh — Wed, 21 Jun 2023 07:10:02 +0000

I had a good chuckle at "squishy machines". That's a really interesting way to think about it. It makes me wonder if, some day, we will be able to build "squishy machines" of our own, capable of outperforming silicon while using a tiny fraction of the energy.

New comment by loh in "ES modules: A cartoon deep-dive (2018)"

loh — Thu, 01 Jun 2023 10:16:45 +0000

Thanks for this. Just a few minutes ago I pulled up an old project using `ts-node` with ESM and tried to run it on a new machine, had some issues and remembered reading your comment here earlier. I switched to `tsx` and in less than a minute everything was working beautifully. I'll probably migrate all my TS projects to `tsx`.

New comment by loh in "New work helps to explain how chronic stress can inflame the gut"

loh — Fri, 26 May 2023 09:48:27 +0000

For years I had the same gut issues described by others here, seemingly caused by a combination of factors. I'll share what helped me solve the problem.

The most effective thing for me seemed to be hitting the gym hard, lifting heavy and sweating a lot.

Alongside that, I went through a lot of trial and error with the foods my body would tolerate. I started with a low histamine/low FODMAP approach, various fasting methods, bone broths (collagen), probiotics (sauerkraut, kefir), etc., and slowly introduced various foods on top of that while noting what made me feel good or bad and basing my diet around that. Everyone is different so what worked for me diet-wise may not work for you.

Lastly, for my particular case, I think liver-boosting supplements like milk thistle and NAC helped significantly (and probably some others for any vitamin/mineral deficiencies, especially D3+K2). I suspect the root cause of my problems was toxic mold plus stress/trauma.