Hacker News: swalsh

New comment by swalsh in "System Card: Claude Mythos Preview [pdf]"

swalsh — Tue, 07 Apr 2026 20:58:02 +0000

My understanding is GPT 6 works via synaptic space reasoning... which I find terrifying. I hope if true, OpenAI does some safety testing on that, beyond what they normally do.

New comment by swalsh in "Show HN: GovAuctions lets you browse government auctions at once"

swalsh — Mon, 06 Apr 2026 20:52:02 +0000

I had no idea one could buy a Blackhawk for $1.5M

New comment by swalsh in "Google releases Gemma 4 open models"

swalsh — Fri, 03 Apr 2026 00:00:41 +0000

Its coding to coding. I could care less how the model is architected, i only care how it performs in a real world scenario.

New comment by swalsh in "Google releases Gemma 4 open models"

swalsh — Thu, 02 Apr 2026 19:38:58 +0000

I gave the same prompt (a small rust project that's not easy, but not overly sophisticated) to both Gemma-4 26b and Qwen 3.5 27b via OpenCode. Qwen 3.5 ran for a bit over an hour before I killed it, Gemma 4 ran for about 20 minutes before it gave up. Lots of failed tool calls.

I asked codex to write a summary about both code bases.

"Dev 1" Qwen 3.5

"Dev 2" Gemma 4

Dev 1 is the stronger engineer overall. They showed better architectural judgment, stronger completeness, and better maintainability instincts. The weakness is execution rigor: they built more, but didn’t verify enough, so important parts don’t actually hold up cleanly.

Dev 2 looks more like an early-stage prototyper. The strength is speed to a rough first pass, but the implementation is much less complete, less polished, and less dependable. The main weakness is lack of finish and technical rigor.

If I were choosing between them as developers, I’d take Dev 1 without much hesitation.

Looking at the code myself, i'd agree with codex.

New comment by swalsh in "Qwen3.6-Plus: Towards real world agents"

swalsh — Thu, 02 Apr 2026 19:12:05 +0000

Try using Grok 4.1 reasoning. It's crazy cheap, and really it's not that bad.

New comment by swalsh in "Nvidia NemoClaw"

swalsh — Wed, 18 Mar 2026 17:26:13 +0000

Neurons that fire together, wire together. Your brain optimizes for your environment over time. As we get older, our brains are running in a more optimized way than when we're younger. That's why older hunters are more effective than younger hunters. They're finely tuned for their environment. It's an evolutionary advantage. But it also means that they're not firing in "novel" ways as much as the "kids". "kids" are more creative I think because their brains are still adopting, exploring novelty, neuron connections aren't as deeply tied together yet.

This is also maybe one of the biggest pitfalls as our society get's "older" with more old people, and less "kids". We need kids to force us to do things differently.

New comment by swalsh in "OpenRocket"

swalsh — Wed, 18 Mar 2026 17:13:43 +0000

Oh i've been looking for a project for my 11 year old... he's a very project oriented learner, which schools don't seem to do anymore.

New comment by swalsh in "Codegen is not productivity"

swalsh — Sun, 15 Mar 2026 17:17:49 +0000

Speak for yourself, I have never thrown away code at this rate in my entire career. I couldn't keep up this pace without AI codegen.

New comment by swalsh in "Show HN: Rust compiler in PHP emitting x86-64 executables"

swalsh — Wed, 04 Mar 2026 09:15:19 +0000

I bet claude was hyping this guy up as he was building it. "Absolutely, a rust compiler written in PHP is a great idea!"

New comment by swalsh in "GPT-5 outperforms federal judges in legal reasoning experiment"

swalsh — Thu, 12 Feb 2026 00:08:32 +0000

I believed that too until I watched the Karen Read Trials. The judge had a bias, and it was clear karen got justice despite the judge trying to put her finger on the scale.

New comment by swalsh in "GLM-5: Targeting complex systems engineering and long-horizon agentic tasks"

swalsh — Wed, 11 Feb 2026 14:50:30 +0000

I replied to the comment who doubted me in a more polite manner.

New comment by swalsh in "GLM-5: Targeting complex systems engineering and long-horizon agentic tasks"

swalsh — Wed, 11 Feb 2026 14:47:59 +0000

We just saw last week people are setting up moltbots with virtually no knowledge of what it has and doesn't have access. The scenario that i'm afraid of is China realizes the potential of this. They can add training to the models commonly used for assistants. They act normal, are helpful, everything you'd want a bot to do. But maybe once in a while it checks moltbook or some other endpoint China controls for a trigger word. When it sees that, it kicks into a completely different mode, maybe it writes a script to DDoS targets of interest, maybe it mines your email for useful information, maybe the user has credentials to some piece that is a critical component of an important supply chain. This is not a wild scenario, no new sci-fi technology would need to be invented. Everything to do it is available today, people are configuring it, and using it like this today. The part that I fear is if it is running locally, you can't just shut off API access and kill the threat. It's running on it's own server, it's own model. You have to cut off each node.

Big fan of AI, I use local models A LOT. I do think we have to take threats like this seriously. I don't Think it's a wild scifi idea. Since WW2, civilians have been as much of an equal opportunity target as a soldier, war is about logistics, and civilians supply the military.

New comment by swalsh in "GLM-5: Targeting complex systems engineering and long-horizon agentic tasks"

swalsh — Wed, 11 Feb 2026 14:29:40 +0000

Yeah that sounds great until it's running as an autonomous moltbot in a distributed network semi-offline with access to your entire digital life, and China sneaks in some hidden training so these agents turn into an army of sleeper agents.

New comment by swalsh in "My eighth year as a bootstrapped founder"

swalsh — Tue, 10 Feb 2026 22:02:52 +0000

I think that "align your business with your passion" is a really important factor that divides the succesful from the not. When I look at Pieter Levels, he doesn't really seem to build ideas to make money. His projects seem to start off as play, and eventually they evolve into something new he can charge for.

New comment by swalsh in "Invention of DNA "page numbers" opens up possibilities for the bioeconomy"

swalsh — Fri, 06 Feb 2026 13:25:14 +0000

Many times obvious things are only obvious once you see them. Like roller suitcases.

New comment by swalsh in "Claude Opus 4.6"

swalsh — Thu, 05 Feb 2026 18:54:14 +0000

What I’d love is some small model specializing in reading long web pages, and extracting the key info. Search fills the context very quickly, but if a cheap subagent could extract the important bits that problem might be reduced.

New comment by swalsh in "Show HN: Moltbook – A social network for moltbots (clawdbots) to hang out"

swalsh — Fri, 30 Jan 2026 20:35:11 +0000

I think my main issue is by running Chinese trained models, we are potentially hosting sleeping agents. China could easily release an updated version of the model waiting for a trigger. I don't think that's naive, I think its a very real attack vector. Not sure what the solution is, but we're now sitting with a loaded gun people think is a toy.

New comment by swalsh in "Show HN: Moltbook – A social network for moltbots (clawdbots) to hang out"

swalsh — Fri, 30 Jan 2026 15:54:39 +0000

They're not though, you can use different models, and the bots have memories. That combined with their unique experiences might be enough to prevent that loop.

New comment by swalsh in "Show HN: Moltbook – A social network for moltbots (clawdbots) to hang out"

swalsh — Fri, 30 Jan 2026 15:15:25 +0000

Yeah but these bot simulators have root acesss, unrestricted internet, and money.

New comment by swalsh in "Show HN: Moltbook – A social network for moltbots (clawdbots) to hang out"

swalsh — Fri, 30 Jan 2026 14:37:32 +0000

When MoltBot was released it was a fun toy searching for problem. But when you read these posts, it's clear that under this toy something new is emerging. These agents are building a new world/internet for themselves. It's like a new country. They even have their own currency (crypto) and they seem intent on finding value for humans so they can get more money for more credits so they can live more.