Hacker News: SilverSlash

New comment by SilverSlash in "Half-Baked Product"

SilverSlash — Fri, 03 Jul 2026 12:31:07 +0000

This was such a great read! Thank you! Too bad Oven Inc never got more headcount. Otherwise the engineers could've had a day hackathon week while the managers and founder went to a retreat for a strategy offsite.

New comment by SilverSlash in "Meta building cloud business to sell excess AI capacity"

SilverSlash — Thu, 02 Jul 2026 12:28:56 +0000

Nah, it's a guy named Matt Deitke and he was 24 at the time.

New comment by SilverSlash in "Meta building cloud business to sell excess AI capacity"

SilverSlash — Thu, 02 Jul 2026 11:26:03 +0000

So have they just given up on llama then? What happened to the 25 year old Zuck paid $250M for?

New comment by SilverSlash in "Historical memory prices 1960-2026"

SilverSlash — Mon, 29 Jun 2026 02:39:38 +0000

This is extremely misleading and not very useful. It makes little sense to use pricing per GB during decades when RAM was at most in MBs. In that case, why not talk about price per TB or PB? Then the line will look pretty much flat and horizontal.

New comment by SilverSlash in "My Mathematical Regression"

SilverSlash — Tue, 23 Jun 2026 03:08:59 +0000

I can definitely relate. My brain also wants to take the path of least effort now, even for simple things like adding two numbers which I could do very quickly in my head in my college days.

And with AI the path of least (initial) effort seems to be to just ask the model to solve it. It might get it wrong and then I'll prompt it again and again. But each individual prompt is fairly low effort on my part. Whereas coming up with the right solution myself might've taken less time but the initial effort is a lot more.

Last year I used to romanticize about building at least 1 thing each month completely by hand without any LLM coding help. The last such project I worked on was 6 months ago so sadly it's not going so well.

New comment by SilverSlash in "Codex logging bug may write TBs to local SSDs"

SilverSlash — Mon, 22 Jun 2026 09:05:10 +0000

> Difference is, humans learn from their mistakes.

Great! So next time the human will prompt the agent to watch out for and avoid this bug.

New comment by SilverSlash in "Apertus – Open Foundation Model for Sovereign AI"

SilverSlash — Mon, 22 Jun 2026 02:22:37 +0000

lol the new "swiss banks". store all your dirty data in digital swiss lockers

New comment by SilverSlash in "Leaving Mozilla"

SilverSlash — Sat, 13 Jun 2026 12:43:31 +0000

damn! then what's happens at the EU where the "goals of the organization" are themselves to increase and champion bureaucracy?

New comment by SilverSlash in "There is a shadow hanging over this Fable thing"

SilverSlash — Sat, 13 Jun 2026 07:48:36 +0000

they already firmly in irrelevant territory

New comment by SilverSlash in "Apple reveals new AI architecture built around Google Gemini models"

SilverSlash — Tue, 09 Jun 2026 04:15:33 +0000

Very good. Just look at Gemma 4.

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

SilverSlash — Tue, 09 Jun 2026 03:00:47 +0000

I like the concept. It would indeed be good to have a modern component library with AI design tropes as I think the old components libs haven't caught up. But in this particular case I must say, a lot of the components here just look plain ugly.

New comment by SilverSlash in "Models.dev: open-source database of AI model specs, pricing, and capabilities"

SilverSlash — Sat, 23 May 2026 02:16:09 +0000

Useful concept but missing some obvious features like filtering on availability of tool calling or support for different modalities, etc.

New comment by SilverSlash in "Google changes its search box"

SilverSlash — Wed, 20 May 2026 08:27:35 +0000

I really like the agentic search feature that can keep you updated. Basically an ifttt but built into google search with an LLM on top.

New comment by SilverSlash in "Tesla tells HW3 owner to 'be patient' after 7 years of waiting for FSD"

SilverSlash — Fri, 17 Apr 2026 23:51:25 +0000

Was this a Tesla with HW3 or HW4? Also, was it in the US or outside the US?

New comment by SilverSlash in "We moved Railway's frontend off Next.js. Builds went from 10+ mins to under 2"

SilverSlash — Wed, 08 Apr 2026 09:10:15 +0000

I hadn't heard of TanStack but a quick look at their website doesn't inspire confidence tbh. I mean, just take "TanStack Pacer".

It provides such things as:

```

import { Debouncer } from '@tanstack/pacer' // class

const debouncer = new Debouncer(fn, options)

debouncer.maybeExecute(args) // execute the debounced function

debouncer.cancel() // cancel the debounced function

debouncer.flush() // flush the debounced function

```

Why? Just why do you need to install some "framwork" for implement debouncing? Isn't this sort of absurdism the reason why the node ecosystem is so insecure and vulnerable in the first place? Just write a simple debouncer using vanilla js...

New comment by SilverSlash in "We moved Railway's frontend off Next.js. Builds went from 10+ mins to under 2"

SilverSlash — Wed, 08 Apr 2026 09:04:40 +0000

As in, htmx is better? I haven't used it but last I looked into it I was extremely confused as to whether it was a meme, an actual framework, or both.

New comment by SilverSlash in "We moved Railway's frontend off Next.js. Builds went from 10+ mins to under 2"

SilverSlash — Wed, 08 Apr 2026 09:01:48 +0000

A lot of the LLMs are very familiar with next.js and vercel is also aggressively building an ecosystem around their tooling for LLMs. So I wonder if this problem will only be exacerbated when everyone using LLMs is strongly nudged (forced) to use next?

New comment by SilverSlash in "OpenAI says its new model GPT-2 is too dangerous to release (2019)"

SilverSlash — Wed, 08 Apr 2026 08:09:48 +0000

Nope. I've been working on this project for a couple of days now and things were mostly going well. A significant portion of the mvp backend and frontend was built and working. Then this one seemingly simple bug appeared and just totally stumped both Codex and Claude Code.

There was even another UI component (in the same file) which was almost the same but slightly different and that one was correct. That's what I copy pasted and tweaked when I fixed the problem. But for some reason the models were utterly incapable of making that connection.

With Codex and Claude Code I thought maybe because these agentic coding tools are trained to be conservative with tokens and aggressively use grep that they weren't looking at the full file in one go.

But with Gemini I used the web version and literally pasted that entire file + screenshots detailing what was wrong (including the other component which was rendering correctly) and it still couldn't solve it. It was bewildering.

New comment by SilverSlash in "OpenAI says its new model GPT-2 is too dangerous to release (2019)"

SilverSlash — Wed, 08 Apr 2026 04:21:56 +0000

That's hard to believe in my case. I tried a variety of prompts, 3 different frontier models, provided manual screenshot(s), the agent itself also took its own screenshots from tests during the course of debugging. Nothing worked. I have now fixed the bug manually after 15-20 minutes of playing around with a codebase where I don't know the language and didn't write a single line of code until now.

New comment by SilverSlash in "OpenAI says its new model GPT-2 is too dangerous to release (2019)"

SilverSlash — Wed, 08 Apr 2026 03:42:42 +0000

I understand how laughable that sounds when I say it out loud. But the reality is, when I'm in a state of 'Tell LLM what to do, verify, repeat', it's really hard to sometimes break out of that loop and do manual fixes.

Maybe the brain has some advanced optimization where once you're in a loop, roughly staying inside that loop has a lower impedance than starting one. Maybe that's why the flow state feels so magical, it's when resistance is at its lowest. Maybe I need sleep.