Hacker News: soleveloper

New comment by soleveloper in "Trademark violation: Fake Notepad++ for Mac"

soleveloper — Tue, 05 May 2026 09:50:18 +0000

NixPad++

But don't block on the name, you could release it under NejneobhospodařovávatelnějšíPad++ and people will download.

It'll be easy search & replace later once you settle on a name

New comment by soleveloper in "Uber Torches 2026 AI Budget on Claude Code in Four Months"

soleveloper — Fri, 01 May 2026 17:47:17 +0000

> Are they just copy/pasting their entire ticket description into Claude Code and having it iterate until they land on something that works?

"Their ticket" = that was AI generated. After which they will wait their AI generated PR be checked by an automated AI QA that will validate against the AI generated spec.

It feels like important metric of "corporate AI adoption" should be how effective the human in steering the AI.

IF THE HUMAN ISN'T EFFECTIVE, THE HUMAN NEEDS TO GO.

New comment by soleveloper in "A Faster Alternative to Jq"

soleveloper — Fri, 27 Mar 2026 21:54:13 +0000

I already can't remember jq syntax. Naming this jg just means I'll type one, instinctively use the other's syntax, and get an error anyway. It's a DX trap.

But I will admit, the new syntax makes a lot more sense.

New comment by soleveloper in "France's aircraft carrier located in real time by Le Monde through fitness app"

soleveloper — Fri, 20 Mar 2026 22:00:08 +0000

An intelligence satellite - which is not a super common utility nations have - will locate where the aircraft _was_ X hours ago, or at least many minutes ago. A constantly updated missile with a rather simple GPS tracker would benefit A LOT from a live location of its target.

New comment by soleveloper in "How will OpenAI compete?"

soleveloper — Thu, 26 Feb 2026 20:19:21 +0000

There are incredible authors who happen to be dyslexic, and brilliant mathematicians who struggle with basic arithmetic. We don't dismiss their core work just because a minor lemma was miscalculated or a word was misspelled. The same logic applies here: if we dismiss the semantic capabilities of these models based entirely on their token-level spelling flaws, we miss out on their actual utility.

New comment by soleveloper in "How will OpenAI compete?"

soleveloper — Thu, 26 Feb 2026 07:29:52 +0000

Treat LLMs as dyslexic when it comes to spelling. Assess their strengths and weaknesses accordingly.

New comment by soleveloper in "Claws are now a new layer on top of LLM agents"

soleveloper — Sat, 21 Feb 2026 20:54:28 +0000

Will that protect you from the agent changing the code to bypass those safety mechanisms, since the human is "too slow to respond" or in case of "agent decided emergency"?

New comment by soleveloper in "The path to ubiquitous AI (17k tokens/sec)"

soleveloper — Fri, 20 Feb 2026 20:28:40 +0000

Yes, and even holding couple of cartridges for different scenarios e.g image generation, coding, tts/stt, etc

New comment by soleveloper in "The path to ubiquitous AI (17k tokens/sec)"

soleveloper — Fri, 20 Feb 2026 13:03:22 +0000

There are so many use cases for small and super fast models that are already in size capacity -

* Many top quality tts and stt models

* Image recognition, object tracking

* speculative decoding, attached to a much bigger model (big/small architecture?)

* agentic loop trying 20 different approaches / algorithms, and then picking the best one

* edited to add! Put 50 such small models to create a SOTA super fast model

New comment by soleveloper in "The path to ubiquitous AI (17k tokens/sec)"

soleveloper — Fri, 20 Feb 2026 12:38:34 +0000

In 20$ a die, they could sell Gameboy style cartridges for different models.

New comment by soleveloper in "Show HN: Trained YOLOX from scratch to avoid Ultralytics (aircraft detection)"

soleveloper — Wed, 18 Feb 2026 11:58:45 +0000

Great write-up! There are so many directions you can take it to:

* By training on user data, you can source specific model data images, and then train & classify the airplane model. It might require another model, where only the bbox will be the input, together with distance/calculated measurements of the object ("pixel size"), and the orientation of the plane (side? front? belly?).

* Provide alerts/notification of special aircrafts like helicopters, military, airforce-1, etc'

* When bbox is detected, you can run super-resolution upscaling on the photo/stream of images

New comment by soleveloper in "Lessons from 14 years at Google"

soleveloper — Mon, 05 Jan 2026 08:49:47 +0000

This is a perfect example of a "bug" actually being a requirement. The travel industry faced a similar paradox known as the Labor Illusion: users didn't trust results that returned too quickly. Companies intentionally faked the "loading" phase because A/B tests showed that artificial latency increased conversion. The "inefficiency" was the only way to convince users the software was working hard. Millions of collective hours were spent staring at placebo progress bars until Google Flights finally leveraged their search-engine trust to shift the industry to instant results.

New comment by soleveloper in "Date bug in Rust-based coreutils affects Ubuntu 25.10 automatic updates"

soleveloper — Sun, 26 Oct 2025 07:35:23 +0000

Is it? I hope I won't step on somebody's else toes: GenAI would greatly help cover existing functionality and prevent regressions in new implementation. For each tool, generate multiple cases, some based on documentation and some from the LLM understanding of the util. Classic input + expected pairs. Run with both GNU old impl and the new Rust impl.

First - cases where expected+old+new are identical, should go to regression suite. Now a HUMAN should take a look in this order: 1. Cases where expected+old are identical, but rust is different. 2. If time allows - Cases where expected+rust are identical , but old is different.

TBH, after #1 (expected+old, vs. rust) I'd be asking the GenAI to generate more test cases in these faulty areas.

New comment by soleveloper in "Show HN: ModernBERT in Pure C"

soleveloper — Sun, 19 Oct 2025 07:57:38 +0000

Hey, cool initiative!

Worth mentioning in the title that it's CPU-only: >1200 tokens/s on a single thread is impressive.

Have you considered doing optimization iterations like nanogpt-speedrun? Would be interesting to see how far you can push the performance.

New comment by soleveloper in "Wtm (Worktree Manager): A simpler way to work with Git Worktrees"

soleveloper — Tue, 30 Sep 2025 15:43:40 +0000

How would you recommend using this for working with multiple agents? I'm thinking about scenarios where you might have several AI coding agents (or automated processes) that need to work on different branches simultaneously without stepping on each other's toes.

Any recommended workflow for coordinating multiple agents? For instance, handling naming conventions, cleanup strategies, or preventing race conditions when multiple agents try to create worktrees at the same time?

This seems like it could be really powerful for that use case, especially with the hook system for per-worktree setup.