Hacker News: je42

New comment by je42 in "Why are we still using Markdown?"

je42 — Sat, 04 Apr 2026 07:43:16 +0000

Writing mark down linter, i am i nterested in - if you think that you requirements for markdown formatting could be encoded in (relatively) simple rules?

New comment by je42 in "Cook: A simple CLI for orchestrating Claude Code"

je42 — Thu, 19 Mar 2026 05:24:50 +0000

Had a quick look. Stumbled upon the markdown format smd.

Was wondering if using front-matter instead of a "custom" encoding for parseble data was considered?

New comment by je42 in "Switch to Claude without starting over"

je42 — Sun, 01 Mar 2026 09:48:31 +0000

Interesting - what kind of structural issues have you encountered?

Is these more related to the existing source code or is this a bad pattern thar you would never do regardless of the existing code?

New comment by je42 in "Nano Banana 2: Google's latest AI image generation model"

je42 — Fri, 27 Feb 2026 12:59:10 +0000

In Chess this has been going on for a while. Story of humans playing Chess is still entertaining - while AI making amazing moves seems to be less news worthy in my perception.

New comment by je42 in "How I use Claude Code: Separation of planning and execution"

je42 — Sun, 22 Feb 2026 09:13:06 +0000

There are frameworks like https://github.com/bmad-code-org/BMAD-METHOD and https://github.github.com/spec-kit/ that are working on encoding a similar kind of approach and process.

New comment by je42 in "We put Claude Code in Rollercoaster Tycoon"

je42 — Sun, 18 Jan 2026 07:26:32 +0000

Claudes search tool uses Ripgrep , which is embedded in Claude.

New comment by je42 in "Google: Don't make "bite-sized" content for LLMs"

je42 — Sun, 11 Jan 2026 17:16:22 +0000

Which searchengine is OpenAI using?

New comment by je42 in "I'm a laptop weirdo and that's why I like my new Framework 13"

je42 — Fri, 26 Dec 2025 13:50:44 +0000

you can switch the ports pretty quickly on framework laptops.

New comment by je42 in "Scaling LLMs to Larger Codebases"

je42 — Tue, 23 Dec 2025 20:27:46 +0000

If claude ignores your claude.md you can force it to read via settings to cat it every session start for example.

New comment by je42 in "Show HN: Bolt – A super-fast, statically-typed scripting language written in C"

je42 — Tue, 12 Aug 2025 05:12:34 +0000

I think I was looking for both error / exception handling within the language and across the C api.

New comment by je42 in "Show HN: Bolt – A super-fast, statically-typed scripting language written in C"

je42 — Mon, 11 Aug 2025 02:17:20 +0000

Nice language! I am wondering how error handling / exceptions works in bolt?

Quickly scanned the programming guide - but wasn't able to find it. Did i miss a section?

New comment by je42 in "Mastercard deflects blame for NSFW games being taken down"

je42 — Mon, 04 Aug 2025 13:25:26 +0000

Steam added recently a rule 15th what you should not publish:

15. Content that may violate the rules and standards set forth by Steam’s payment processors and related card networks and banks, or internet network providers. In particular, certain kinds of adult only content.

See discussion here for example: https://steamcommunity.com/discussions/forum/0/6019100814124...

New comment by je42 in "We're all CTO now"

je42 — Sat, 05 Jul 2025 14:33:39 +0000

Have you tried to add more guidelines ? Similar to documentation you would provide to new members of the team

New comment by je42 in "Apptainer: Application Containers for Linux"

je42 — Thu, 26 Jun 2025 21:29:41 +0000

How do you guys use Lua modules?

New comment by je42 in "Accumulation of cognitive debt when using an AI assistant for essay writing task"

je42 — Wed, 18 Jun 2025 07:16:22 +0000

However, I believe it is quite an assumption that a setup with time pressure reflects "normal" usage of a LLM.

New comment by je42 in "Accumulation of cognitive debt when using an AI assistant for essay writing task"

je42 — Tue, 17 Jun 2025 10:23:11 +0000

> All participants were then reassured that though 20 minutes might be a rather short time to write an essay, they were encouraged to do their best.

Given that the task has been under time pressure, I am not sure this study helps gauging the impact of LLMs in other contexts.

When my goal is to produce the result for a specific short term task - I maximize tool usage.

When my goal is to improve my personal skills - I use the LLM tooling differently optimizing for long(er) term learning.

New comment by je42 in "Accumulation of cognitive debt when using an AI assistant for essay writing task"

je42 — Tue, 17 Jun 2025 10:09:31 +0000

I find that LLM extremely good in training such language skills by using following process:

a) write a draft yourself.

b) ask the LLM to correct your draft and make it better.

c) newer LLMs will explicitly mention the things they corrected (otherwise ask for being explict about the changes)

d) walk through each of the changes and apply the ones you feel that make the text better

This helped me improving my writing skills drastically (in multiple languages) compared to the times where I didn't have access to LLMs.

New comment by je42 in "Show HN: A new programming language inspired by Go, no LLVM"

je42 — Sun, 01 Jun 2025 06:35:25 +0000

Looking at the co routine example. Does the function type implicitly change when using co.sleep in the function body?

New comment by je42 in "Show HN: Evolved.lua – An Evolved Entity Component System for Lua"

je42 — Wed, 21 May 2025 19:21:32 +0000

One alternatives I like is https://bakpakin.github.io/tiny-ecs/doc/

New comment by je42 in "ChatGPT Helps Students Feign ADHD: An Analogue Study on AI-Assisted Coaching"

je42 — Tue, 20 May 2025 21:24:45 +0000

There are alternatives that are not on the EU list for controlled substances. Like for example:

https://en.wikipedia.org/wiki/Lisdexamfetamine