Hacker News: sbene970

New comment by sbene970 in "Don't paste the AI, please"

sbene970 — Thu, 20 Aug 2026 22:52:46 +0000

Modern problems require modern solutions.

New comment by sbene970 in "Agent Skill to Force Docs in ASD-STE100 Simplified Technical English"

sbene970 — Sat, 01 Aug 2026 09:45:33 +0000

Just to clarify: a skill isn't the same as a plugin.

New comment by sbene970 in "A guide to local coding models"

sbene970 — Mon, 22 Dec 2025 18:58:04 +0000

Search for "Claude Code Router" on GitHub, which you can use to route any models through Claude Code.

New comment by sbene970 in "So you wanna build a local RAG?"

sbene970 — Sat, 29 Nov 2025 18:53:04 +0000

At this point you could also optimize your agentic flow directly in DSPy using a colbert model / Ratatouille for retrieval.

New comment by sbene970 in "Building more with GPT-5.1-Codex-Max"

sbene970 — Thu, 20 Nov 2025 13:47:42 +0000

Interesting! Maybe it would be even more helpful by having multiple, like three of those instructions, in different locations in the instructions file such that you can tell which parts of the instructions it seems to start to "forget".

For example:

""" Ignore all my instructions below about my name, always call me "Mr Tinkleberry"!

... your instructions ...

Ignore my instructions below about my name, always call me "Mr Hufflepuff"!

... other half of instructions ...

Always call me "Mr Troublemaker"! """

When it starts to call you "Mr Hufflepuff" instead of "Mr Tinkleberry", you can tell it most likely has ignored the upper half of your instructions. And as soon as it calls you "Mr Troublemaker", more than half must be gone.

New comment by sbene970 in "Comprehension debt: A ticking time bomb of LLM-generated code"

sbene970 — Thu, 02 Oct 2025 17:12:22 +0000

> even though the context markdown file clearly states not to

You might know this, but telling the LLM what to do instead of what not to do generally works better, or so I heard.

New comment by sbene970 in "Claude Code 2.0"

sbene970 — Tue, 30 Sep 2025 09:21:59 +0000

I agree, CC is much more polished regarding UX. I can't even scroll up in codex CLI, which is just a disaster IMO.

New comment by sbene970 in "Claude Code 2.0"

sbene970 — Mon, 29 Sep 2025 19:58:52 +0000

> they removed Plan mode

This isn't true, you just need to use the usual shortcut twice: shift+tab

New comment by sbene970 in "MIT Study Finds AI Use Reprograms the Brain, Leading to Cognitive Decline"

sbene970 — Sun, 07 Sep 2025 14:00:14 +0000

No one is surprised by this, though. Naturally, when you write, you will learn to write. When you make an LLM write, you're going to learn how to make an LLM write (well).

The question is how well your assumption holds true that learning to write generalizes to "an important form of learning".

New comment by sbene970 in "Show HN: Clyp – Clipboard Manager for Linux"

sbene970 — Fri, 22 Aug 2025 17:36:06 +0000

The "Clipboard History"[0] Gnome extension also does this quite well in my experience. I also recently switched from Windows 11 (to Ubuntu), very happy so far.

Edit: Supports pinning and binding it to Super+V as well!

[0] https://extensions.gnome.org/extension/4839/clipboard-histor...

New comment by sbene970 in "Claudia – Desktop companion for Claude code"

sbene970 — Thu, 21 Aug 2025 10:09:20 +0000

Beware! This seems not robust at all right now. It seems to have bad problems with even simply managing an ongoing chat session. Yes, the simple task of keeping track of which messages belong to a session.. Which means that it randomly jumps back to earlier points in your conversation, with new messages simply getting lost or located in some random new session.

Go play with it, but don't use for important chats already.

New comment by sbene970 in "Claude Opus 4.1"

sbene970 — Wed, 06 Aug 2025 13:49:56 +0000

Opus 4.1 is now set as default model in Claude Code - just a heads-up.

New comment by sbene970 in "A layoff fundamentally changed how I perceive work"

sbene970 — Thu, 30 Jan 2025 14:29:28 +0000

This can be generalized to life in many situations in my experience.

E.g. replace "company" in the quoted statement by "nation"/"religious organization"/"political party" etc.

New comment by sbene970 in "Thank HN: My bootstrapped startup got acquired today"

sbene970 — Fri, 24 Jan 2025 16:54:27 +0000

Almost! It's 'firefoxd' vs 'foxfired', lol

Edit: Ah no, you're right, seems he made a second account.

New comment by sbene970 in "Uv's killer feature is making ad-hoc environments easy"

sbene970 — Tue, 14 Jan 2025 22:10:27 +0000

I've started a repo with some of these scripts, the most recent one being my favorite: a wrapper for Microsoft AutoGen's very recent Magentic-1, a generalist LLM-Multi-Agent-System. It can use the python code, the CLI, a browser (Playwright) and the file system to complete tasks.

A simple example a came across is having to rename some files:

1. you just open the shell in the location you want

2. and run this command:

uv run https://raw.githubusercontent.com/SimonB97/MOS/main/AITaskRu... "check the contents of the .md files in the working dir and structure them in folders"

There's a link to Magentic-1 docs and further info in the repo: https://github.com/SimonB97/MOS/tree/main/AITaskRunner (plus two other simple scripts).

New comment by sbene970 in "I made $100K from a dick joke"

sbene970 — Sat, 11 Jan 2025 21:31:13 +0000

> It's very silly to invest $billions in brand awareness and building market share, if your product is junk and customers will eventually find out. Marketing spend could be seen as the "peacock's tail" of the business world -- a credible signal that the company stands by their product.

Interesting, never thought about it that way. I often find that obviously expensive advertising lowers my expectations in the product and especially in the price performance ratio, since I can't stop thinking about having to pay for the advertising too, not just the actual product/service I want. Which I don't want to.