Hacker News: outofpaper

New comment by outofpaper in "Microsoft announces Scout, an autonomous AI agent built on OpenClaw"

outofpaper — Tue, 02 Jun 2026 22:34:48 +0000

It's got a target audience.

New comment by outofpaper in "Gmail thinks I'm stupid, so I left"

outofpaper — Tue, 02 Jun 2026 22:32:17 +0000

It's almost as though someone was put in charge of AI growth and all they care about is token burn.

New comment by outofpaper in "Preparing for KDE Plasma's Last X11-Supported Release"

outofpaper — Tue, 02 Jun 2026 18:19:45 +0000

Time to fork and move on...

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

outofpaper — Mon, 04 May 2026 23:08:08 +0000

Notepad++ is not registered with the USPTO (U.S. Patent and Trademark Office). Searches around will turn up nothing in the U.S. database. The name is trademarked in France (via INPI, the French patent office), which is why the maintainer has been able to send cease-and-desist notices in recent cases (e.g., the unauthorized “Notepad++ for Mac” site).

In the U.S. its only covered by common-law trademark rights from long use, as there’s no federal registration.

New comment by outofpaper in "Using “underdrawings” for accurate text and numbers"

outofpaper — Mon, 04 May 2026 10:33:53 +0000

What's amazing is that they even can fairly reliably appear to count characters. I mean we're talking about systems that infer sequences not character counters or calculators. They are amazing in unrelated ways and we need to accept this so we can use them effectively.

New comment by outofpaper in "Measuring Claude 4.7's tokenizer costs"

outofpaper — Fri, 17 Apr 2026 19:04:40 +0000

That's why open models are going to win in the long run.

New comment by outofpaper in "Claude Code Routines"

outofpaper — Tue, 14 Apr 2026 17:52:35 +0000

Yes but much less efficiently. Having LLMs handle automation is like using a steam engine to heat your bath water. It will work most of the time but it's super inefficient and not really designed for that use and it can go horribly wrong from time to time.

New comment by outofpaper in "Nvidia CEO Jensen Huang says 'I think we've achieved AGI'"

outofpaper — Mon, 23 Mar 2026 23:29:35 +0000

It's just hard for us to see its grand plans.

New comment by outofpaper in "CLI RSS/Atom feed reader inspired by Taskwarrior, synced using Git"

outofpaper — Sun, 08 Mar 2026 23:04:54 +0000

If anything a CLU, a Command Line Utility would be the best thing to call the small programs that both van be run as one offs from the command line and have their output piped to other Command Line Utilities... I don't know why the term isn't being used more. CLU keep it simple. CLIs are a catch all from every single CLU up to MidnightCommander, Zork, Mosh, and OpenCode.

New comment by outofpaper in "The human.json Protocol"

outofpaper — Sun, 08 Mar 2026 22:58:50 +0000

To the average person ab public key is about as comprehensible as JSON.

New comment by outofpaper in "Wikipedia was in read-only mode following mass admin account compromise"

outofpaper — Thu, 05 Mar 2026 20:48:17 +0000

Why would anyone test in production???!!!

New comment by outofpaper in "History of the Graphical User Interface: The Rise (and Fall?) Of WIMP Design"

outofpaper — Tue, 03 Mar 2026 14:26:16 +0000

It's sucrose to being a good sweet article. Really though it should be used as a draft for something that wasn't just vibed. Eg fix the mice and loose the sparks from cutting wood.

New comment by outofpaper in "Pi – A minimal terminal coding harness"

outofpaper — Tue, 24 Feb 2026 23:12:08 +0000

A harness is a collection of stubs and drivers configured to assist with automation or testing. It's a standard term often used in QA as they've been automating things for ages before Gen Ai came on to the scene.

New comment by outofpaper in ""Token anxiety", a slot machine by any other name"

outofpaper — Mon, 16 Feb 2026 20:41:33 +0000

??? I'm pretty sure you know what the differences are. Go touch grass and tell me it's the same as looking at a plant on a screen.

Dealing with organic and natural systems will, most of the time, have a variable reward. The real issue comes from systems and services designed to only be accessible through intermittent variable rewards.

Oh, and don't confuse Claude's artifacts working most of the time with them actually optimizing to be that way. They're optimizing to ensure token usage. I.E. LLMs have been fine-tuned to default to verbose responses. They are impressive to less experienced developers, often easier to detect certain types of errors (eg. Improper typing), and will make you use more tokens.

New comment by outofpaper in "I’m joining OpenAI"

outofpaper — Mon, 16 Feb 2026 06:00:44 +0000

Exactly! The whole point of personal agents is that the data is yours and it's where you want it not in someone's cloud. What harness you use to work with this should be a matter of preference and not one of lock in.

New comment by outofpaper in "OpenAI should build Slack"

outofpaper — Sun, 15 Feb 2026 06:01:46 +0000

Lol it aas an admirable attempt at something new. I loved the interesting blend of messaging and document creation. It the code still lives on as an archived open project btw.

https://github.com/apache/incubator-retired-wave

New comment by outofpaper in "Show HN: LocalGPT – A local-first AI assistant in Rust with persistent memory"

outofpaper — Sun, 08 Feb 2026 10:58:32 +0000

As misleading. Lots of their marketing push or at least thr ClawBros pitch it as running local on your MacMini.

New comment by outofpaper in "Show HN: LocalGPT – A local-first AI assistant in Rust with persistent memory"

outofpaper — Sun, 08 Feb 2026 10:57:22 +0000

Horrible. Just because you have code that runs not in a browser doesn't mean you have something that's local. This goes double when the code requires API calls. Your net goes down and this stuff does nothing.

New comment by outofpaper in "Microsoft open-sources LiteBox, a security-focused library OS"

outofpaper — Fri, 06 Feb 2026 18:20:05 +0000

What's dumb, on top of everything, is needing to store non special standard operating procedures in specific AI folders and files when wanting to work with AI tooling.

New comment by outofpaper in "Claude Opus 4.6"

outofpaper — Fri, 06 Feb 2026 10:38:07 +0000

A real test is synthesizing 100,000 sentences of this slect random ones and then inject the traits you want thr LLM to detect and describe, eg have a set of words or phrases that may represent spells and have them used so that they do something. Then have the LLM find these random spells in the random corpus.