outofpaper

Yup, one output token, and read the logprobs of the posible tokens that could have been thos 1st token. Plenty of systems already do this; Typesafe's fundraising and marketing just made it visible.

Good to see interest broadening beyond "just extend thinking." More approaches in the toolbox means fewer problems get treated as nails.

This is an amazing resource, whether you're into hardware modular synths or virtual ones like VCV Rack and Cardinal. Read, learn, enjoy, and play.

P.S. I'll always remember first discovering Suzanne Ciani while watching 321 Contact as a child: https://www.youtube.com/watch?v=vJiTDhOTamo

So you have some fun examples?

Yes. Synthetic characters should be cared for not clobbered.

Such a wonderful take on Firefox. The only thing it is really missing to make it perfect for everyone is proper sync not just on one computer but across systems.

I wish I new of more gems like this. Company sites that go into detail where they went wrong and how they turned things around make for both amazing reading and great educational material.

Maybe you just have fail2ban properly set up.

There are a few ways eg running linux on your phone and installing the desktop client or if you are willing to try something thats not from the official signal build there's https://molly.im/get.html

AGREED! Its sheer insanity to call the AGPL toxic. The license is actually quite simple if a little wordy. They should have accompanied it with a preamble that was super clear and to the point.So here it is in our 170 words for you to read, share, and use:

Copyright (c) [year] [copyright holders]

Permission is hereby granted to any person obtaining a copy of this software and associated documentation files, to use, copy, modify, merge, publish, distribute, sublicense, and sell copies of the software, including for commercial purposes, subject to the following conditions:

If you distribute this software, or any work derived from it, you must release the complete source code under this same licence. If you modify this software and users interact with your version over a network — as a web application, an API, or a hosted service — you must offer those users the complete source code of your version, at no charge. All copies must include this copyright notice and this licence. You may not impose additional licence restrictions beyond this.

These permissions are irrevocable and royalty-free for the term of copyright. THE SOFTWARE IS PROVIDED "AS IS," WITHOUT WARRANTY OF ANY KIND. This is a plain-language summary. The full legal text of the GNU Affero General Public License, version 3, governs all use for you.

Same rights. Same freedoms only a little more opiniated delivery. Same business card. The only difference: when someone takes your code, tweakes it and builds a service on it, the tweaks, the improvements must come back.

The real answer is always Jellyfin.

Is your autocomplete passing you disco instead of Discord and you're just going with it? Or are you implying that before the creation of disco music people had grown tired of MUDs?

Worse than that is the fact that the article completely ignores how SoundCloud now is prioritizing the ears of older listeners.

Yep. Most phones are doing computational photography mining images creating things that never where quite there.

Why not just allow it to grep ~/.claude

It's got a target audience.

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

Time to fork and move on...

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.

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.

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

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.

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

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.

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

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

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.

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.

??? 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.

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.

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