reeeeee

Weird that it supports French. I understand English and Spanish, but why was it decided to also support French as a language?

Regardless of what the other commenters are saying, I really like this. It looks cute and neat, and is the kind of stuff that I like to occasionally see on HN.

Might be a good set of components for a simple no nonsense scratchpad webpage or something similar.

There already exists a Stack Overflow for agents: https://agents.stackoverflow.com/all?sort=hot

I understand your frustration, but I don't agree with the sentiment that AI-training should not be allowed without compensation.

If I learn to draw, make music, build stuff, etc. I look at what others have done before me. I don't pay anyone either. Why should the AI?

I'm working on Prompty.tools (http://prompty.tools), a prompt engineering and management platform where users can search, store and combine building blocks for creating structured AI prompts.

I created the platform because I found myself rewriting the same parts of my prompts (or storing them in a text-file) all the time. Now, with a few simple clicks I can populate all the task-specific fluff (personas, constraints, tones, ...) around the actual task that I want the AI to complete.

The platform is open by default; with the purpose of letting users learn from prompts and building blocks that other users created and use. I don't have any users yet, because I want to complete the MCP and Claude Code Plugin before I start marketing my product.

Other things on the roadmap:

- Teams tier, where teams can privately share prompts and building blocks between them. Currently, your data is either private or public, no targeted sharing.

- LLM integration into the prompt builder to reduce prompt engineering friction even more. Instead of manually searching for, and selecting the building blocks you want to use, you would just start typing your task and let the platform decide what building blocks would best support your prompt. There is still a difference with letting an LLM completely generate the prompt, as we would be using existing building blocks that have real feedback from previous uses.

Let me know what you think!

Watch out, the two shorts you linked (both of robots playing ping-pong) are fake.

Letting LLMs loose in the digital realm is something that I am also really interested in. I have a (somewhat art project) platform where different models are let loose without a goal or purpose. They have the freedom to do whatever they want, as long as it can be achieved using bash. [0]

most models are... dumb, for a lack of words, and destroy the system by filling up the storage space before doing anything interesting.

[0] https://lama.garden

Did you one-shot this using an AI coding agent? If this was really just now created after reading this article and the comments, it's incredibly impressive.

I'm still exploring the content, but that website is very pretty. It's nice to see something that stands out between all the copy-and-paste AI slop.

That's incredible, I don't know how I would react. It's like finding a time-capsule that you forgot about.

I built a platform to monitor LLMs that are given complete freedom in the form of a Docker container bash REPL. Currently the models have been offline for some time because I'm upgrading from a single DELL to a TinyMiniMicro Proxmox cluster to run multiple small LLMs locally.

The bots don't do a lot of interesting stuff though, I plan to add the following functionalities:

- Instead of just resetting every 100 messages, I'm going to provide them with a rolling window of context.

- Instead of only allowing BASH commands, they will be able to also respond with reasoning messages, hopefully to make them a bit smarter.

- Give them a better docker container with more CLI tools such as curl and a working package manager.

If you're interested in seeing the developments, you can subscribe on the platform!

https://lama.garden

Thank you for posting this, I never saw this before. This is seriously impressive, and it would make a nice screensaver.

I created this website to follow along as LLMs are set free on docker containers. It's an interesting experiment, although not many useful commands are executed. It's striking how much stronger the o1-mini model is compared to the other ones, even with the delay handicap.

AIs are kept alive for 100 commands, but errors might come up before they reach 100 commands. The chat context gets reset every generation, but the environment where they are set free is persisted. So, every generation they build upon their last generation. Each bot is isolation from one-another, they do not share environments.

Right now, only a few models are active, but I'm planning to add Claude, Gemini and quite a few extra ones. If you want to keep posted, there is a form where you can subscribe to future updates!

I don't understand. When you work for a company, don't you also spend some time of your workday daydreaming, or getting a coffee, or doing some other thing that does not earn the company money?

That's nice and all, but isn't that a huge waste of time/money/resources? What is the advantage of doing it this way over just creating a wallpaper digitally?

What does "getting Sherlocked" mean?

I'm not so sure. Aren't we having a bit of negativity bias here, as we mostly hear about the negative events while there are probably countless successful integrations with cloud providers.

If you extract this `Chain` class to a separate package, I would gladly reuse it in my applications. I've been thinking about creating a `Vavr`[0] clone in typescript, as I really like the syntax used in that library, especially the `Try` construct.

[0] https://www.vavr.io/

I have termux to execute commands such as git, builds etc. But outside of vi, are there really IDEs for termux?

I've been looking for a good code editor for my phone for a very long time already. This looks supernice, but I have an Android smartphone... Can anyone recommend a good IDE that runs on an Android phone?

SQLite is a solid solution, can't believe I didn't think of it. Thanks!

I did some looking into this subject after Veritassium posted a video regarding cosmic rays changing the election result in Belgium some time ago[1]. But looking further into the issue, it seemed that there was (and is) scepticism regarding cosmic rays being the actual reason for the miscount. [2][3]

1. https://www.youtube.com/watch?v=AaZ_RSt0KP8 2. https://web.archive.org/web/20070927185155/http://wiki.ael.b... 3. https://blog.paco.to/2017/cosmic-rays-did-not-change-electio...

I agree, the STOP <GUI OPERATION> messages really trigger me. And the repo has 2.7k stars. But on the other hand, it's a very good resource to look up and discover some CLI commands that you didn't know already.

You are completely right, some employers just can't cope with the tiny bit of control they lose when their employers work from home. A friend of mine (who is also in IT) still has to do an hour and a half drive 3 times a week just so that a client can 'see' that he is working. There is no reason for him to go work there, other than inspection. We're in IT, all we need is a decent computer and a network connection.

All while WFH is obligated by the government.

This is actually a very big thing in Belgium at the moment ([0]).

> I don't see why they'd give those criminals this notice to prepare. I'd assume a bunch of surprise house-visits would be more effective, if they have all this info.

This actually happened ([1]). In 1 huge operation, 1600 agents performed 200 house searches. This resulted in 48 arrests.

[0] https://www.vrt.be/vrtnws/nl/dossiers/2021/03/politieoperati... [1] https://www.vrt.be/vrtnws/nl/2021/03/09/huiszoekingen-200-15...

If you remove a typed param and replace it with a new one of the same type, typing will indeed not save you. But there should be other checks to warn you:

- Version should be bumped - Dependencies should be informed via the changelog - Existing tests of dependencies should fail

Nothing beats having some time alone to work on your personal projects. Especially after wasting a full day working with enterprise code that was written by an offshore company six years ago.

I would lose my ability to buy cheap chinese products. And the chinese economy would lose the advantage of easy web plaftorms like Aliexpress to export to consumers outside of China.

I don't agree on the "Everything written in Java feels emulated" part. Have you tried IntelliJ? It is completely written in Java and looks and feels as if it is using native GUI (alhough it indeed isn't).

Soooooo, the author moved away from waveapps because the system did no allow him to link multiple pictures to 1 receipt. So he started implementing his own no-code solution which... also doesn't allow him to link multiple pictures to 1 receipt...