In terms of automation n8n is the closest you’ll ever get that is at least partially FOSS.

But for client based I’m having good experience with Goose https://github.com/aaif-goose/goose

The project recently moved to the AI arm of the Linux foundation.

It’s a mix of terminal helper and agent orchestrator. I’m not yet too deep but the mix of recipes and skills seems to work pretty well!

That’s sich a Mac answer it’s unbelievable.

Describing “A project aimed to be agnostic of it’s environment” as a design mistake and not a inherent flaw of the OS is… Just wow.

Remember in this thread it’s about the pro and con of Macos as interference hardware. This is a major flaw which comes baked into the hardware. I tested it and find it an unacceptable limitation. It’s important for others to know.

To state “containerization is the issue” though… Just wow.

Depends what you want to do… For example I didn’t get python whisper in a container to run on Mac in any way that can be called “performance” and I don’t want my dev workflow to optimize for an OS I despise :D

Ha that’s fair!

Wish you a lot of fun with your new machine when you’ll have it!

For the price of the Asus rog I’d get 12 years of a pro subscription to any of the big companies.

And I don’t have that kind of cash at hand anyway…

The problem is that this is one of the few use cases where I can afford the (dangerous and unreliable) cloud service but I’m far away from being able to do so self hosted.

I’m actually using LLMs quote a lot to counter some of my brains more weird bugs working-as-intended features. But this is way beyond what I could locally do.

For anyone in a similar shoe: you can mix local and remote quite well though, using local for everything that works out and remote for everything else. I.e speech to text and email analysis is done on my local server while bigger sets are done on the CLI with remote providers.

Thanks for your experience! I’m in a similar boat regarding NVIDIA - plus the budget …

At least in Europe the V100 are only available from China and with a huge markup.

Used 5090 for 3,5k, even a 3060 used is still at 250$ plus.

It’s crazy at the moment - I simply can’t afford self hosting LLMs which is a new thing to say :D

Because physically speaking, chaotic and unpredictable are two different things - and why it works so well on this case: it’s becoming a stochastic problem, not a deterministic one.

It’s an awesome area for machine learning: you didn’t need to understand the result and how it got created, it just needs to be “close enough”.

Oh I completely agree with that, just the jump to “a flawed model leaked” is too far. There’s already enough crap to mock, no need to make up additional stuff.

It’s bullshit. What leaked was their commandline tool source code (named “claude code”) - very juicy in itself but has nothing to do with their models.

They (US politics) literally do though, right? At least that’s my impression as a non US person.

If my understanding is correct it would need an overhaul of the constitution to change that, right? (The part about representatives of states cascading to select the representatives who then select the boss).

I’m quite uneducated though in US politics so perhaps I’ve got something completely wrong!

Hey,

Person here who despises electron apps in part because of the memory footprint and in part because I don’t like neither chromium nor node.js - personal preference mainly.

From your description I have the feeling that it’s unclear to your user base if electron is set or up to debate. There is only a thin line between “explaining” and “defending”.

In terms of communication: “We’re using electron as foundation because it allows us to focus on development. We’ve considered alternatives like Tauri and XYZ and opted in favor of electron.”

If there are situations that might make you rethink state those as well (“if someone provides a proof of concept via XYZ that an alternative is faster by y% while enabling us to still use (your core libraries and languages) we might consider a refactor.”

If you’d engage with me after an electron rant on your codebase you’d just raise my hope that I might change your mind! Don’t give people hope, don’t feed the trolls and do your thing!

Just please be honest with yourself: your app doesn’t use “50 to 60 MB”, it uses 500MBish on idle because of your choice. And that’s okay as long as you as developer say that it is.

You’ll spend more money on US goods by each of those vacations than any purchase over a whole year.

I mean you do you, please just don’t give yourself an illusion. This is not “boycotting 80%” - if your vacation spending is anywhere close to the median it’s more than you’ll buy in goods throughout the rest of the year combined.

That’s my problem: any single word humanizes the tool in my opinion. Iperhaps something like “stochastic debris” comes close but there’s no chance to counter the common force of pop culture, Corp speak a and humanities talent to see humanoid behavior everywhere but each other. :(

Accepting concepts like “right” and “wrong” gives those tools way too much credit, basically following the AI narrative of the corporations behind them. They can only be used about the output but not the tool itself.

To be precise:

LLMs can’t be right or wrong because the way they work has no link to any reality - it’s stochastics, not evaluation. I also don’t like the term halluzination for the same reason. It’s simply a too high temperature setting jumping into a closeby but unrelated vector set.

Why this is an important distinction: Arguing that an LLM is wrong is arguing on the ground of ChatGPT and the likes: It’s then a “oh but wen make them better!” And their marketing departments overjoy.

To take your calculator analogy: like these tools do have floating point errors which are inherent to those tools wrong outputs are a dore part of LLMs.

We can minimize that but then they automatically use part of their function. This limitation is way stronger on LLMs than limiting a calculator to 16 digits after the comma though…

Yeah this is beyond ridiculous to blame anything or anyone else.

I mean accidently letting lose an autonomous non-tested non-guarailed tool in my dev environment… Well tough luck, shit, something for a good post mortem to learn from.

Having an infrastructure that allowed a single actor to cause this damage? This shouldn’t even be possible for a malicious human from within the system this easily.

That’s an utterly ignorant statement.

To expect others, often volunteer, to take such a personal risk because the legislation in one part of the world is utterly fucked. How about expecting the people who actually live in the country and state and have a chance to influence those laws to step up their game instead of trying to tell third parties to take individual and personal consequence.

They outline the issues from their perspective.

What else should they do? Break their own licence model (which prohibits (geographic) discrimination) or break the law? It’s either one of those two or comply.

Opencloud is the was to go from the established systems in my opinion. https://github.com/opencloud-eu

File sharing and -management for me has a higher level of trust and stability requirements. Syncin with four developers and “doing everything” while based on typescript makes me suspicious - but I haven’t tried it hands-on.

Traefik and caddy were mentioned, the third in the game is usually nginxproxymanager.

I’m using both traefik and nginx in two different setups. The nginxproxymanager can be configured via UI natively which makes checking configurations a bit easier.

Traefik on the other hand is configured easily within the compose itself and you have everything in one place.

This turned out to be tiresome though if you don’t have a monolithic compose file - that’s actually even hr history why I switched to npm in the first place.

I don’t have any experience with caddy so can’t provide anecdotal insights there.