jdright

any numbers to share? also, what inference engine do you use and with which api?

I use https://zedra.dev/ which supports a lot of agents, also uses GPUI but has mobile clients.

Agreed, ACP should be a minimum requirement on new agentic tooling. Hope this gets it, then I can try using my niche agent.

Mathematicians are a kind of programmers, the original ones.

not apples to apples. comparing official vs. pi.dev+openrouter and having slow times is more a openrouter issue. try comparing using official z.ai.

Not sure holding a break and making sure to release it to have a correct reading is any easier than something like this (if this is real).

as basic as needed, most of them don't even require this. They are not products and we know their limitations.

100% agree with this.

I have years of experience, but I never had the time (or will) to take on some _very minor nuisances_ or different areas of dev far from my day job expertise.

LLMs solved this. I produced about 12 different things that "I needed" to improve aspects of my life.

Each single took between a few hours to 3 days, and most of them I use daily, they are the most used applications (mobile, desktop and web) for my family.

It is a game changer.

Personalized custom software would never really reach critical mass, LLM enabled it, this is the age of personalized software, egosoftware, llmware.

The group that insists on keeping a community or software project 'non-political' often fails to recognize that this stance is itself a political position. They claim to want a neutral space, but what they really mean is that the existing political view does not align with their own. By dismissing other perspectives as 'political' while treating their own as neutral, they end up being both hypocritical and unwilling (or unable) to acknowledge that their opinions are political too.

I read this comment and the only thing I can think of is about the infamous Dropbox comment[1].

ps. I'm not saying this project has the same potential as Dropbox or otherwise.

[1] https://news.ycombinator.com/item?id=9224

awesome documentation, I'll try this. thank you!

Any idea if there is a way to run on 256gb ram + 16gb vram with usable performance, even if barely?

yes, that is a very usual way (known practices) of vendors applying specific optimizations for known things.

It is also part of the benchmarks game they play against each other.

jart putting Carmack and Musk at the same level is a bit sad and revealing, no wonder the downvotes.

You're wrong, obedient people are exactly the type that don't need unions, they are obedient and accept anything.

Unions are for people that don't accept anything and know that they are a target taking action alone or in non organized ways.

Unions are the way to multiply the forces and work as a group with common interests, it is for people that are not extremely selfish and egocentric.

> This addresses the union part.

lol, good luck with that.

you thinking that one or two people doing non organized _boycott_ is the same thing as an union tell a lot about you.

That is a ridiculous statement. Nobody would even care to break this thing. Look at it's base price, then lookat their customers. It makes no sense to break it.

In practice, it is not what happens. I've been doing AI assisted Rust for some time, and it is very convincing that this is the way. I expect 6mo to 1y to be basically fully automated.

Rust has tons of code out there, and quality code. Different from js or Python that has an abundance of low quality to pure garbage code.

> In computer vision, there has been a similar pattern. Early methods conceived of vision as searching for edges, or generalized cylinders, or in terms of SIFT features. But today all this is discarded.Modern deep-learning neural networks use only the notions of convolution and certain kinds of invariances, and perform much better.

I was there, at that moment where pattern matching for vision started to die. That was not completely lost though, learning from that time is still useful on other places today.

also see: https://github.com/plasma-umass/ChatDBG

> I cannot work with those who denounce calling out misbehavior on social media to thousands of followers, while themselves roasting people both on social media and on mailing lists with thousands of subscribers.

That person is someone called `Sima` and their posts on Mastodon are pure gas lighting. These are the worst abusers.

I'll try it then, if it can get a docker setup using my GPU and no dependency hell, then good. I'll report back to correct myself once I try it.

Yeah, I would love an actual alternative to Ollama, but RamaLama is not it unfortunately. As the other commenter said, onboarding is important. I just want one operation install and it needs to work and the simple fact RamaLama is written in Python, assures it will never be that easy, and this is even more true with LLM stuff when using AMD gpu.

I know there will be people that disagree with this, that's ok. This is my personal experience with Python in general, and 10x worse when I need to figure out all compatible packages with specifc ROCm support for my GPU. This is madness, even C and C++ setup and build is easier than this Python hell.

4 minutes is too long for a "missed flush". This looks like bad software simply. One may wonder if it is also developed by Boeing.

Nintendo must be getting ready to launch the next generation, which by targeting Switch emulators may signal that Switch 2 is not that far from it.

Interesting tool, but very tuned for modern days, with few content management options from what I can see. Thanks anyway, this is a nice addition the same.