New non-copyleft Rust implementation. While we're at it, let's throw in some blockchain and AI as well. The eccentric South African billionaire CEO will be pleased.
@programming.dev
A fully open-source LLM
As a fully open language model, Apertus allows researchers, professionals and enthusiasts to build upon the model and adapt it to their specific needs, as well as to inspect any part of the training process. This distinguishes Apertus from models that make only selected components accessible.
“With this release, we aim to provide a blueprint for how a trustworthy, sovereign, and inclusive AI model can be developed,” says Martin Jaggi, Professor of Machine Learning at EPFL and member of the Steering Committee of the Swiss AI Initiative. The model will be regularly updated by the development team which includes specialized engineers and a large number of researchers from CSCS, ETH Zurich and EPFL.
The US likely has many years of recession to look forward to. There might even be a civil war. The country is utterly broken and the ones to blame are capitalists and useful idiots preaching and implementing their propaganda (neoliberalism and its even more degenerated derivates).
When did you try Debian? Nvidia should be quite painless since they added the official non free repo. But make sure to install a backports version of the kernel and firmware. And modern apps should be installed with flatpak.
Anyway. I suggest that you try Debian again. There is nothing better out there.
GPT-OSS:120b is really good.
Tools are powerful and make local inference on cheap hardware good enough for most people.
DSPy is pretty cool.
Intel caught my attention at the begin of 2025, but seems to have given up on their software stack. I regret buying cheap Arcs for inference.
Inference on AMD is good enough for production.
Exactly what an LLM-agent would reply. 😉
I would say that the LLM-based agent thinks. And thinking is not only "steps of reasoning", but also using external tools for RAG. Like searching the internet, utilizing relationship databases, interpreters and proof assistants.
You just described your subjective experience of thinking. And maybe a vauge definition of what thinking is. We all know this subjective representation of thinking/reasoning/decision-making is not a good representation of some objective reality (countless of psychological and cognitive experiments have demonstrated this). That you are not able to make sense of intermediate LLM reasoning steps does not say much (except just that). The important thing is that the agent is able to make use of it.
The LLM can for sure make abstract models of reality, generalize, create analogies and then extrapolate. One might even claim that's a fundamental function of the transformer.
I would classify myself as a rather intuitive person. I have flashes of insight which I later have to "manually" prove/deduc (if acting on the intuition implies risk). My thought process is usually quite fuzzy and chaotic. I may very well follow a lead which turns out to be dead end, and by that infer something which might seem completely unrelated.
A likely more accurate organic/brain analogy would be that the LLM is a part of the frontal cortex. The LLM must exist as a component in a larger heterogeneous ecosystem. It doesn't even have to be an LLM. Some kind of generative or inference engine that produce useful information which can then be modified and corrected by other more specialized components and also inserted into some feedback loop. The thing which makes people excited is the generating part. And everyone who takes AI or LLMs seriously understands that the LLM is just one but vital component of at truly "intelligent" system.
Defining intelligence is another related subject. My favorite general definition is "lossless compression". And the only useful definition of general intelligence is: the opposite of narrow/specific intelligence (it does not say anything about how good the system is).
Readest. But I'm looking for a free app with good TTS and (maybe this breaks the free) which is able to handle DRM content from Adobe digital editions (Or is able to remove the DRM). Unfortunately, my library only provide books through ADE.
TLDR: Yes, it matters. Especially when it comes to inference and "new" features and hacks it relies on.
What GPU and what inference engine are you using?
On Debian I would use the stable version (not old stable) and I would enable nonfree firmware and also the backports version of the kernel and nonfree firmware. Then you're probably set for a year or two.
An old kernel with only free firmware likely performs much worse. Look at the release logs of the Linux kernel and any GPU driver.
If your hardware is very old, it probably doesn't matter super much. But sometimes it does (like when a manufacturer decides to unlock some sleeping feature in an old forgotten device).
If one wants rolling, I would suggest NixOS, Guix System or Tumbleweed. Or something container based like Silverblue or openSUSE micro.
But rolling doesn't really make sense. Just go with Debian/Leap and then use Flatpak, podman, Nix and/or Guix on top of that. For Desktop.
Debian and then maybe Guix on top of that. Rootless Podman for services.
There is no good reason to choose Arch in 2025. If you want to feel special, NixOS or Guix System is the way to go.
I think Guix is way more coherent than Nix. It also has better documentation and a more friendly community. And you use Scheme instead of Nix lang.
Some would certainly say it is. I guess that's a key difference between social democracy and democratic socialism. And the definition differs a lot within countries and even parties. There is no absolute definition of socialism and will never be.
Oh, that's quite fancy hardware.
Hmm.. Unless exllama is explicitly recommended by NVIDIA for that particular GPU and setup, it seems "risky". vLLM seems to be the popular choice for most "production" systems. I'm switching from llama.cpp to vLLM because of better performance and its the engine recommended by most model providers. I don't really have the time to benchmark, so I'll just do what the documentation says. And it's really hard to do good benchmarks. Especially when "qualitative language performance" can vary for the same weights on different hardware/software.
With that kind of hardware, I would do exactly what NVIDIA and your model provider(s) say. Otherwise you might waste a lot of GPU power.
Yeah, I meant Scheme as you've already figured out.
I would say that nonguix makes nonfree stuff trivial: https://gitlab.com/nonguix/nonguix
However, I do advocate that Guix introduce an official "curated" nonfree repository (like Debian). I believe that would make more good for user freedom and reproducibility. Almost no mainstream hardware works well with the libre kernel.
thanks for using Leebra!
go to feed...