3abiton

At this point, is the second L (language) a limitations to LLMs? Is reasoning in latent space directly a more efficient and more "native" inference? I remember when one researcher replicated the middle layer of deepseek model (just the "thinking" layers) and its benchmark scores got noticebly higher. All of this is moving so fast, and yet it's quite exciting.

Releasing weights even with permissive license, doesn't technically make it "open-source", unless all the method, data and technical inner working to do it is also released. Otherwise, it's just a binary floating in the wild, even if it's under MIT.

I am not sure if I side with Tao on this, or 3B1B. It's already causing quite a kerfuffle (to say the least) in the academic communities. This is the new norm now.

Honestly I don't get openshell. You can do the same with bubblewrap on linux, on any shell.

> Submitted on 16 Jun 2022 (v1), last revised 6 Mar 2026 (this version, v3)]

This is rather interesting. I haven't fully checked the diffs, but v1 had 1 more page than v3, otherwise from a quick glimpse it seems to retain most of the overall structure. Was there a correction?

> because old software is going to be patched or thrown away and new one is going to be security-scanned and tested.

I highly disagree with this, I've worked in many environment and I can tell you some medium/big companies do not adapt fast enough, some have multiple projects, and when someone critical leaves, many of these projects remain unmaintained but "working". If you don't have deep monitoring, you won't even detect that you've been "hacked" or "infiltrated". Companies accepted that risk because the pace from CVE -> exploitation was big enough, but now with AI, exploitation at scale is easier than ever.

This is again will be very funny race to watch. Right now you can fairly do lots of reverse enginnering or "hacking" with off the shelf Chinese models, and they are very capable (GLM3 for example) which can be run locally if you stomach the hardware. Tools like rea are also becoming more popular. If openai continues to be pedantic, they will lose the technical base given how close is the gap getting.

Honestly WSL sucks. Even msys2. My current client forces me to use windows to access their data, and I really, really tried to make it a dev machine, it just MS made it such a shit experience. I had scoop, I had msys2, I had WSL2, etc ... My mere setup (nvim, tmux, or even herdr, etc ...) all run very slow. nvim is barely usable. Where is on my nearly 10 yo voidlinux notebook of 4GB, it runs amazing. Something about MS bloatware will never disappoint.

He rehearsed it.

It was a great read. I've been recording a lot of the ideas I had, and especially after discussions with people. Sadly never found time to sit down, digest them and write them down yet. Your article is quite inspiring!

Checks notes, one dayabase per client, per user, per project ... etc

I would love to point them at my old time series prediction problems to see their ability. I was very proud of my lightgbm back then, performing miracles after a heck of a lot fearure engineering.

We're past the one model fits them all kind of LLM. Most of the recent release actually regress on world knowledge for example, but optimize for something different: tool usage, thinking process, and agentic approach. And yes, in my own usage, some usecases Opus beats Fable.

Why wait, if there is already a similar implementation a year ago, and it's fully open source: dataset, paper, repo etc ... The idea is not new.

https://news.ycombinator.com/item?id=49736660

Few years ago, there was an android app (open source from fdroid) that basically provided the model and ability to listen and give you informafion about the birds. It was very fun during hikes with friends.

This is a great evolution in the right direction compared to LLM + pydantic and temperature 0.

Man this looks amazing, more competition is always welcome! The issue for Ai inference is always firmware/software support. Up until recently, that rocm hardware became usable, let alone optimized. Nvidia had a big start, now everyone is trying to catch up

I 100% support this "loophole"

Wait a bayesian advocate using a frequentist approach and not having a fight over which branch is supreme. What's happening with the world. I guess all stats united against AI.

I have no doubts about this, even if you ask chatgpt itself to run a security audit, this would have been one of them flags.

Honestly a big part of this is AMD's lackluster strategy to GPU software. To say it's lacking is understatement. At least for non-data center gpus.

I wonder the effect of diary writing on the brain, I see always recommended as either part of the self-improvement space or meditation. But reading your comment, I wonder if it allows to strengthen memories, especially if ones reread it after a while. I must experiment, now it's easier than ever with LLMs

> trust

One interesting aspect ij academic literature about trust, it is highly reverse correlated with diversity. No matter the grouping and size, the more diverse, the less trust within the group.

It's very much how I've been using claude code in the past 5 month: brainstorm -> generate specs (constraints) -> generate exact plan -> implementation + review -> test / validate. The last stage is the most crucial one, and it's the most difficult to get it right for a complex solution (it's tough to cover every variation). But so far, it's been working great..

Unfortunately it's not always easy to move away from systemd. I still run void on one of my machines, but aur make things so much easier.

Even more videos to binge before the holidays end! Thanks for sharing!

Alright, a new series to binge now.

I hate to be pedantic but you can finetune a skill to shape the PR message the way you like it. That being said, I did have exactly this issue you mentioned, but the defualt output can always be tuned.

Nonetheless, it's the year og the linux desktop!

I think the github readme repo is more for people who heard about it, but you're absolutely right, it is lacking in context and explanation.