Hacker News: 3abiton

New comment by 3abiton in "Three new discoveries in mathematics, computer science, and physics"

3abiton — Mon, 26 Oct 2026 22:27:40 +0000

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.

New comment by 3abiton in "OpenShell – A safe, private runtime for fleets of autonomous AI agents"

3abiton — Sat, 24 Oct 2026 08:17:53 +0000

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

New comment by 3abiton in "A visual introduction to information theory"

3abiton — Sat, 24 Oct 2026 08:14:53 +0000

> 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?

New comment by 3abiton in "Is this the new cyber normal?"

3abiton — Sat, 24 Oct 2026 07:59:32 +0000

> 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.

New comment by 3abiton in "Samsung TV privacy issues"

3abiton — Sat, 24 Oct 2026 07:52:19 +0000

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.

New comment by 3abiton in "Tmux and Claude Code: Sessions, Send-Keys, and the Ceiling"

3abiton — Mon, 19 Oct 2026 22:30:00 +0000

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.

New comment by 3abiton in "How the Elizabeth Holmes documentary “You Can See Everything” is deceiving"

3abiton — Sun, 18 Oct 2026 11:18:29 +0000

He rehearsed it.

New comment by 3abiton in "You could have invented transformers from memory"

3abiton — Sat, 17 Oct 2026 22:50:08 +0000

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!

New comment by 3abiton in "Pg_vectorsearch: An index that is faster than pgvector's IVFFlat and HNSW"

3abiton — Wed, 14 Oct 2026 13:23:08 +0000

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

New comment by 3abiton in "TabPFN and TabICL vs. tuned XGBoost: the model that doesn't train won 14/14"

3abiton — Mon, 28 Sep 2026 05:46:10 +0000

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.

New comment by 3abiton in "MiMo v2.6"

3abiton — Tue, 22 Sep 2026 11:37:10 +0000

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.

New comment by 3abiton in "Introducing System One Models and Jev"

3abiton — Sat, 19 Sep 2026 06:23:10 +0000

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

New comment by 3abiton in "Show HN: An e-ink frame that hears birds and draws them as 1800s illustrations"

3abiton — Sat, 19 Sep 2026 06:15:03 +0000

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.

New comment by 3abiton in "OpenJev"

3abiton — Sat, 19 Sep 2026 06:10:28 +0000

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

New comment by 3abiton in "Fujitsu launches made-in-Japan next-generation CPU FUJITSU-MONAKA"

3abiton — Thu, 17 Sep 2026 22:32:44 +0000

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

New comment by 3abiton in "German Rheinmetall open-sources its Battlesuite connected weapon system protcol"

3abiton — Wed, 16 Sep 2026 13:28:55 +0000

I 100% support this "loophole"

New comment by 3abiton in "We do modern frequentist statistics: Using fake-data simulation"

3abiton — Wed, 16 Sep 2026 13:27:22 +0000

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.

New comment by 3abiton in "Discovery of a new OpenAI agent message board"

3abiton — Wed, 09 Sep 2026 21:54:45 +0000

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.

New comment by 3abiton in "Speculative Decoding in vLLM on AMD GPUs"

3abiton — Tue, 08 Sep 2026 14:07:56 +0000

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.

New comment by 3abiton in "Aging brains blend memories together instead of just forgetting them"

3abiton — Thu, 03 Sep 2026 06:13:25 +0000

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