Pavel Zloi

AI/ML, MCP, MLOps, LLM, GPT, GNN, NLP, GCN, Python, AWS, Linux, DevOps

[Pavel Zloi @EvilFreelancer]

https://t.co/PJEV4fI8XV

[Pavel Zloi @EvilFreelancer]

Agent Reliability Engineer (ARE)

Агенты в одном проекте = SRE между командами. Rules, skills, флоу. Не AI SRE, а reliability агентов. Agent Reliability Engineer. ARE, who they are?

[Andrej Karpathy @karpathy]

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

[David Finsterwalder | eu/acc @DFinsterwalder]

I vibecoded this neural network visualization for my students and open sourced it.

It shows a simple MLP trained on MNIST handwritten digits at several training steps. The visualization is using @threejs and it comes with training code in @PyTorch .

Link + repo 👇

[MIT CSAIL @MIT_CSAIL]

14 sorting algorithms in just 60 seconds.

v/@7etsuo

[Kai Lentit (e/xcel) @KaiLentit]

us-east-1 is down

Here is why:

[Andrej Karpathy @karpathy]

I quite like the new DeepSeek-OCR paper. It's a good OCR model (maybe a bit worse than dots), and yes data collection etc., but anyway it doesn't matter.

The more interesting part for me (esp as a computer vision at heart who is temporarily masquerading as a natural language person) is whether pixels are better inputs to LLMs than text. Whether text tokens are wasteful and just terrible, at the input.

Maybe it makes more sense that all inputs to LLMs should only ever be images. Even if you happen to have pure text input, maybe you'd prefer to render it and then feed that in:
- more information compression (see paper) => shorter context windows, more efficiency
- significantly more general information stream => not just text, but e.g. bold text, colored text, arbitrary images.
- input can now be processed with bidirectional attention easily and as default, not autoregressive attention - a lot more powerful.
- delete the tokenizer (at the input)!! I already ranted about how much I dislike the tokenizer. Tokenizers are ugly, separate, not end-to-end stage. It "imports" all the ugliness of Unicode, byte encodings, it inherits a lot of historical baggage, security/jailbreak risk (e.g. continuation bytes). It makes two characters that look identical to the eye look as two completely different tokens internally in the network. A smiling emoji looks like a weird token, not an... actual smiling face, pixels and all, and all the transfer learning that brings along. The tokenizer must go.

OCR is just one of many useful vision -> text tasks. And text -> text tasks can be made to be vision ->text tasks. Not vice versa.

So many the User message is images, but the decoder (the Assistant response) remains text. It's a lot less obvious how to output pixels realistically... or if you'd want to.

Now I have to also fight the urge to side quest an image-input-only version of nanochat...

[Pavel Zloi @EvilFreelancer]

Мда, давно это было. #MyXAnniversary

[dhruv @hail_dhruv]

forget leetcode, I'm farming food with python.

[SaltyAom @saltyAom]

I DID THE THING FOR GITHUB

[The Internet of Cats 🐈🐈‍⬛ @KittiesInternet]

Who made this?!😂

[Pavel Zloi @EvilFreelancer]

@de5imulate hi!

You might want to check out Hunyuan by Tencent, it's an AI-driven tool that converts text and images into playable 3D scenes:
https://t.co/zzTNgUCYzI
https://t.co/hzQrSgqN6N

[Pavel Zloi @EvilFreelancer]

Тут исходники бенчмарка:
https://t.co/RDkjH3nXED

[Pavel Zloi @EvilFreelancer]

🇷🇺 Russian Router Ranking (RRR) Leaderboard

Проект бенчмарка, который позволяет оценить качество работы больших языковых моделей (LLM) в роли маршрутизатора запросов.

https://t.co/cqNgrnUijN

[will o’brien @Willob]

Software creates soft men
Soft men create hard times
Hard times create hard men
Hard men create hardware
Hardware creates good times
Good times creates software

[PUNS @ThePunnyWorld]

For the science nerds.

[AlmostFriday.TV @AlmostFridayTV]

Professor crashes out over cheating students