Tensor Fiend

life revolving around tensors. Building

[Tensor Fiend @tensorfiend]

LEARN RL BY END OF 2026
LEARN RL BY END OF 2026
LEARN RL BY END OF 2026
LEARN RL BY END OF 2026
LEARN RL BY END OF 2026
LEARN RL BY END OF 2026

[Tensor Fiend @tensorfiend]

Me with codex:

https://t.co/IEiSdVqxcf

[Tensor Fiend @tensorfiend]

Adding a Ghibli scenery image in the background increased the aesthetics of the site so much📈

[Tensor Fiend @tensorfiend]

@neural_avb What model/library do you use for text extraction from PDFs?

[Tensor Fiend @tensorfiend]

What happened to my Senpai😭

[Andrej Karpathy @karpathy]

This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under the hood engineering work to make this "just work" (e.g. across tools, integrations, compute environments, memory, security, etc.), Claude basically joins the team in a seamless way - you can talk to it as you would talk to a person and it can help with a very large variety of workloads.

Imo this is the 3rd major redesign of LLM UIUX. The first paradigm was that the LLM is a website you go to, the second was that it is an app you download to your computer. This third one is that it is a self-contained, persistent, asynchronous entity with org-wide tools and context, working alongside teams of humans. It really takes a while to wrap your head around it, but it works and it is awesome.

[Tensor Fiend @tensorfiend]

YouTube showing ads of @EleveLabs and Codex @ChatGPTapp one after another 😵‍💫

[Tensor Fiend @tensorfiend]

@amritwt I am seeing codex ads on Youtube often now. More irritating than that Excel guy. Time to get YT premium.

[Tensor Fiend @tensorfiend]

@maharshii Bro we had Engineering Drawing. I realized how bad I was at visualizing things😭

[Tensor Fiend @tensorfiend]

Every technology that has been built flourishes when the inventor themselves says, "Damn, you built this with the thing I made? That's awesome"

[shadcn @shadcn]

No model survives the "are you sure?" They all fold instantly.

[Tensor Fiend @tensorfiend]

Woahhhh, found this on @huggingface , this is even simpler, damn!

https://t.co/Fowy7yHprr

[Tensor Fiend @tensorfiend]

Found this great blog on PPO and GRPO by @YugeTen. The simplest explanation I have ever seen

https://t.co/LHdVoSlMjX

[Tensor Fiend @tensorfiend]

Found this great blog on PPO and GRPO by @YugeTen. The simplest explanation I have ever seen

https://t.co/LHdVoSlMjX

[Tensor Fiend @tensorfiend]

@amritwt Even notarization was taking a long time yesterday. I think it is working now.

https://t.co/MDV2lKWIdp

[Tensor Fiend @tensorfiend]

Why is Apple Notarization taking so longgggg @Apple 😐

[Tensor Fiend @tensorfiend]

Indus Valley script characters look beautiful

[Tensor Fiend @tensorfiend]

How difficult is it to make a RL env from scratch (not as great as @puffer_ai but a simple one.

Iam thinking of developing some env like Mars exploration with rover as agent

[Tensor Fiend @tensorfiend]

Why is Apple Notarization taking so longgggg @Apple 😐

[Tensor Fiend @tensorfiend]

🥲 Atleast I am in the top 10% for this. Hopefully nexttime🤞

[Tensor Fiend @tensorfiend]

⛄️

[Tensor Fiend @tensorfiend]

@AtharvaXDevs Shot this on 17-Mile Drive in California

[Tensor Fiend @tensorfiend]

@rasbt blog is like a dictionary for LLM Architectures 🫡. He has a blog for everything.

I started with GLM 5.2 and then ended up reading his DSA, MLA, MTP, DeepSeekV3.2 blogs

[Tensor Fiend @tensorfiend]

@Sol_Survivr @0xSero Do 30min a day and it’ll become a habit. I started this year (I miss somedays but regularly read Gita)

[Tensor Fiend @tensorfiend]

@0xSero Best thing one can do. Lord Krishna has aura man!!