←
Vedika7,286 posts
Vedika avatar

Vedika

@Coderiin

Age : quarter life+ | your not so average AI enthusiast | Current job : randomly posting tweets

◷ Joined May 2016▧ 739 Photos and videos
Vedika avatar
Vedika@Coderiin·Jun 26

Where y'all getting money to buy Midea Portasplit AC? My broke student bank balance can barely afford two fans.

Vedika avatar
Vedika@Coderiin·Jun 11

Yes, Yes I could have used something already available, but I needed something less bloated, customisable, and not behind a paywall.

Vedika avatar
Vedika@Coderiin·Jun 11

I just vibecoded a daily task tracker React app using Fable. I wanted it to be more visually accessible for my ADHD, and what I have got so far is impressive.

Vedika avatar
Vedika@Coderiin·Jun 6

PSA: If you are a student or learning any subject, please use AI as a study buddy. Otherwise, you will end up with smooth brains.

Science Simplified avatar
⟳ Vedika retweeted
Science Simplified@Scivf4·Jun 4

A 3D model of the solar system, driven by the sun's gravitation pull. The solar system does not look like a flat spinning mobile. The sun hold 99.8% of the mass in the solar system and it's gravity keeps every planet , asteroid and comet locked in orbit around it.

0:40
Boris Cherny avatar
⟳ Vedika retweeted
Boris Cherny@bcherny·May 21

In the next version of Claude Code: run /usage to see a breakdown of which Skills, Agents, MCPs, and Plugins are using your tokens CLI today, coming to Desktop next

Post attachment
kubesimplify avatar
⟳ Vedika retweeted
kubesimplify@kubesimplify·May 21

Underrated K8s feature for AI: scheduling-gates. Been GA since 1.30. Still underused. You can hold a Pod in Pending until -external state license check -GPU readiness -model cache is confirmed ready. Stop using sleep loops in init containers. If you're on 1.30+, you already have this.

Post attachment
atomic.chat avatar
⟳ Vedika retweeted
atomic.chat@atomic_chat_hq·May 21

Qwen 3.7-max beats Opus 4.7 and GPT-5.5 We tested three frontier models on a real agentic task: write a Tetris bot that plays the game and trains itself. Each model could read its own code, run benchmarks, and rewrite itself across 10 iterations. Then we compared the final bots head to head. Qwen 3.7-Max: training cost $1.32, bot improvement +56% Claude Opus 4.7: training cost $12.15, bot improvement +28% GPT-5.5: training cost $2.85, bot improvement +7% Qwen won on every dimension - biggest jump, 9× cheaper than Claude, 2× cheaper than GPT. Long agentic loops is where Qwen Max actually delivers.

0:10
Vedika avatar
Vedika@Coderiin·May 22

"All the power vested in me....I banish you from my FYP."

Post attachment
Vedika avatar
Vedika@Coderiin·May 22

Is anyone working with VLAs or has used VLAs for continual learning? I would like to connect with or follow such people.

Vedika avatar
Vedika@Coderiin·May 22

To all the bots asking what am I building today? Do I look like Bob the Builder to you? Beeezjessuz

Vedika avatar
Vedika@Coderiin·May 22

So I come back on X after 3 years, and everyone is a founder?....

Vedika avatar
Vedika@Coderiin·May 22

This thing gaurantees end time survivals...I'll take that

Minimum requirements for Linux

0:11