Xenon (霧 🐾 )

Full-stack Developer | AI Automation | Open Source • Claude | Anime • Math • Code | student @NIT Warangal

[Xenon (霧 🐾 ) @itsmeuttu]

@ash_twtz It mostly depends on the desktop environment rather than the distro itself. A lightweight DE like XFCE, LXQt, or LXDE can make even a heavier distro run well on low RAM, while a heavier DE such as GNOME or KDE will use more memory regardless of the distro

[Xenon (霧 🐾 ) @itsmeuttu]

A few weeks ago, I thought Minecraft bots were just simple scripts that followed players around.
Today, I've built a Minecraft helper bot that can navigate the world, mine resources, build structures, fight mobs, manage inventory, and interact with players through commands.

[Xenon (霧 🐾 ) @itsmeuttu]

The only math equation I actually care about 📐🌸
#yuri #gl #manga #animeart #webtoon

[Xenon (霧 🐾 ) @itsmeuttu]

@thelittlemugi which shader do you use?

[Xenon (霧 🐾 ) @itsmeuttu]

This paper looks scary at first, but honestly it’s more theory than numericals 😭 If someone studied basics properly, most questions are directly from standard topics.
Examiner really said: “No tricks… just write the entire syllabus.” 💀

[shreya @whatevershreya]

to all the very invested people in my applied physics II exam thankyou 😝

[Xenon (霧 🐾 ) @itsmeuttu]

Here is the pdf: https://t.co/b4LqTsSUen

[Xenon (霧 🐾 ) @itsmeuttu]

Solved and analyzed JEE Advanced 2026 Chemistry Paper 2 with detailed concept-based explanations.
Focused on deriving formulas, conceptual clarity, and problem-solving approaches instead of rote memorization.

#JEEAdvanced2026 #JEEAdvanced #Chemistry #PhysicalChemistry #IITJEE

[Kevin Naughton Jr. @KevinNaughtonJr]

ssh was created in 1995
tmux was created in 2007

sadly most engineers won't understand why this is relevant

[Dwarkesh Patel @dwarkesh_sp]

New blackboard lecture w @ericjang11

He walks through how to build AlphaGo from scratch, but with modern AI tools.

Sometimes you understand the future better by stepping backward. AlphaGo is still the cleanest worked example of the primitives of intelligence: search, learning from experience, and self-play. You have to go back to 2017 to get insight into how the more general AIs of the future might learn.

Once he explained how AlphaGo works, it gave us the context to have a discussion about how RL works in LLMs and how it could work better – naive policy gradient RL has to figure out which of the 100k+ tokens in your trajectory actually got you the right answer, while AlphaGo’s MCTS suggests a strictly better action every single move, giving you a training target that sidesteps the credit assignment problem. The way humans learn is surely closer to the second.

Eric also kickstarted an Autoresearch loop on his project. And it was very interesting to discuss which parts of AI research LLMs can already automate pretty well (implementing and running experiments, optimizing hyperparameters) and which they still struggle with (choosing the right question to investigate next, escaping research dead ends). Informative to all the recent discussion about when we should expect an intelligence explosion, and what it would look like from the inside.

Timestamps:

0:00:00 – Basics of Go
0:08:06 – Monte Carlo Tree Search
0:31:53 – What the neural network does
1:00:22 – Self-play
1:25:27 – Alternative RL approaches
1:45:36 – Why doesn’t MCTS work for LLMs
2:00:58 – Off-policy training
2:11:51 – RL is even more information inefficient than you thought
2:22:05 – Automated AI researchers

[Grant Kot @kotsoft]

chemical reaction between sodium and water

[Xenon (霧 🐾 ) @itsmeuttu]

here's how my completely free discord ai image bot works:

[Xenon (霧 🐾 ) @itsmeuttu]

built a completely free discord image generator bot

stack:
- google colab (free gpu)
- stable diffusion (open source)
- flask backend
- https://t.co/RNHOs3jR7Y integration

unlimited images
zero cost
one weekend build

here's how to do it

[Xenon (霧 🐾 ) @itsmeuttu]

Watch how I bypassed expensive API fees by building my own completely free AI image generator Discord bot using a Google Colab GPU, Flask, and Stable Diffusion.

[Xenon (霧 🐾 ) @itsmeuttu]

built a completely free discord image generator bot

stack:
- google colab (free gpu)
- stable diffusion (open source)
- flask backend
- https://t.co/RNHOs3jR7Y integration

unlimited images
zero cost
one weekend build

here's how to do it

[Xenon (霧 🐾 ) @itsmeuttu]

Watch how I bypassed expensive API fees by building my own completely free AI image generator Discord bot using a Google Colab GPU, Flask, and Stable Diffusion.

[Xenon (霧 🐾 ) @itsmeuttu]

built a completely free discord image generator bot

stack:
- google colab (free gpu)
- stable diffusion (open source)
- flask backend
- https://t.co/RNHOs3jR7Y integration

unlimited images
zero cost
one weekend build

here's how to do it

[Google @Google]

Today, we introduced Gemini Intelligence, which brings the best of Gemini to our most advanced devices.

Gemini Intelligence integrates premium hardware and innovative software to help you stay a step ahead and work proactively to get things done throughout your day. #TheAndroidShow

[Xenon (霧 🐾 ) @itsmeuttu]

The real war has begun now: AI vs AI

[News from Google @NewsFromGoogle]

The Google Threat Intelligence Group has detected the first known instance of a threat actor using an AI-developed zero-day exploit in the wild. While the attackers planned a wide-scale strike, our proactive counter-discovery may have prevented that from happening. This finding is part of our new report on AI-powered threats.

[Xenon (霧 🐾 ) @itsmeuttu]

you can using AI in terminal (no ollama)

[Xenon (霧 🐾 ) @itsmeuttu]

i'm about to blow your mind:

you can use chatgpt-level ai in your terminal

NO API
NO SETUP
NO PAYMENT
NO FRICTION

just:
$ [command] "write me code"

and you get production ready answers

this is why i'm never leaving terminal again

#DeveloperLife #AI #Terminal

[Xenon (霧 🐾 ) @itsmeuttu]

you can using AI in terminal (no ollama)

[Xenon (霧 🐾 ) @itsmeuttu]

i'm about to blow your mind:

you can use chatgpt-level ai in your terminal

NO API
NO SETUP
NO PAYMENT
NO FRICTION

just:
$ [command] "write me code"

and you get production ready answers

this is why i'm never leaving terminal again

#DeveloperLife #AI #Terminal