Geevarghese George

PhD in Computational Physics,
Data stuff @AVL_List
Previously @MIAAIDPU @CharlesSadron @CNRS,
Went to @UniStra @UniFreiburg #CUSAT

[Manning Publications @ManningBooks]

Passing the CKA exam takes more than memorizing commands. It takes hands-on practice.

That's the focus of Acing the Certified Kubernetes Administrator Exam, Second Edition by @ChadMCrowell and @rafaelbrito, two @CloudNativeFdn Ambassadors. With practical labs, realistic examples, and practice questions, it's built to help you prepare for the real exam.

See how @thatgeeman used it to earn his certification: https://t.co/qIVC6Sh7cr

Book: https://t.co/Sgj68ybp93

[Geevarghese George @thatgeeman]

Appreciate the organizers @huggingface @Gradio and sponsors for putting together a genuinely motivating challenge. It was fun, exhausting, and worth it.

#MCP #Hackathon #AIAgents #AgenticAI #Python #BuildInPublic #LLM

[Geevarghese George @thatgeeman]

Excited to share "FixMyEnv", my submission for MCP’s 1st Birthday Hackathon hosted by @AnthropicAI and @Gradio.

🔗 App: https://t.co/0M6ZLYrcyI
🎥 Demo: https://t.co/lCDqN3LQOb

[Geevarghese George @thatgeeman]

What’s happening under the hood:
- GitHub MCP servers
- Tools for PyPI Index Search
- Tools for Dependency and version analysis across package constraints (powered by uv / Astral)
- And the whole app as an MCP Server with some gradio magic.

[Geevarghese George @thatgeeman]

@huggingface Inference endpoint returning 500 Internal Error

POST to `https://t.co/ndlfuLSfxq` returning `Received response from question rewriter: {'error': "Internal Error - We're working hard to fix this as soon as possible!"}`

Reproducible also here: https://t.co/KZnZdS3A3J

[PyTorch @PyTorch]

🎉 The 2025 #PyTorch #Docathon brought together 150+ contributors who tackled long-standing issues and submitted 60+ merged PRs across core repos.

Congratulations to our top contributors:
🥇 j-silv, kiszk, windsonsea
🥈 Rachel0619, jafraustro, loganthomas, @nirajkamalk, @Dhia_naouali_
🥉 @juliandlb11, ggsmith842, ParagEkbote

📘 Read the recap: https://t.co/snnLUtxQcz

#OpenSourceAI #AICommunity #DocumentationMatters

[SpaceXAI @SpaceXAI]

We want to update you on an incident that happened with our Grok response bot on X yesterday.

What happened:
On May 14 at approximately 3:15 AM PST, an unauthorized modification was made to the Grok response bot's prompt on X. This change, which directed Grok to provide a specific response on a political topic, violated xAI's internal policies and core values. We have conducted a thorough investigation and are implementing measures to enhance Grok's transparency and reliability.

What we’re going to do next:
- Starting now, we are publishing our Grok system prompts openly on GitHub. The public will be able to review them and give feedback to every prompt change that we make to Grok. We hope this can help strengthen your trust in Grok as a truth-seeking AI.
- Our existing code review process for prompt changes was circumvented in this incident. We will put in place additional checks and measures to ensure that xAI employees can't modify the prompt without review.
- We’re putting in place a 24/7 monitoring team to respond to incidents with Grok’s answers that are not caught by automated systems, so we can respond faster if all other measures fail.

[Leonardo Rizzo @LnrdRizzo]

How we "guessed" the Pope using network science: inside the cardinal network. A study by me, Beppe Soda and Alessandro Iorio. Article: https://t.co/xQ0fTmpVxb @Unibocconi

[Geevarghese George @thatgeeman]

A great beginning to a paper. https://t.co/Fmt2PYBF8z

[Geevarghese George @thatgeeman]

Documentations are fun to read. "If your machine is a potato, it'll take a bit longer."

tutorial-resources/mxd at main · eclipse-tractusx/tutorial-resources via @_Glasp
https://t.co/4lKkyLlvUC

[Geevarghese George @thatgeeman]

"there are many ways that illicit AI agents could obtain GPUs."

The Rogue Replication Threat Model via @_Glasp
https://t.co/kO0LR2EnMq

[Geevarghese George @thatgeeman]

"Llama 3.1 405B at 969 tokens/s"

Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference - Cerebras via @_Glasp
https://t.co/30mFwrJgQe

[Geevarghese George @thatgeeman]

Me trying to buy a calculus practice book looking at amazon reviews

[Andrej Karpathy @karpathy]

Can I just say I loooove Suno. Some of my favorites:

Dog dog dog dog dog dog dog dog woof woof
https://t.co/3yWAqFGDe3
Chemical elements
https://t.co/p7EEc4iYgd
train_gpt2.c header (who did this lol)
https://t.co/6gz25sxiKA
Suno tutorial (in Suno!):
https://t.co/vN5lPa55Tg

Many others. So good. Anyone else favorites?

[Geevarghese George @thatgeeman]

https://t.co/o5vVJoC3qT

[Santiago @svpino]

In 1994, people told me programming was for nerds and that I should become a doctor or a lawyer instead.

Ten years later, they told me that someone from India or the Philippines would take my job for $5/hour.

When that didn't happen, no-code became an existential threat. I was finally doomed.

In 2021, it was Codex. Then, Copilot. Then, ChatGPT. Every time, people told me, "Programming is Dead."

Last week, a company released a demo of the "first AI software engineer." This is it! I should start looking for a far now, right?

Reality is different. The demand for good programmers has never been higher before. Today, in the age of AI, few things will make you more valuable than knowing how to write good software.

Learn to code.

[Talk Python Podcast @TalkPython]

Very timely and excellent episode with the prolific @charliermarsh (and host @mkennedy):

uv - The Next Evolution in #Python Packaging?
https://t.co/kAkoS04db1

[Geevarghese George @thatgeeman]

@arghya_dutta_ Yep this is great! My trigger for day planning: https://t.co/fd8vcdNMar