Arun Reddy

Founder/CEO - AGNT5
Orchestration backend for Agentic Applications

[Sebastian Raschka @rasbt]

How can an LLM switch between low-, medium-, and high-effort reasoning? And how does an LLM learn to reason more or less?

I put together a “little” article explaining how these effort levels are implemented at inference time and during training.

[Arun Reddy @arunreddy]

@ankurnagpal Taxes and running finance - current pain point. Thanks for putting it together.

[Arun Reddy @arunreddy]

just discovered this Claude Code hack - kept hitting the 5hr quota limit on Max Plan when using deep thinking mode (burns through Opus like crazy). started using Opus to generate a TODO list, then spin up a new Sonnet session to execute it. no more waiting for reset.

[Arun Reddy @arunreddy]

🤯 Claude Code is absolutely mind-blowing! Just accomplished in a few hours what usually takes me a week to build. If you want superhero-level coding powers, the Max Plan is a game-changer!
💪 #ClaudeCode #AI

[Andrej Karpathy @karpathy]

Next level support for startups: FLOPS 👏😍

[Jeremy Howard @jeremyphoward]

After 2 years, Practical Deep Learning for Coders v5 is finally ready! 🎊

This is a from-scratch rewrite of our most popular course. It has a focus on interactive explorations, & covers @PyTorch, @huggingface, DeBERTa, ConvNeXt, @Gradio & other goodies 🧵
https://t.co/nzv7pek0iq

[Sebastian Raschka @rasbt]

After putting together a lecture on multi-GPU training paradigms, I thought it might be a good idea to catch up with the recent “Cramming: Training a Language Model on a Single GPU in One Day” paper (https://t.co/sv3VMPEDAd).

An interesting read with lots of insights!
1/8

[Anaconda @anacondainc]

📢 Did you hear the news from PyCon!? We are thrilled to introduce PyScript, a framework that allows users to create rich Python applications IN THE BROWSER using a mix of Python with standard HTML! Head to https://t.co/n4OoeBD46z for more information. 🧠 💥

[Sachin Grover @sachingrover]

I am a PhD student in the Yochan lab @SCAI_ASU, advised by @rao2z looking to graduate and seeking research+engineering opportunities in the industry. In the past, I have been a research intern with Amazon Alexa and a full-stack developer @ Sapient Nitro India before Masters. 1/

[Arun Reddy @arunreddy]

@sujit_g Dedication and energy 👏🏻 At 2am 🙏

[Blinkist @blinkist]

When he’s not building rockets, boring tunnels beneath Los Angeles, or sending cars into space, Elon Musk reads a lot. Here are 9 nonfiction books he thinks we should all read.

[Arun Reddy @arunreddy]

@maidylm Thank you so much Lydia.

[Arun Reddy @arunreddy]

CP16: Automatic Frankenstiening: Greedy model selection and learning the ensemble of classifiers automatically. #kaggle #stacking #SIAMSDM17

[Arun Reddy @arunreddy]

CP16: T3 by Kohei. Proposed an approach for sparse graphical modeling via the PCLA. #SIAMSDM17

[Arun Reddy @arunreddy]

CP16: T2(2/2) Interesting multiview multi resolution settings for time series data. #SIAMSDM17

[Arun Reddy @arunreddy]

CP16: T2(1/2) Learning for multimodality and multi resolution by Yada Zhu+ prsntd by Yao. #SIAMSDM17

[Arun Reddy @arunreddy]

CP16: T2(1/2) Learning for multimodality and multi resolution by Yada Zhu+ prsntd by Yao. Proposed an optimization framework for multi view

[Arun Reddy @arunreddy]

CP11: Ramki (2/2) The core idea is to separate the for outlier detection in text data. #SIAMSDM17

[Arun Reddy @arunreddy]

CP11: Ramki (1/2) proposed a matrix factorization approach for outlier detection in text data. #SIAMSDM17

[Arun Reddy @arunreddy]

CP11: Subhabrata Mukherjee (1/2): Good analysis on facets that contribute and don't contribute to the user expertise.