Dinesh Maluchuru · A working notebook
Understanding systems.
One idea at a time.
Notes on AI, machine learning, data & the engineering behind them. Written to make complex things a little clearer.
About the authorThe latest essay
machine learning
30 min read
Reading OpenAI’s Math Repository: From Research Claims to Checkable Proofs
A deep guide to OpenAI’s math release: proof versus tests, rational approximation, zeta zero-free regions, Lean, and what formal verification does—and does not—establish.
Read the essayMore from the notebook
All articlesKimi K3 From Zero to Deep — Math, Architecture, Training, and Systems
A zero-to-deep Kimi K3 course: prerequisite math and terminology, Transformers and MoE, KDA, AttnRes, vision, RL, training systems, inference, benchmarks, and a verified YouTube learning path.
90 min readIntroduction to TensorFlow on Google Cloud
Diving deep into a Google Skill boost
10 min readTaking the Azure Fabric Ignite Edition Challenges to Complete
Microsoft Learn Challenge conducting a challenge to get good in few of the challenges which are super useful to complete to gain knowledge on Microsoft Fabric.
16 min readExploring different services in GCP
Exploration and documentation of different services offered in GCP
15 min readStarting a company in India
Documenting the process of starting a company in india
10 min readGoogle 5 Day Gen AI course with interactive hands-on practice
Google and Kaggle provided good summary course on Gen AI , the blog contains details and highlights of the course.
1 min readAI Voice chatting to help with Customer support use-cases
Using current speech augmented LLMs (SpeechLLMs) with realtime voice modality to understand user issues and to provide support and solutions.
2 min readAudio to Video Generation Using Replit AI and Deploy as an Azure Webapp
Tool to convert an uploaded audio mixed with an image and generate a video format with image and uploaded audio in the video format.
1 min read
Go a little deeper
Make room for learning.
Follow a structured series, explore a topic, or start with the six-month engineering path. Pick up wherever you are.