PinnedAndrew Lukyanenko·Sep 29, 2025My experience of interview preparation as MLEHow I prepared to interviews as MLE and got into MetaA response icon5A response icon5
PinnedAndrew Lukyanenko·Dec 24, 2025Top-10 ML papers I read in 2025LLMs, vision, agents, time-series, and other top AI/ML papers of 2025A response icon3A response icon3
PinnedInTDS ArchivebyAndrew Lukyanenko·Dec 2, 2018A long-term Data Science roadmap which WON’T help you become an expert in only several monthsFrom time to time I’m asked: how does one become Data scientist? What courses are necessary? How long will it take? How did you become DS…A response icon19A response icon19
Andrew Lukyanenko·6d agoStarting and iterating on a Kaggle competition in Google AntigravityI used a Claude Code starter kit and Google Antigravity with Gemini 3.1 to participate in a Kaggle Playground competition. Most of the work…
Andrew Lukyanenko·Jul 8Cayley graph search with Claude Code: what puzzle competitions look like in 2026Two learnings from two CayleyPy Kaggle competitions: how learned-heuristic beam search solves enormous Cayley graphs, and how Claude Code…
Andrew Lukyanenko·Jul 6Book Review: GPU-Accelerated Computing with Python 3 and CUDAA review of GPU-Accelerated Computing with Python 3 and CUDA, a hands-on book that goes from raw Numba-CUDA kernels through CuPy, RAPIDS…
Andrew Lukyanenko·Jun 22LocateAnything Explained: Parallel Box Decoding and how it makes visual grounding faster and more…A review of LocateAnything, an NVIDIA vision-language model that treats each bounding box as one atomic unit and decodes it in a single…
Andrew Lukyanenko·Jun 15MiniMax Sparse Attention: Per-Group Block Selection for Cheap Million-Token InferenceMiniMax Sparse Attention is a practical sparse-attention design for million-token LLMs — it uses a lightweight learned indexer to select…
Andrew Lukyanenko·Jun 10Testing MiniMax M3 on real tasks: repo refactor, screenshot debugging, and Spotify recommendationsA hands-on look at MiniMax M3 through Claude Code — what its new MiniMax Sparse Attention (MSA) is and using it for three real tasks…
Andrew Lukyanenko·Jun 9Book Review: 50 ML Projects to Understand LLMsA review of Mike X Cohen's 50 ML Projects To Understand LLMs, a hands-on book that uses code, statistics, and controlled experiments to…
