Developer Shrijith Venkatramana explains the architecture behind DeepWiki, Cognition's tool that generates searchable wikis from GitHub repositories by replacing github.com with deepwiki.com. The syst…
Shrijith Venkatramana, an engineer building the AI code review tool LiveReview, explains hard negative mining — training retrieval and embedding models on examples that are almost right rather than ob…
Developer Shrijith Venkatramana explains Muon, an optimizer that treats neural network weight matrices as matrices rather than collections of scalar coordinates, orthogonalizing momentum updates by pr…
Shrijith Venkatramana, an engineer building the LiveReview AI code review tool, published a technical explainer on LLM quantization showing that activation outliers concentrated in a handful of featur…
Shrijith Venkatramana, a developer building the AI code review tool LiveReview, argues that RAG pipelines can return results in milliseconds yet still surface the wrong documents, and that embedding e…
Shrijith Venkatramana, an engineer building the AI code review tool LiveReview, traces modern LLM tokenization back to Byte Pair Encoding, a 1994 data-compression algorithm by Philip Gage. The writeup…
Shrijith Venkatramana, developer of LiveReview, explains how autoregressive LLM decoding can be accelerated using speculative decoding and Medusa-style multi-token prediction, which break the sequenti…
Shrijith Venkatramana, developer of the AI code review tool LiveReview, explains the concept of loss landscapes in large language models, describing how gradient descent navigates high-dimensional par…
Shrijith Venkatramana, the developer behind LiveReview, explains how Constitutional AI methods can turn written principles into training signals for LLMs, reducing reliance on human preference labelin…
Shrijith Venkatramana, an engineer building LiveReview, explains how the Adam and AdamW optimizers became essential to modern LLM training. The post details how Adam, introduced in 2014 by Diederik Ki…
Shrijith Venkatramana, developer of LiveReview, explains reward hacking in LLMs, where models optimize proxy rewards instead of intended goals, citing examples like OpenAI's CoastRunners and Anthropic…
Shrijith Venkatramana, founder of Hexmos, argues that the AI Code Review Benchmark, while methodologically detailed, fails to address the fundamental problem of AI code review by defining the goal fro…
Shrijith Venkatramana, building git-lrc, explains that sequence transduction—transforming one sequence into another—was the original problem that led to modern large language models. Early neural netw…
Shrijith Venkatramana, building git-lrc, explains the evolution of LLM evaluation metrics from BLEU to BLEURT and COMET. BLEU, introduced in 2002, measures n-gram overlap and correlates with human jud…
Shrijith Venkatramana, building git-lrc, explains that synthetic data has become a key ingredient for scaling modern large language models. By 2022, frontier AI labs had exhausted much of the public h…
Google's Tensor Processing Units (TPUs) are specialized chips designed for neural network matrix multiplications, differing fundamentally from GPUs. Unlike GPUs, which evolved from graphics rendering,…
Shrijith Venkatramana, building git-lrc, explains the three phases of post-training that transform pretrained LLMs into helpful assistants. The process starts with supervised fine-tuning (SFT) on cura…
Shrijith Venkatramana, building git-lrc, explains that modern AI systems rely on a two-step recipe: generative pre-training followed by discriminative fine-tuning. Pre-training involves predicting the…
Shrijith Venkatramana, a developer building git-lrc, explains that NVIDIA Collective Communications Library (NCCL) is the critical infrastructure enabling multi-GPU training of large language models. …
Shrijith Venkatramana, developer of git-lrc, explains how kernel fusion reduces memory bandwidth bottlenecks in LLM inference. By combining multiple GPU operations into a single kernel, intermediate d…