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…
Maneshwar, building LiveReview, cut the cost of an AI code-review run from over 50 cents to about 4 cents by replacing Gemini's hosted File Search with a local Chroma vector store embedded with Qwen3-…
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…
Maneshwar, a developer building the LiveReview AI code review tool, has demonstrated a retrieval-augmented generation pipeline in Go that uses Gemini's File Search instead of a vector database, requir…
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…
Rijul, a developer building the AI code review tool LiveReview, explains why retrieval-augmented generation systems fail to surface information that is present in a source document. The core issue, he…
Rijul, a developer building the AI code review tool LiveReview, published an explainer comparing two methods for aligning language models with human preferences: Direct Preference Optimization (DPO) a…
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…
Rijul, a developer building the AI code review tool LiveReview, outlined why vector search alone is insufficient for retrieval-augmented generation systems and argued for hybrid retrieval. The writeup…
Developer Rijul built a demonstration project showing how knowledge poisoning attacks can manipulate retrieval-augmented generation (RAG) systems by planting false, malicious, or misleading documents …
Rijul, a developer building the AI code review tool LiveReview, outlined the difference between autoregressive and diffusion-based text generation. Autoregressive models, used by most deployed languag…
Maneshwar, a developer building the AI code review tool LiveReview, explains how HyperLogLog can estimate cardinality for massive datasets like 100 billion unique visitors using only about 12 kilobyte…
Developer Rijul describes Vectorless RAG, an approach that replaces similarity-based vector retrieval with document structure and reasoning to address fragmented context, weak relevance, and opaque re…
Maneshwar, an engineer building the AI code review tool LiveReview, outlined seven infrastructure patterns that determine whether an AI application can survive scaling to 10,000 users. The patterns co…
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…
Uber's DeepETA system predicts arrival times by dividing roads into roughly 100 million segments and using driver GPS pings collected every four seconds as live traffic telemetry, then forecasting seg…
A developer's exploration of the Allen Institute for AI's OLMo repository reveals the components required to build an open large language model, including dataset provenance, tokenizer implementation,…
Developer Rijul, creator of LiveReview, explains the concept of an 'open stack' in AI, contrasting it with open-weight models. He notes that open-weight models like Llama, Mistral, Gemma, and Qwen pro…
Maneshwar, a developer building LiveReview, an AI code review tool, shares seven techniques for making APIs faster, emphasizing that optimization should follow measurement and profiling. The technique…