Machine Learning

Sarvam Vision 2.1 is the first OCR model to handle both Indian language scripts and English document structure without sacrificing either.

Polars is a Rust-based DataFrame library built for speed and efficiency. This cheat sheet covers its core functionality for high-performance data processing.

Brave Leo is a built-in browser AI assistant that processes queries without storing data or requiring an account, making it well-suited for sensitive profession

Jev is a new AI model that returns structured judgments instead of generating text, designed for automated decision-making inside software.

JONI positions itself as an orchestration and execution layer above foundation models. Here's how its architecture and routing work in practice.

Five leading agentic coding CLIs compared across autonomy, tooling, permissions, cost, and real-world engineering workflows.

ArrowJS positions itself as the first UI framework built for AI coding agents. Here's what that means for data scientists building AI-powered apps.

NVIDIA NeMo Switchyard is an open-source routing layer that directs LLM requests to the right model based on complexity, saving cost and latency.

Spec-driven development with Claude Code fails when criteria have no failing state. Here's how to write specs that prevent agents from self-certifying completio

PagedAttention and RadixAttention solve the two core KV cache problems in LLM serving: memory fragmentation and redundant prefix computation.

A blind experiment comparing RAG and long-context retrieval on 12 questions across 32 articles, measuring cost, latency, and answer quality.

Three practical strategies for managing small LLM context windows, with Python examples covering sliding windows and token budgeting with RAG.