Tagged: llm
Showing 31–35 of 70 articles
Three Bets on Long-Context Attention Gemma 4, Qwen 3.6, and DeepSeek V3 each take a different path to long context. A reverse-engineering test shows where the trade hurts. Read article Part 2: Why Pixel Prediction Goes Blurry Yann LeCun says generative models fail on video because the future is ambiguous. I tested the claim with a 700K-parameter PyTorch model on a synthetic bouncing ball. Read article Part 1: Yann LeCun's Bet Against LLMs The LeCun argument in plain terms, with the papers behind it. The map for a five-part series testing his recommendations on a MacBook. Read article Decode throughput is bandwidth divided by model size Single-token decode reads every weight once, so the spec sheet predicts tokens per second before you download anything. Measured against six Qwen models on an M3 Max. Read article pi vs Claude Code: The Philosophical Split Two TypeScript agents with opposite design choices. A half-million-line spaceship versus a four-tool kit. Read article