Skip to content On the map On the map: Model evaluation related to related to Model evaluation — Methods and metrics used to estimate how well a model will perform on data it has not seen. Model evaluation Machine learning — The field that studies how computers improve their performance on a task by learning patterns from data rather than being explicitly programmed. Machine learning Formal verification — Establishing with a mechanical checker, such as the kernel of a proof assistant like Lean, that a statement or a program meets a precise mathematical specification. Formal verification Statistical power — The probability that a test detects an effect of a given size when the effect is really there; it grows with the sample size and the size of the effect. Statistical power Benchmark saturation — The state of a benchmark on which current models score so close to the maximum that it no longer separates them. Benchmark saturation Data leakage — Information that would not be available in real use reaching the model during training or evaluation, making performance look better than it is. Data leakage Evaluation harness — The software that runs a model on a benchmark: it builds the prompts, calls the model, executes or scores the outputs and aggregates the results. Evaluation harness Fifteen ways my coding agent and I mis-measured two models on one DGX Spark — Before you compare models on your own hardware, fix the sampling, the token budget, the harness and the number of runs: on one DGX Spark, three of the four moved a score by more than the gap between the models. Fifteen ways my coding agent and I… Small agent teams win by trying more, not by coordinating — A six-worker GLM-5.3 team proved more Lean statements than one agent of the same model, but four copies that could not talk to each other matched it. Here there is no evidence that coordination adds: try independent attempts with a verifier first. Small agent teams win by trying more, not… Speculative decoding on GB10: a wider draft speeds up one stream and slows sixteen — Choose the speculative-decoding draft width for the number of users you serve: in darkdatter's sweep on a DGX Spark, 16 draft tokens instead of 8 made one stream 28% faster and sixteen streams 10% slower. Speculative decoding on GB10 The 1,802-second hang: serving a hybrid linear-attention MoE under agent load — In July I ran coding-agent evaluations on SWE-bench Verified against Qwen3.6-35B-A3B, served by vLLM 0.21 ( ) on one DGX Spark, four requests at a time. The… The 1,802-second hang Show on the main map → Narrower concepts Benchmark saturation The state of a benchmark on which current models score so close to the maximum that it no longer separates them. Data leakage Information that would not be available in real use reaching the model during training or evaluation, making performance look better than it is. Evaluation harness The software that runs a model on a benchmark: it builds the prompts, calls the model, executes or scores the outputs and aggregates the results.