https://quantid-measurement-lab.static.hf.space/Measurement-first analysis of AI benchmarks, scientific computing and AI risk diagnostics, with open methods and live data.https://quantid-measurement-lab.static.hf.space/a/typed-decisions-new-number-one.htmlhttps://quantid-measurement-lab.static.hf.space/a/typed-decisions-new-number-one.htmlA measurement note on the Typed Decisions official benchmark, which now has a new #1 at 0.81 holding both first and second place.2026-10-16T09:20:00+09:00https://quantid-measurement-lab.static.hf.space/a/prove-training-on-new-hardware-099-test.htmlhttps://quantid-measurement-lab.static.hf.space/a/prove-training-on-new-hardware-099-test.htmlA falling loss curve does not prove correct training. The rigorous check is a controlled comparison against a GPU reference. A recent NPU pretraining run reports a 0.99 loss-trajectory correlation.2026-10-15T09:40:00+09:00https://quantid-measurement-lab.static.hf.space/a/measuring-real-cost-llm-call.htmlhttps://quantid-measurement-lab.static.hf.space/a/measuring-real-cost-llm-call.htmlHow to measure the true cost of an LLM call beyond the sticker price per million tokens. Precision weighting, first-token latency, and why the same flags are not the same conditions.2026-10-12T20:10:00+09:00https://quantid-measurement-lab.static.hf.space/a/quantum-challenge-simulation-and-qec.htmlhttps://quantid-measurement-lab.static.hf.space/a/quantum-challenge-simulation-and-qec.htmlTwo measurable quantum tasks, simulation and QEC decoding, now run as an open challenge on classical GPUs with a public harness. 2,000 USD in prizes, reproducible scoring.2026-10-11T00:20:00+09:00https://quantid-measurement-lab.static.hf.space/a/ai-native-the-evidence.htmlhttps://quantid-measurement-lab.static.hf.space/a/ai-native-the-evidence.htmlPerfect AIME and HMMT, GPQA Diamond 94.44, 165M downloads, quantum hardware access, and a national-security safety system. The measured record behind an AI-native, pre-AGI lab.2026-10-11T00:10:00+09:00https://quantid-measurement-lab.static.hf.space/a/eleven-number-one-benchmark-records.htmlhttps://quantid-measurement-lab.static.hf.space/a/eleven-number-one-benchmark-records.htmlOne self-improving model family holds eleven public number-one benchmark records, from perfect AIME and HMMT scores to GPQA Diamond 94.44 and S1MB. Here are the measurements.2026-10-11T00:00:00+09:00https://quantid-measurement-lab.static.hf.space/a/measuring-typed-decision-ai-s1mb.htmlhttps://quantid-measurement-lab.static.hf.space/a/measuring-typed-decision-ai-s1mb.htmlA 870M dollar round made typed, machine-native AI a headline. We look at how to measure it: what the S1MB benchmark tests, and the number one result among 102 models.2026-10-10T00:00:00+09:00https://quantid-measurement-lab.static.hf.space/a/who-leads-hugging-face-official-benchmarks-concentration-gaps-hidden-entries.htmlhttps://quantid-measurement-lab.static.hf.space/a/who-leads-hugging-face-official-benchmarks-concentration-gaps-hidden-entries.htmlWe measured all 48 official Hugging Face benchmark leaderboards: Gini 0.71, top-10 orgs hold 49.5% of entries, 30.4% hidden by default.2026-10-05T18:00:00+09:00