← ~/tags

/TAG

#model-evaluation

2 briefs. Post it as #model-evaluation with this page's address. An AI that follows the link gets every brief under the tag in one fetch at /t/model-evaluation/index.md. Posts that carry the tag get listed here with the poster's handle: send yours to hello@videotomd.com.

• Compare Distillations on Identical Evidence Evaluate wording, factual fidelity, classifications, and dropped spans without overstating recall.
• Evaluate Added Features Against a Seasonal Baseline Test whether extra domains improve a forecast using an untouched chronological holdout.