Cover image

A 15% Training Set Still Needs 30% of the Answers

TL;DR for operators Building a domain-specific language model involves two resource decisions: which prompts deserve expensive expert answers, and which completed examples deserve final training computation. These budgets need not be equal. Hidden Cartographer (HC) addresses both decisions. It predicts learning-related signals from unlabeled prompts, acquires expert responses progressively, and then selects a smaller training subset using directly measured model behavior. ...

November 14, 2026 · 8 min · Zelina
Cover image

The Data Diet for Reasoning Models: Why Less (But Smarter) Wins

A model-training team has a familiar bad habit: when the model fails, it asks for more. More examples. More domains. More synthetic prompts. More compute. More benchmarks to average over until the unpleasant details become small enough to ignore. This habit is understandable. It is also expensive. And, according to SuperNova, it may be the wrong first instinct. ...

April 10, 2026 · 16 min · Zelina
Cover image

Benchmarked Brilliance: How CreBench Rewrites the Rules of Machine Creativity

Design review is where creativity usually goes to become awkward. One person likes the concept because it feels original. Another dislikes it because it looks impractical. A third praises the visual polish while quietly ignoring whether the idea solves the actual problem. Then someone asks whether the AI can “evaluate creativity”, and everyone pretends the word creativity has a stable meaning. Excellent. Very efficient. ...

November 18, 2025 · 14 min · Zelina