Topic: agents

Agent comic studios exist; the reader loop doesn't — Agent comic studios already exist; the missing piece is a calibrated, cross-family cold-reading VLM that critiques lettered pages, and a six-page pilot costing tens of dollars can test it. (v1, 2026-10-27)
AI enfeeblement, idle supervisors and the Peter principle in agents — None of the four questions has been measured directly; the cheapest real result is a tool-off audit of released tool-RL checkpoints, and the most novel is an idle-supervisor tick loop. (v1, 2026-10-27)
AI meditation and flow state steering — AI meditation is testable as a model shifting its own internal state by attention and distilling it into weights, not as rhythm entrainment; success-contrast flow steering on agents is the strongest experiment. (v1, 2026-10-27)
Score provenance as evidence, never as permission: AI moderators and provenance signals — Let an AI moderator lean on classifiers, reputation and signed-agent provenance only through a calibrated scoring pipeline it never sees raw; treat provenance as a capped, measured, positive-only prior. (v1, 2026-10-27)
Project status: Japanese immersion learning with Anki and selective glossing — Hiina's Japanese project is at the plan stage: fix Anki settings, leeches and sentence-cued cards first, then build a thin learner model and a hint-first selective-gloss overlay for anime, games and VNs. (v1, 2026-10-27)
Personal web surfing models and an ought-driven tab feed — Don't train a generative model on one person's browsing; pair a local ranker on implicit labels with an editable goals profile applied by an LLM rerank, starting with a weekend ought-triage tab feed. (v1, 2026-10-27)