研究
Pockot はオフグリッド計算の下限から始めます。アクセラレーター TOPS、持続ワット、携行バッテリー Wh、モデルサイズ、量子化、ストレージ、オフラインコーパスサイズです。
- 初期 digest：`knowledge/research-digests/2026-05-30-pockot-offgrid-compute-floor.md`
- 最初の基準：Apple M4、Meta Llama 3.2、Raspberry Pi AI HAT+、FAA battery rules、Snapdragon X Elite
- 推定規則：能力階層はヒューリスティックであり、保証ではありません
研究ノートOffline Updating Is Not Automatic Self-ImprovementPockot's north star includes a local system that can keep becoming more useful. That has to be handled carefully. Updating a retrieval corpus, adding notes, training a small adapter, and ...研究ノートTOPS Is a Starting Point, Not a DevicePocket-scale AI hardware is now marketed with large TOPS numbers. Pockot needs to track those numbers, but it also needs to keep them in their lane. TOPS does not specify memory, model qu...研究ノートPocket Solar Is a Power Source, Not a ShortcutEnergy autonomy sounds simple until area, weather, angle, battery safety, charge electronics, and duty cycle enter the model. Pockot should treat solar as a slow input to a watt-hour ledg...研究ノートSmall Models Make the Floor MeasurableThe off-grid question is not "can a pocket device run the largest model?" It is "which tasks become useful at 1B, 3B, 7B, or 13B parameters under a strict power budget?" Pockot needs a mo...研究ノートA Local AI Has to Survive the Watt-Hour LedgerThe simplest off-grid calculation is also the one most likely to be skipped: watt-hours divided by sustained watts. Pockot starts with that ledger because a useful local model is not usef...