Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong. Parent comment
2. We combine both on Cactus; rolling entropy method helps with per-token signal for early exit, while the probe runs on complete output.
3. Users hate this in production, drains battery on edge devices, but ultimately primarily works ok-ish on 7B+ models, we will share the results too.
There are no comments on this comment yet.
2. We combine both on Cactus; rolling entropy method helps with per-token signal for early exit, while the probe runs on complete output.
3. Users hate this in production, drains battery on edge devices, but ultimately primarily works ok-ish on 7B+ models, we will share the results too.