Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
By HenryNdubuaku · 2026-07-22 · 2 points · 1 comments
https://github.com/cactus-compute/cactus-hybrid
Hey HN, Henry & Roman here from Cactus. A small, on-device model is fast and private, but sometimes wrong, but frontier models are getting expensive pretty fast. So, we post-trained Gemma 4 E2B post-trained to know when it's wrong. Every response comes with a confidence score be…
Open the full discussion on BetterNews