Live
HitlistAI

Open Models14 Oct 2026

Google DeepMind's fine-tuned Gemma spots scams on-device

Why it matters

Built with Singapore's GovTech: Gemma fine-tuned on local scam conversations flags manipulation on the phone, so encrypted chats aren't scanned in the cloud. A lightweight classifier screens messages, then Gemma checks the wider conversation. Training excluded private/PII data.

Read the source: Google DeepMind (opens in a new tab)

All hits from 14 Oct 2026More Open ModelsGet the daily hits by email