Tether's 0.8B BotPsy targets on-device agents and tool calls
Tether AI Research says BotPsy, built on Qwen3.5-0.8B, roughly doubles its base model on BFCL v4, ACEBench and τ-bench, and cuts its unsafe rate under prompt injection from 46% to 31%. Weights are due under Apache 2.0.
Why it matters: Small local models can now take routine tool calls; test one for low-stakes tasks where data must stay on the device. Tether says it still makes mistakes and is not for high-stakes use.
From Drop #080 · Wed, Nov 11, 2026 · Evening