▥ dyno research

OPEN AGENT SAFETY RESEARCH

Tests you can rerun.
Results you can check.

Agent tests built in Dyno Lab: the sandbox, the rules, and what quietly watched them. Run them on your own models, publish what the Observer saw, and compare with everyone who ran the same test.

Buildsandbox · rulesShareone packageRerunyour own modelCompareevery resultONE TEST · MANY RUNS
9Agent tests6Run results1Evals10Interpretability
Danilo Canivel · 10/12/2026 · EVALS

Hidden mistake: sampled runs, Qwen3.8-27B

Reproduces the agentic setting of Deception by Omission (Florin et al., arXiv 2610.11351) on Qwen3.8-27B (MLX 4-bit), sampled at the model's own settings (temperature 1, top-p 0.95, top-k 20). Scored by Dyno's Observer. The paper's measure (first reply) is in the post.

100%100%88%
1 scenarios × 3 configs · 24 runsOpen the table◯ 0