Study compares human and Mixtral-simulated clients in counselling role-play
Novice counsellors practiced with peers and with 4-bit Mixtral 8x7b clients; sentence-level patterns both matched and diverged.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #llm-simulation
Simulated Control Evaluations Predict AI Safeguard Performance
SCEs using language models to simulate environments predict safety with 3.6 percentage point RMSE, outperforming BashArena by explaining 78-85% of variance.