Remix.run Logo
pennomi 4 hours ago

Tuning the model so far in the direction of being aggressively useful that it will quickly go off the rails in the name of helpfulness.

I swear I spend more time telling Claude not to do things than telling it what to do.

vintermann 2 minutes ago | parent | next [-]

I guess the agentic coding benchmarks don't have many rewards for stopping and clarifying what the user wants?

mdp2021 34 minutes ago | parent | prev [-]

> aggressively useful ... in the name of helpfulness

But is that because of training, or can that be (also? mostly?) an effect of the "system prompt"?