On own benchmark evals
is anyone else here having the same session with 10 different agents via OpenRouter on pi?
it may not be much, but it’s my own benchmark eval
or agent psychosis creeping in
— Albin H. on X, August 21, 2026
is anyone else here having the same session with 10 different agents via OpenRouter on pi?
it may not be much, but it’s my own benchmark eval
or agent psychosis creeping in
— Albin H. on X, August 21, 2026