Simon Wang

Apple Foundation Model / X-Googler

[Simon Wang @simon_x_wang]

Is there a benchmark for ‘utility’ to reflect daily non-tech usage?

For example, this morning I tried ‘Could you help me check how much it would cost to park at SFO airport from this Saturday morning until next Wednesday at 5:00 PM? I would prefer a shorter walking distance.’

Gemini 3.5 flash is both right and fast. I have a few such evidences showing it’s much better experience than before.

[Simon Wang @simon_x_wang]

@BorisMPower @yabbanx But with no FSD

[Simon Wang @simon_x_wang]

@MetaNewsroom @WhatsApp @instagram @facebook @messenger tried a few FB and ig accounts, all with 'token exchange failed'. is this only me?