Jev plays Super Mario Bros.
got @typesafeaiβs new model Jev to play Super Mario Bros. fast inference + structured outputs makes it surprisingly good for real time use cases. I'm excited to see what can be done with these new models!
@typesafeai's Jev controls the 2 hands and each finger to play the piano in real-time. Jev only "sees" what we see and plays this from the "note waterfall". It uses @browser_use's jev-ultrafast and some decision scheduling to make this happen in real-time. Sound on πππ

Chandramouly Kandachar
@chandamamz
@typesafeai's Jev controls the 2 hands and each finger to play the piano in real-time. Jev only "sees" what we see and plays this from the "note waterfall". It uses @browser_use's jev-ultrafast and some decision scheduling to make this happen in real-time. Sound on πππ
Jev sits between the incoming context and the next system action. Rather than generating lengthy, slow natural language that requires brittle regex parsing, Jev returns non-autoregressive, calibrated probabilities that downstream code can immediately execute.
got @typesafeaiβs new model Jev to play Super Mario Bros. fast inference + structured outputs makes it surprisingly good for real time use cases. I'm excited to see what can be done with these new models!
We love how this doomo doomonstrates real-time intelligence and what can be doone with code + AI! ~10 calls/sec = ~$7/hour
jev is insane π€― Here is Jev playing subway surfers at super human speed, and also playing 50 games at once. cost less than a cent to do this run. Jev does not replace llms like astra or fable, but opens up an entirely new world of capabilities.