[bgirard]

Last week I got together with my math alumni friend. We cracked some beers, we chatted with voice mode ChatGPT and toyed around with Collatz Conjecture and we sent some prompt to a coding agent to build visualizations and simulation. It was a lot of fun directing these agents while we bounced off ideas and the models could explore them.

I think with the right problem and the right agentic loop it’s clear to me improvements will speed up.

[drakenot]

I think voice mode uses weaker models, just an FYI relative to the SOTA

[pxc]

The bigger problem for me is that the realtime voice modes lack tool use, so they can't look anything up or do anything. Model strength definitely also matters, but even dumb models can be helpful when they can look things up and try things out. And smart models that don't do those things kinda suck.

[SOLAR_FIELDS]

Can get around this with a local STT model and use text input but UX is probably clunkier

[scrollop]

Definitely, seems like gpt 3