o1 is a much larger, more expensive to operate on OpenAI's end. Having a smaller "newer" (roughly equating newer to more capable) model means that you can match the performance of larger older models while reducing inference and API costs.
The HP Prime, though pricy, supports a decent RPN mode. Definitely for a higher level of education (CAS, programs, all that fun stuff), but approved for a decent amount of US based exams.
Definitely an improvement over your normal Text-To-Speach model, and to some degree really different, but the subtle imperfections do appear and ruin the overall perception. A move in the right direction, though, I suppose.
Yeah after a few interactions, the repetition of the mannerisms that initially added to the sense of life-likeness started to break the illusion a bit. The "you got me" response shows up a bit too often. The creativity remains impressive though
I’d like that idea, but I feel like more would have to go into it. Things like user-accessible updates/reflashing, or someone to care enough about the software to fix it for use by everyone else. Support requirements + this are probably a better way to go.
