Much faster, 10x cheaper and still good enough for most things.
I don't think gpt-4 is worth its 10fold price premium for all but niche usecases (coding may be one but I don't do that too much). And the much longer response delays are annoying.
I think 3.5 turbo is a really nice general use model. And the price difference makes it worry free (I use it a lot and most months I used less than $1) whereas gpt-4 really tends to trigger disturbing invoices after using it a bit :)
I still have 4 on tap for a second opinion if I'm dissatisfied with gpt-3.5 but in general it doesn't really yield much better results, whereas better prompt engineering helps much more with both models.
Of course YMMV but I wouldn't write gpt-3.5 off just because it's no longer the coolest kid on the block.
I don't trust Google enough to feed them my data though. I don't even use a google account on my Android devices :)
OpenAI and Microsoft aren't a lot better but it is somewhat better at least.
So Gemini isn't an option for me. Curiously enough, LLaMa 2 is, even though it's from meta, but the fact that you can run it at home is of course a real winner for privacy.
Still great. The better students get at writing prompts, the better they get at formulating what they want, learning to be more precise, and seeing how what they say could be confusing. Think of how search engines [used to] train people to use basic logic to disambiguate.
Yes it is GPT-3.5 access through Azure if I am correct. University of Oslo has already done this for their staff and students. They have built a UI https://www.uio.no/english/services/it/ai/gpt-uio/index.html . They call it privacy-focused chatgpt but it is poor quality UI and doesnt have access to GPT-4.
I don't think gpt-4 is worth its 10fold price premium for all but niche usecases (coding may be one but I don't do that too much). And the much longer response delays are annoying.
I think 3.5 turbo is a really nice general use model. And the price difference makes it worry free (I use it a lot and most months I used less than $1) whereas gpt-4 really tends to trigger disturbing invoices after using it a bit :)
I still have 4 on tap for a second opinion if I'm dissatisfied with gpt-3.5 but in general it doesn't really yield much better results, whereas better prompt engineering helps much more with both models.
Of course YMMV but I wouldn't write gpt-3.5 off just because it's no longer the coolest kid on the block.