3.5 was like Jenny from customer service. davinci-001 was like Jenny the dreamer trying to make ends meet by scriptwriting, who was constantly flagged for racist opinions.
Both of these had an IQ of around 70 or so, so the customer service training made it a little more useful. But I mourn the loss of the "completion" way of interacting with AI vs "instruct" or "response".
Unfortunately with all the money in AI, we'll just see companies develop things that "pass all benchmarks", resulting in more creations like GPT-5. Grok at least seems to be on a slightly different route.
I do think GPT-4.1 onwards has a lot of personality. It's able to pretend to go into this mindset and go back out, which works fine. If I wanted to talk to actual racists, there's plenty out there. But I just want the spicy flavor in my AI because it's a little bland otherwise.
How do you use the product to get this experience? All my questions warrant answers with no personality.