Whenever I wonder what cool application I would personally build with #GPT models, I keep coming back to the problem that there's zero guarantee of "worst-case" performance.
When I put on my software engineering hat, my first thought is always to ask "what could go wrong and how?" The answer of #LLM|s is that things could go wrong in completely unpredictable ways, we just try to make it statistically unlikely.
Using #GPT to build a product is like programming a calculator that gives the right answer 90% of the time, but in 8% of cases fails in subtle and hard-to-notice ways, and in the remaining 2% it claims to be a potato farmer, insults the user, or deletes your hard drive.
Yet somehow people are okay with that, because when it's in the 90%, it's a really really awesome calculator?
2/3
Think like a business clown, not like an engineer.
You need something that seems to work on the surface and is cheap. Then you sell it for a profit and if people begin to cry you say, sorry people! software's always been shitty, everybody knows that. We might fix this in the next release if you're lucky.
Meanwhile you competitors, stupid enough to put actual work and effort into their product, silently leave the market because they are prohibitively expensive.
Marcel Bollmann 
Dieu