People often think that fine-tuning is what the should be aiming for.
Funnest part from the talk was the story of fine tuning GPT-3.5 on the company slack so it "learned their tone of voice".
The result:
> Human: Write a 500 word blog post on prompt engineering
> AI: Sure
I shall work on that in the morning"
> Human: "Do it now
> AI: "ok"
jordn|2 years ago
The result:
> Human: Write a 500 word blog post on prompt engineering > AI: Sure I shall work on that in the morning" > Human: "Do it now > AI: "ok"
siva7|2 years ago