Claudette, a new friend that makes Claude 3.5 Sonnet even nicer
answer.ai
answer.ai
>According to Douglas Adams, “42.” More seriously, it’s often considered to be finding personal fulfillment, happiness, and purpose.
"Chattiness" still seems to be an issue with LLMs. For many use cases, it is desirable to just get a "42" back, or just the Douglas Adams bit; but that's still quite a challenge to set up in a reliable way. Even using the "command" or "instruct" versions of the best LLMs, answers still diverge significantly. Hope this gets fixed (i.e. trained) soon.
About a year ago, I was trying to get a very concise query from GPT-4.
"Do not write anything else but the specific answer the user requires."
"Be extremely brief and concise."
"Do not write <this> and <that> explicitly."
Nothing seemed to work. GPT always wants to put a little bit more out and that was really bad for my use case.
I asked about this on the OpenAI community but the reception was poor (it is a very toxic community, btw, I'd advise readers to not engage with it).
I'm surprised to see this is still an issue a year later with top of the line LLMs.
Disregarding that, Claudette looks pretty nice, thanks for putting it out for others to use :).