News for hackers. Stuff that matters.

A comment on GPT-4o. Parent comment

Re:GPT-4o by navigate8310 on Monday May 13, 2024 @02:24PM (#40346527)
> voice sounds like an over enthusiastic podcast interviewer

I believe it can be toned down using system prompts, which they'll expose in future iterations

[ Parent | on HN ]
Re:GPT-4o by TacticalCoder on Monday May 13, 2024 @06:00PM (#40349005)
As in the Interstellar movie:

    chuckling to 0%

    no acting surprised

    not making bullshit when you don't know
[ Parent | on HN ]
Re:GPT-4o by sangnoir on Monday May 13, 2024 @06:36PM (#40349379)
> not making bullshit when you don't know

LLMs today have no concept of epistemology, they don't ever "know" and are always making up bullshit, which usually is more-or-less correct as a side effect of minimizing perplexity.

[ Parent | on HN ]
Re:GPT-4o by xarope on Tuesday May 14, 2024 @12:44AM (#40351686)
Oooh, now I want me a TARS...
[ Parent | on HN ]