Hacker News new | ask | show | jobs
by hn_user82179 475 days ago
It was genuinely startling how human it felt. Apparently they are planning on open-sourcing some of their work as well as selling glasses (presumably with the voice assistant). I’m very excited to have a voice assistant like this and am almost a bit worried I will start feeling emotionally attached to a voice assistant with this level of human-like sound.
2 comments
jofzar 475 days ago
I still feel like they don't have the right amount of human to them, maybe it's because I'm Australian and it sounds like I'm hearing an American robot?

Edit: well I asked the "male" model to speak more like an Australian and yep, getting way more uncanny. If it had an Australian accent I think it would mess with me more

link
igleria 475 days ago
Maybe the ability to personalize the voice so it is more... robotic or based on a fictional thing like Knight Rider would help to change the attachment to something more... healthy?
link
MarcelOlsz 475 days ago
Yeah this is straight up creepy, and I also can't stand chatgpt saying "Lmao" and "Yeah". Keep it formal & robotic.
link
WesolyKubeczek 475 days ago
What ever did you tell ChatGPT so it responded with "lmao"?

I told it that it should behave explicitly like a computer in the system prompt, sort of worked.

link
MarcelOlsz 474 days ago
After multiple prompts and utterly garbage output: https://i.imgur.com/5aOARCV.png

I'm almost positive that some AI systems have a backend that analyzes the sentiment of your messages and if you threaten to cancel billing it will notice your defcon-1 sentiment and spin up some more powerful instances behind the scenes to tide you over.

This is actually much more stressful than working without any AI as I have to decompress from constantly verbally obliterating a robotic intern.

I'll try with the system prompt. Also love your username.

link
WesolyKubeczek 474 days ago
> After multiple prompts

It generally maintains the tone you set. Remember that it outputs most likely tokens based on the system prompt of its owners + your system prompt + the whole conversation. If OpenAI and default system prompt tell it that it's a helpful cheerful secretary/assistant, you get best results if you talk to it "professionally".

I heard you could make Claude say "kurwa" a lot while helping you program in Go if you convince it that you want a conversation with your ziomek Seba from your backyard with whom you like to share kebab and browar, so there goes.

link