Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How OpenAI delivers low-latency voice AI at scale

openai.com

Post reply on HN
Print view View original

161–170 of 172 posts

Re: How OpenAI delivers low-latency voice AI at scale

#161

Post by pstuart »

a456463 wrote: post #48
thatxliner wrote: post #33

Earlier quoted context omitted.

slightly unrelated but what’s with storing the entire codebase in the root directory instead of a nested src folder? It makes getting to the README a lot more difficult

This is valid criticism. Go fanbois don't like listening to any go criticism. They were all like who needs templates in go. and now go has templates. To me go code looks like somebody vomitted stuff in the root dir and i have to wade through that every time. No namespacing. nothing

I believe it was "They were all like who needs generics in go. and now go has go generate and templates."

I guess I qualify as a Go fanboi -- it is not perfect but gets the job done for a lot of us, sorry it doesn't work for you.

But back to your point about "vomit in the root dir", Go does have namespacing of sorts via packages, and the pattern you criticized is not the only way -- often just a simple main.go at the root bringing in packaged functionality.

Re: How OpenAI delivers low-latency voice AI at scale

#162

Post by dgunay »

thatxliner wrote: post #33
Sean-Der wrote: post #23

Very grateful that OpenAI published the article/publicized their usage of Pion[0] a library I work on. If you aren't familiar with WebRTC it's a super fun space. I work on a book WebRTC for the Curious [1] that details how it works. [0] https://github.com/pion/webrtc [1] https://webrtcforthecurious.com

slightly unrelated but what’s with storing the entire codebase in the root directory instead of a nested src folder? It makes getting to the README a lot more difficult

FWIW I usually don't structure my Go projects this way unless they're very very small. This is what I usually do for anything larger than 2-3 files:

  ├── cmd
  │   └── binary-name
  │       └── main.go (may subpackage for things like CLI porcelain, etc)
  ├── go.mod
  └── internal
      └── app.go (and subpackages, etc)

Re: How OpenAI delivers low-latency voice AI at scale

#164

Post by fragmede »

tedsanders wrote: post #106
fragmede wrote: post #45

Earlier quoted context omitted.

GPT 5.5's knowledge cutoff is August 2025. Which aspect of WebRTC has meaningfully changed since then?

Dec 2025, actually: https://developers.openai.com/api/docs/models/gpt-5.5 (though knowledge cutoffs in practice can be bit fuzzy)

That's what I get for trusting the output of the LLM instead of checking the docs!

Re: How OpenAI delivers low-latency voice AI at scale

#165

Post by NikolaNovak »

drusepth wrote: post #11
NikolaNovak wrote: post #8

Earlier quoted context omitted.

Fwiw - I found the advanced AI voice feature to be actually detrimental. It's good if you just want a single sentence answer. I've turned it off though when I want a more detailed, structured, considered answer.

Interestingly, that kind of parallels the real world too: if you want a quick and high level answer, talk to someone in person; if you want something detailed and info-dense, get them to write it down.

Turning advanced voice still leaves "regular" voice interaction which are actually (for me:) much much better - it's just the regular response, verbalized :). Voice quality isn't worse, it just doesn't try to summarize in one casual sentence.

(I still hate that the voice is getting more and more "natural" - the umms and ahhs and weird pauses)

Re: How OpenAI delivers low-latency voice AI at scale

#167

Post by hadlock »

drusepth wrote: post #11
NikolaNovak wrote: post #8

Earlier quoted context omitted.

Fwiw - I found the advanced AI voice feature to be actually detrimental. It's good if you just want a single sentence answer. I've turned it off though when I want a more detailed, structured, considered answer.

Interestingly, that kind of parallels the real world too: if you want a quick and high level answer, talk to someone in person; if you want something detailed and info-dense, get them to write it down.

The AI attached to their voice chat is running a completely different model. Ask any question and you quickly realize it is completely, unapologetically lobotomized. If you want to talk to it about how you feel after your gf/bf broke up with you, it is fine. If you want to ask it something about tunneling machines and how tunneling through different types of rock impact engineering decisions, it is going to skim the first four sentences of some blog article and then defend whatever hill it has chosen until it dies, regardless of what the larger body of work on the topic says. OpenAI's voice chat being so bad and being totally divorced from their SOTA models is largely why I cancelled my subscription. I am tempted to wire up piper/whisper and the OAI api to get back what I actually want/need. But today you cannot have a conversation about engineering questions and get anything close to factually reliable answers out of it.

Re: How OpenAI delivers low-latency voice AI at scale

#169

Post by a456463 »

idiotsecant wrote: post #109
a456463 wrote: post #48

Earlier quoted context omitted.

This is valid criticism. Go fanbois don't like listening to any go criticism. They were all like who needs templates in go. and now go has templates. To me go code looks like somebody vomitted stuff in the root dir and i have to wade through that every time. No namespacing. nothing

Ok... The question was why is it like that. The answer is because it's in go. Nobody was anything other than civil before you neckbearded in here. Chill. There's a sane way to say what you said.

I wish I could grow a beard. Also as far as being civil: please watch literally any Rob Pike vibe chastizing Python and Java communities to no end. It is that rhetoric. That is why Go has fanbois. They can only see what the Gopher says and what Rob Pike says. Nothing else.

Re: How OpenAI delivers low-latency voice AI at scale

#170

Post by a456463 »

junon wrote: post #63
a456463 wrote: post #48

Earlier quoted context omitted.

This is valid criticism. Go fanbois don't like listening to any go criticism. They were all like who needs templates in go. and now go has templates. To me go code looks like somebody vomitted stuff in the root dir and i have to wade through that every time. No namespacing. nothing

I don't like go as a personal preference but reducing them to "fanboys" is a bit reductive. I'm sure the same could be said about your own favorite language.

Also as far as being civil: please watch literally any Rob Pike vibe chastizing Python and Java communities to no end. It is that rhetoric. That is why Go has fanbois. They can only see what the Gopher says and what Rob Pike says. Nothing else.

Other languages have fanbois but they didn't disparage and denigrate other communities to prove themselves.

Post reply on HN