There doesn’t seem to be any indication whether this is available in the chat-got app nor is there any indication in the app that anything has changed. Anyone know how to actually try this?
Read the post
GPT‑Live
41–50 of 556 posts
Re: GPT‑Live
#42Is it possible to create a "companion" of sorts with this model, using, say, an RPi and a speaker + microphone? Not for advanced scientific brainstorming, but for seniors who are often alone in their homes.
Re: GPT‑Live
#43I had preview access to this one for a few weeks. It's very good. I had one conversation that lasted a full hour while I was walking the dog, got some good brainstorming done against one of my projects. The best feature is that it can delegate questions out to GPT-5.5 in the background, so you're no longer restricted to a voice model that's several years behind the frontier. I did report a fun bug with it though: it…
But does it generate good pelicans?
Re: GPT‑Live
#44>GPT‑Live can show it’s paying attention with phrases like “mhmm” or “yeah” [...]
Nooooooo!
Re: GPT‑Live
#45I like this and felt like some of it was much more fluid; but was I alone in feeling like the interjected "uh-huh" or "yeah?" moments felt a little jarring? Almost felt a bit *uncanny valley* for what "natural" conversation is supposed to be like. If the "uh huh" isn't timed correctly, it'll feel like a zoom call with lag.
I agree. Many times those little interjections don't feel natural. It's impressive, but there's still a lot of room for improvement.
Re: GPT‑Live
#46I had preview access to this one for a few weeks. It's very good. I had one conversation that lasted a full hour while I was walking the dog, got some good brainstorming done against one of my projects. The best feature is that it can delegate questions out to GPT-5.5 in the background, so you're no longer restricted to a voice model that's several years behind the frontier. I did report a fun bug with it though: it…
Is it a dumb-down version of GPT like the current voice model? At least in french, I find the current GPT voice mode to be useless, to the point I only use the dication mode. I would ask a question and it would answer something along "That's a interesting question. I can help you with that. Anything you want to know about X?" I would ask again and it would answer the same kind of non answer.
Click through to the link, the answer is no it uses the latest gpt models now.
Re: GPT‑Live
#47This feels so dehumanising.
Re: GPT‑Live
#48Is it possible to create a "companion" of sorts with this model, using, say, an RPi and a speaker + microphone? Not for advanced scientific brainstorming, but for seniors who are often alone in their homes.
If this is my idea of hell, I can't imagine what it'd be like for a 90 year old
Re: GPT‑Live
#49Are there any open source full duplex models that are out besides PersonaPlex? There was a chinese open one, maybe Fun Audio chat or something, that said it was going to release a full duplex version but I am not sure if it did. My dream would be open source full duplex with function calling or some kind of rudimentary text output. PersonaPlex is still interesting although it was looking like we would need to fine tu…
I want to know this too, as I’m hoping to fabricobble up a “smart speaker” that communicates with my local AI assistant. Right now we do everything via iMessage but it would be nice to be able to tell it to add things to my grocery list by voice while my hands are busy in the kitchen. Also would love if anyone has any advice on what microphone & speaker to pick out, was planning on just reusing a raspberry pi I’ve go…
if you don't find that then you could fake it with personaplex possibly but making another ASR/STT model just listen continuously and transcribe then send to an LLM with function calling. at least that would allow one direction easily.
Re: GPT‑Live
#50Does this model do better ignoring side conversations? That's the biggest hindrance to using ChatGPT's carplay feature is someone will say something, stopping ChatGPT from speaking or taking it in a different direction.