ChatGPT with voice is now available to all free users

Post by yellow_lead » Wed, Nov 22, 2023, 7:08 AM UTC

madmod wrote: post #140

I just used this to practice my Japanese and it was really helpful having a judgement free correction of my grammar. It definitely takes longer than English because it’s using more tokens but the feedback is very thorough. I wish I could make the pause before sending automatically a bit longer. (I know I can hold to do it manually but the automated send is nice.)

Post by WendyTheWillow » Wed, Nov 22, 2023, 7:20 AM UTC

vore wrote: post #142

superultra wrote: post #114

I’ve been using this for several weeks now and it’s replaced podcasts for me. I’ll just pick a topic and then ask for a summary and then ask clarifying questions. Other times I’ll just goof off. In one chat, I’m rewriting the Star Wars sequels movie by movie with ChatGPT. I’ve realized that I’m built to learn socially, and ChatGPT never tires of my questions or gets annoyed. One interesting story. My 15 year old kid…

How can you tell if ChatGPT is lying to you and what you're learning is total hogwash?

Post by makapuf » Wed, Nov 22, 2023, 7:33 AM UTC

alchemist1e9 wrote: post #123

modeless wrote: post #60

Earlier quoted context omitted.

Currently OpenHermes2-Mistral-7B (via exllama2), OpenAI Whisper (via faster_whisper), and StyleTTS2 (uses HF Transformers). All PyTorch-based. I will probably update to the OpenHermes vision model when Nous Research releases it, so it'll be able to see with the webcam or even read your screen and chat about what you're working on! I also need to update to Whisper-v3 or Distil-Whisper, and I need to update to a newer…

This is why I think the personal Jarvis for everyday use won’t eventually be in the cloud. It can already be done on local hw as you are demonstrating and cloud has big downsides around privacy and latency and reliability. Like you said it’s difficult to keep up with and to me it feels very much like open source stuff might win for inference.

Post by vore » Wed, Nov 22, 2023, 7:34 AM UTC

WendyTheWillow wrote: post #143

vore wrote: post #142

Earlier quoted context omitted.

How can you tell if ChatGPT is lying to you and what you're learning is total hogwash?

I imagine the stakes of rewriting the Star Wars films are sufficiently low that this risk is acceptable...

   I’ll just pick a topic and then ask for a summary and then ask clarifying questions.

Post by vore » Wed, Nov 22, 2023, 7:36 AM UTC

cosmojg wrote: post #146

vore wrote: post #142

Earlier quoted context omitted.

How can you tell if ChatGPT is lying to you and what you're learning is total hogwash?

As long as we're entertained, who cares?