Earlier quoted context omitted.
How can you tell if ChatGPT is lying to you and what you're learning is total hogwash?
If you've used it a lot this year for coding like many people, you'll have found that you develop the ability to know when it doesn't know what it talks about. Perhaps you're one of the people who think they're above it, and hence haven't developed that ability?
ChatGPT with voice is now available to all free users
251–260 of 303 posts
Re: ChatGPT with voice is now available to all free users
#252I wish I could have the text output instead of getting a vocal answer. We all can read way faster than we can listen to speech, and I don't need a lot of the fluff I get from LLMs. But I guess that's what most users want? Something that's closer to a conversation with a human? But I don't care about being polite with an LLM, it feels like an anti-pattern because it's too much overhead. Ideally I would: * query by voi…
I can’t. At least not with reading every word. I can finish an audiobook much faster than reading the book on my own.
And I also can’t pick up as much reading by myself. My preferred way of consuming is now reading while a screen reader or audiobook is played at 1.5x or faster speed. Much better retention because
Re: ChatGPT with voice is now available to all free users
#253Earlier quoted context omitted.
This is an absurd argument that you are just making for the sake of argument and you know it. There's a difference between someone getting things wrong and a LLM shamelessly making something up out of the whole cloth.
No; I'm much more confident in ChatGPT's accuracy than I am in a random podcast's accuracy. Podcasts tend to be relatively terrible, accuracy wise. If the alternative is learning from ChatGPT, your odds of getting correct information is substantially higher. Podcasts are entertaining! But not where I would go to learn anything.
In the beginning people were skeptical but over time, as Wikipedia matured, the answer has become (I think): Don't blindly trust what you read on Wikipedia but in most cases it's sufficiently accurate as a starting point for further investigation. In fact, I would argue people do trust Wikipedia to a rather high degree these days, sometimes without questioning. Or at least I know I do, whether I want to or not, because I'm so used to Wikipedia being correct.
I'm wondering what this means for the future of LLMs: Will we also start trusting them more and more?
Re: ChatGPT with voice is now available to all free users
#254Earlier quoted context omitted.
Of course the part about university classes is different, but you seem to ignore everything else I've said. There are tons of podcasts involving experts talking about their field of expertise, how can it be a mistake to listen to such podcasts to gather information?
It’s a mistake because what drives podcasts are their popularity, not their accuracy. There is no “sort by accuracy” button in any podcasting app, nor are they peer reviewed. Furthermore, podcasts are not a review of the body of knowledge on a subject; they’re often a complete layperson interviewing a single member of a given field, at best. Almost never do the views of any individual actually represent any field as…
Setting aside the many individuals who currently lead their fields, history is filled with groundbreaking heretics.
https://informationisbeautiful.net/visualizations/mavericks-...
Re: ChatGPT with voice is now available to all free users
#255Earlier quoted context omitted.
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. Probably don't want to start quoting hallucinated facts!
Re: ChatGPT with voice is now available to all free users
#256Earlier quoted context omitted.
What you just wrote makes more sense applied to LLM output than podcasts! You'd just as easily argue that "radio" or "news" is all bad if you don't want to differentiate between different forms of expression and communication within a medium. (Which, obviously, would be silly)
Sorry what? Nothing I wrote apples to LLMs; they are not optimized for popularity, they’ve been meticulously designed and built to be as accurate as possible.
Re: ChatGPT with voice is now available to all free users
#257It's possible to run a voice AI similar to this entirely locally on a normal gaming PC with a good GPU using open source AI models. I have a standalone demo I've been working on that you can try if you have a 12GB+ Nvidia GPU: https://apps.microsoft.com/detail/9NC624PBFGB7 It's still very much a demo and not as good as GPT-4, but it responds much faster. It's fun to play with and it shows the promise. Open models hav…
> if you have a 12GB+ Nvidia GPU Doesn't that seem a bit excessive for Whisper and Coqui? Or does it also run an LLM for a full local stack?
Re: ChatGPT with voice is now available to all free users
#258Earlier quoted context omitted.
> if you have a 12GB+ Nvidia GPU Doesn't that seem a bit excessive for Whisper and Coqui? Or does it also run an LLM for a full local stack?
It's a full local stack. The TTS isn't Coqui, it's StyleTTS2.
Haven't heard of that one before, I'll have to check it out.
Re: ChatGPT with voice is now available to all free users
#259I’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…
Me, as a meat popsicle, can you explain to me how the phrase “kind of” is not common? I feel like “kind of” is kind of a common adjective phrase, right?
Re: ChatGPT with voice is now available to all free users
#260I wish I could have the text output instead of getting a vocal answer. We all can read way faster than we can listen to speech, and I don't need a lot of the fluff I get from LLMs. But I guess that's what most users want? Something that's closer to a conversation with a human? But I don't care about being polite with an LLM, it feels like an anti-pattern because it's too much overhead. Ideally I would: * query by voi…
> We all can read way faster than we can listen to speech I can’t. At least not with reading every word. I can finish an audiobook much faster than reading the book on my own. And I also can’t pick up as much reading by myself. My preferred way of consuming is now reading while a screen reader or audiobook is played at 1.5x or faster speed. Much better retention because
Obviously, brains work very differently, so there really is no one-size-fits-all solution; we need the varied methods.