ChatGPT - Good, Bad, Indifferent. What will it change? What does this mean?

WRITING STUFF

[zr]

So happy you're still here! Been assuming/wondering about the secret project for a couple months now, looking forward to the reveal!

[Anders]

Wow, I now tested a headline from CNN and asked ChatGPT: Is this text grammatically correct: "World Cup champion France edges out England to reach semifinals as Harry Kane misses penalty." ? And it replied: "Yes, the text you provided is grammatically correct. It uses proper nouns, verb tenses, and sentence structure to convey a clear and concise message. The sentence is easy to understand and does not contain any errors or inconsistencies. The use of the verb "edges out" is particularly effective in conveying the idea that France narrowly defeated England to advance to the semifinals, and the mention of Harry Kane's missed penalty adds an additional layer of detail and context to the story. Overall, the text is well-written and uses correct grammar."

[RowanSheridan]

I agree that using chatgpt as a replacement for search is very expensive - you argue too expensive. However, I think it's important to consider the benefits that chatgpt provides in terms of the personalized and conversational experience it offers. While it may be costly, it can also provide valuable insights and improve the overall user's "search for an answer" experience. I think the fundamentals of search will change, perhaps tired - in terms of cost of access. So Google will still be used (free + more adverts), but a tool like chatgpt will offer more that just search as we've seen and it will have a subscription model.

[theKonshus]

I will say that using chatGPT for several real-world chats for me, it summarized technical articles and gave me working code where I'd find it worth $0.20 / question. I'm a github copilot user and a little bit in love with its usefulness for the data science I use it for. I don't think this conflicts with what you're saying about it not being a revolution. However, the pace of developments in models and the developer--> public attention has been astounding to me so far. It seems likely to me to lead into an amazing hype cycle.

[rowan]

Last month, I created a chatbot according to your tutorial (hence why I’m subscribed to you), and it’s _far_ better than ChatGPT to the point that I haven’t even tried the latter.

[rowan]

I’d say this is more of an AI spring. I remember looking into making a chatbot using the GPT-3 in the latter half of 2021, searching for tutorials, guides, etc, not finding anything, and resorting to Tensorflow. That didn’t work well for me at all due to the lack of spontaneity and difficulty creating curated training data, so I gave up. Then, about 2 months ago, my interest peaked again after I encountered a new GPT-3 based chatbot called CharacterAI. I once again searched for tutorials and was shocked by how much the GPT-3 had exploded in just a year.

[nuvotion-live]

I’m working on an AGI scripting framework that uses the unofficial ChatGPT API, and I’m mind blowing and very satisfied by the results. I will definitely reach out to you, I’d love to get your perspective. It’s “scripting” in the way that actors read scripts to learn their characters, and can provide feedback on their own roles.

[matts]

Hmmm, ChatGPT sometimes asks me questions actually. It happens when you give it a text with a missing context. Specifically when it is not clear what it should do with the data that I input there.

[Martinit]

I could see a commercial use in marketing: churning out social media posts or blog posts. So basically creative writing in a business context.

[Ianosh]

First question I asked was: "Are you just a GPT-3 model?" It said he wasn't, I don't even think he understood what I was asking...

[Anders]

I asked ChatGPT if it could ask me a question and it replied: "Sure, here is a question for you: What is your favorite thing about learning new things?" But it only followed up with one more question, and then became a bit repetitive. There seems to be a huge difference between GPT-3 and ChatGPT however. GPT-3 said that a jellybean will break a violin into four pieces, while ChatGPT explained why a jellybean can't break a violin in any ordinary circumstances.

[maxziebell]

The utility of GTP, even though it may not be completely accurate, is increasing for many users. I have been using the GTP playground for a while now to stimulate my thinking. It reminds me of the situation with Wikipedia, which is and was often dismissed as unreliable because anyone can edit it. However, even if that is still true to some extent, the usefulness of Wikipedia is too great to ignore.

[Hiroprotagonist]

Great video. Thanks. Do you have a reading list for someone looking to get into AI?

[maxziebell]

What about making it sparse AI… hence, a little down the line, it should become much cheaper to run?