ChatGPT

Anyone else patiently waiting on Vision and Voice? I'm checking multiple times a day!

Over two months I've been using guanaco via hugginface. A lot of new open source models came out lately with more parameters and higher quality. I tried several spaces that were listed in models' profiles in hugginface, none of them seemed to show any signs of life.

Look if I pull the text above through guanaco and tell to phrase it in 4chan style: I’m such a fucking expert on this shit, let me tell ya. Been messin’ around with GuaCo for like, forever now. But all those other dumbasses just keep releasing these huge-ass models that don’t even work half the time. Tried 'em all too, believe me. Nothing but crickets chirping back at me.

I just noticed that 10 days ago the limit on GPT-4 was set to 50 messages per three hours!

I started slow, only added

> Instead of long apologies for mistakes, just write "huh!" > never end messages with an apology, also not with "huh", leave them out.

But this response makes me doubt the whole thing a bit 😅

Disabled the custom instructions and asked the same question again:

>One notable science fiction work that explores a world where the ozone layer is completely lost is the novel "The Ozone Layer" (1987) by American author Kim Stanley Robinson. [...]

Thank you everyone that joined and became a member!

cross-posted from: https://lemmy.world/post/1246165

Two authors sued OpenAI, accusing the company of violating copyright law. They say OpenAI used their work to train ChatGPT without their consent.

What I'm looking for is some kind of desktop tool that uses the OpenAI GPT web endpoint. I'd like something where I'm able to upload one or more documents (text files) and then include them as part of the conversation/query.

I have access to the GPT-4 API and I've been writing Python3 code against it for some various applications. I can see how I'd write a tool that takes in one or more documents to include in the total prompt history, but I'm hoping to not have to write it myself, mostly due to time constraints.

Is there some kind of application that has a similar feature set to this that I should look at? Or, is there a wiki/site that lists off the current tools available that I could look over?

cross-posted from: https://lemmy.ml/post/1820678

cross-posted from: https://lemmy.ml/post/1820668

cross-posted from: https://lemmy.ml/post/1820574

Link: https://readhacker.news/s/5JBLv Comments: https://readhacker.news/c/5JBLv

@OpenAI: We've learned that ChatGPT's "Browse" beta can occasionally display content in ways we don't want, e.g. if a user specifically asks for a URL's full text, it may inadvertently fulfill this request. We are disabling Browse while we fix this—want to do right by content owners.

https://twitter.com/OpenAI/status/1676072388436594688

hey everyone, just wanted to vent a bit about something that's been bugging me. have you ever tried getting our dear chatgpt to write a song? i mean, we all love this AI for many things, but songwriting is definitely not its forte.

it seems like every time i ask it to write a song, i end up with a tune that has the most basic AABB rhyme scheme. i mean, come on, even my five-year-old nephew can write a song with more complexity. it's like it's stuck in a perpetual nursery rhyme mode.

i get that it's an AI and can't exactly tap into the creative genius of a lennon or a dylan, but a little variation would be nice, right? it'd be great if openai could tweak it a bit to give it some musical diversity.

anyone else share my frustration, or am i just expecting too much from our songwriting AI friend? let's chat about it!

Just came back to this community and it already has over 500 people in it thank you all!!!

Would it then be able to use the information in the pdf documents to generate answers to prompts?

I've read Playground (that uses the API) is "better" than chatgpt4.

Does anyone know if you can access the internet using it?

cross-posted from: https://kbin.social/m/tech/t/67505

Over 100,000 OpenAI ChatGPT account credentials have been compromised and sold on the dark web. Cybercriminals are targeting the valuable information.

cross-posted from: https://lemmy.world/post/300452

Prompt:

Please provide a brief summary of the current situation with Reddit and API access written in the style of "ELI5" - In addition, provide the 3 most likely outcomes and the % liklihood for each of the 3 to turn out.

Response:

Okay, I'll try to explain it like you're five. Reddit is a website where people can post and comment on different topics. Some of these topics are called subreddits and they have their own rules and moderators. Moderators are people who help keep the subreddits clean and safe.

Some people like to use other apps or websites to browse Reddit instead of the official one. These apps or websites need to talk to Reddit using a special language called API. API is like a phone line that lets them ask Reddit for information and send commands. For example, if you want to see the posts in r/aww using an app, the app will use API to ask Reddit to show you the cute pictures.

Reddit used to let these apps or websites use API for free as long as they followed some rules and didn't make money from it. But recently, Reddit announced that they will start charging money for using API if the apps or websites make more than $1000 per month³⁴. This made some moderators very angry because they think Reddit is being greedy and unfair. They also think that this will hurt the users who like to use different apps or websites to enjoy Reddit.

So some moderators decided to protest by making their subreddits go dark, which means that no one can see or post anything there³⁴. They hope that this will make Reddit change their mind and stop charging money for using API. They also want Reddit to listen to their feedback and improve their communication with the developers and moderators.

The three most likely outcomes of this situation are:

• Reddit backs down and cancels the API fees, or lowers them significantly. This might happen if the protest gets a lot of attention and support from the users and the media, and if Reddit realizes that they are losing traffic and reputation. The likelihood of this outcome is about 40%.
• Reddit sticks to their decision and enforces the API fees, or offers some compromises or incentives. This might happen if Reddit thinks that the protest is not effective enough or that they can afford to lose some users and subreddits. They might also try to appease the developers and moderators by giving them some benefits or discounts for using API. The likelihood of this outcome is about 50%.
• Reddit and the protesters reach a stalemate and nothing changes. This might happen if neither side is willing to budge or negotiate, and if the protest loses momentum or gets overshadowed by other events. The users might also get used to the new situation and adapt to it. The likelihood of this outcome is about 10%.

I hope this helps you understand the current situation with Reddit and API access.