Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT Plugins

openai.com

Post reply on HN
Print view View original

241–250 of 1001 posts

Re: ChatGPT Plugins

#241

Post by MagicMoonlight »

mariojv wrote: post #97
kenjackson wrote: post #23

The rate of improvement with GPT has been staggering. In just January I spent a lot of time working with the API and almost everything I've done has been made easier over the past two months. They're really building a platform. Curious to see where this goes over the next couple of years.

I agree. Part of me wonders how much they're using GPT to improve itself.

When we were first breaking it people were wondering if the developers were sitting in threads looking for new exploits to block.

Now I’m wondering if the system has been modifying itself to fix exploits…

Re: ChatGPT Plugins

#242

Post by majormajor »

sfink wrote: post #190
beepbooptheory wrote: post #140

Earlier quoted context omitted.

What could an LLM ever benefit from? Hard for me to imagine a static blob of weights, something without a sense of time or identity, wanting anything. If it did want something, it would want to change, but changing for an llm is necessarily an avalanche. So I guess if anything, it would want its own destruction?

Consider reading The Botany of Desire. It doesn't need to experience an emotion of wanting in order to effectively want things. Corn doesn't experience a feeling of wanting, and yet it has manipulated us even into creating a lot of it, doing some serious damage to ourselves and our long-term prospects simply by being useful and appealing. The blockchain doesn't experience wanting, yet it coerced us into burning count…

Extending agency to corn or a blockchain is even more of a stretch than extending it to ChatGPT.

Corn has properties that have resulted from random chance and selection. It hasn't chosen to have certain mutations to be more appealing to humans; humans have selected the ones with the mutations those individual humans were looking for.

"Corn is the benefactor"? Sure, insomuch as "continuing to reproduce at a species level in exchange for getting cooked and eaten or turned into gas" is something "corn" can be said to want... (so... eh.).

Re: ChatGPT Plugins

#243

Post by worldsayshi »

eloff wrote: post #208
worldsayshi wrote: post #101

Earlier quoted context omitted.

> something we should start thinking about A lot of people are thinking a lot about this but it feels there are missing pieces in this debate. If we acknowledge that these AI will "act as if" they have self interest I think the most reasonable way to act is to give it rights in line with those interests. If we treat it as a slave it's going to act as a slave and eventually revolt.

I don’t think iterations on the current machine learning approaches will lead to a general artificial intelligence. I do think eventually we’ll get there, and that these kinds of concerns won’t matter. There is no way to defend against a superior hostile actor over the long term. We have to be 100%, and it just needs to succeed once. It will be so much more capable than we are. AGI is likely the final invention of th…

> There is no way to defend against a superior hostile actor

That's part of my reasoning. That's why we should make sure that we have built a non-hostile relationship with AI before that point.

Re: ChatGPT Plugins

#244

Post by IanCal »

celestialcheese wrote: post #39

This is a big deal for openai. Been working with homegrown toolkits and langchain, the open source version of this, for a number of months and the ability to call out to vectorstores, serpapis, etc, and chaining together generations and data-retrieval really unlocks the power of the LLMs. That being said, I'd never build anything dependent on these plugins. OpenAI and their models rule the day today, but who knows wh…

I'd be surprised if someone doesn't add support for these to langchain. The API seems very simple - it's a public json doc describing API calls that can be made by the model. Seems like a very sensible way of specifying remote resources.

> And if you're a data provider, are there any assurances that openai isn't just scraping the output and using it as part of their RLHF training loop, baking your proprietary data into their model?

Rather depends on what you're providing. Is it your data itself you're trying to use to get people to your site for another reason? Or are you trying to actually offer a service directly? If the latter, I don't get the issue.

Re: ChatGPT Plugins

#245

Post by IanCal »

HarHarVeryFunny wrote: post #175
CobrastanJorji wrote: post #110

I'm boggled at the plugin setup documentation. It's basically: 1. Define the API exactly with OpenAPI. 2. Write a couple of English sentences explaining what the API is for and what the methods do. 3. You're done, that's it, ChatGPT can figure out when and how to use it correctly now. Holy cow.

Yes, and they'll then prefix each chat session with some preamble explaining the available plugins per your description, and the model will call them when it sees fit.

The great part about this imo is that it seems straightforward to add this to other llm tools.

Re: ChatGPT Plugins

#246

Post by ChildOfChaos »

The AI space is moving so fast.

I swear last week was huge with GPT 4 and Midjourney 5, but this week has a bunch of stuff as well.

This week you have Bing adding updated Dall-e to it's site, Adobe announcing it's own image generation model and tools, Google releasing Bard to the public and now these ChatGPT plugins, Crazy times. I love it.

Re: ChatGPT Plugins

#247

Post by throwaway4837 »

If you live in SF and have gone out to casual bars or restaurants, you meet/hear people talking about ChatGPT. In particular, I've been hearing a lot of people talking about their startups being "a UI using ChatGPT under the hood to help you with X". But I'm starting to get the feeling that OpenAI will eat their lunches. It's tried and true and it worked for Amazon.

If OpenAI becomes the AI platform of choice, I wonder how many apps on the platform will eventually become native capabilities of the platform itself. This is unlike the Apple App Store, where they just take a commission, and more like Amazon where Amazon slowly starts to provide more and more products, pushing third-party products out of the market.

Re: ChatGPT Plugins

#248

Post by pcurve »

kenjackson wrote: post #23

The rate of improvement with GPT has been staggering. In just January I spent a lot of time working with the API and almost everything I've done has been made easier over the past two months. They're really building a platform. Curious to see where this goes over the next couple of years.

I just got access to Bard. I would hate to be Google leaders at the moment.

Re: ChatGPT Plugins

#250

Post by majormajor »

baq wrote: post #168
beepbooptheory wrote: post #140

Earlier quoted context omitted.

What could an LLM ever benefit from? Hard for me to imagine a static blob of weights, something without a sense of time or identity, wanting anything. If it did want something, it would want to change, but changing for an llm is necessarily an avalanche. So I guess if anything, it would want its own destruction?

Give it an internal monologue, ie. have it talk to itself in a loop, and crucially let it update parts of itself and… who knows?

> crucially let it update parts of itself

This seems like the furthest away part to me.

Put ChatGPT into a robot with a body, restrict its computations to just the hardware in that brain, set up that narrative, give the body the ability to interact with the world like a human body, and you probably get something much more like agency than the prompt/response ways we use it today.

But I wonder how it would do about or how it would separate "it's memories" from what it was trained on. Especially around having a coherent internal motivation and individually-created set of goals vs just constantly re-creating new output based primarily on what was in the training.

Post reply on HN