SoylentNews is people
SoylentNews
ChatGPT gets "eyes and ears" with plugins that can interface AI with the world:
On Thursday, OpenAI announced a plugin system for its ChatGPT AI assistant. The plugins give ChatGPT the ability to interact with the wider world through the Internet, including booking flights, ordering groceries, browsing the web, and more. Plugins are bits of code that tell ChatGPT how to use an external resource on the Internet.
Basically, if a developer wants to give ChatGPT the ability to access any network service (for example: "looking up current stock prices") or perform any task controlled by a network service (for example: "ordering pizza through the Internet"), it is now possible, provided it doesn't go against OpenAI's rules.
Conventionally, most large language models (LLM) like ChatGPT have been constrained in a bubble, so to speak, only able to interact with the world through text conversations with a user. As OpenAI writes in its introductory blog post on ChatGPT plugins, "The only thing language models can do out-of-the-box is emit text."
I see (and hear) you!
(Score: 4, Insightful) by SomeGuy on Wednesday March 29, @12:07PM (1 child)
If you give ChatCGPT a gun, can it shoot me? Because this endless stream of AI bullshit articles is beyond redicious.
One can already look up stock prices or order pizza using anything from an IBM PCJr to their internet connected dildos and a zillion other kinds of gadget or software, so how is plugging it in to the "AI" program of the day even notable?
(Score: 3, Interesting) by ElizabethGreene on Wednesday March 29, @02:06PM
ChatGPT 4 is capable of tool use and processing visual input. If someone (like me!) embodies it and gives it a gun then yes it can shoot you.
GPT-3.5 turbo and Smaller Alpaca both struggle with tool use. I can't get either of them to send commands to my ROS reliably, and they aren't quite clever enough to grasp the concept of talking to each other. I'm still working on it.