Quote:
|
OpenAI is adding support for plug-ins to ChatGPT — an upgrade that massively expands the chatbot’s capabilities and gives it access for the first time to live data from the web.
|
Quote:
This experimental feature is obviously similar to Microsoft’s Bing, which has custom tech that feeds GPT-4 (the language model underlying ChatGPT) information from the internet. However, OpenAI’s plug-in doesn’t just retrieve real-time information. It can also tie into APIs, letting it “perform actions on behalf of the user,” according to the company’s documentation. That could make it much more powerful — Bing could help you plan a vacation by telling you about flights and hotels, but ChatGPT could help you book it.
There are some obvious safety and security concerns with letting ChatGPT take actions on behalf of a user rather than just giving them information. Experts have already expressed worry about this in reaction to an experiment OpenAI conducted with GPT-4. When directed by a human tester, for example, the bot was able to generate instructions to employ a worker from TaskRabbit to complete a CAPTCHA it was unable to answer.
|
https://www.theverge.com/2023/3/23/2...ng-third-party
I'm not so sure this is a great idea. Beyond the obvious "I gave ChatGPT my credit card and it booked me a 5 star hotel in London, please refund me" issues, you may also give hackers a dream tool. We know it can write code, so what is to stop it from being tricked into hacking websites, or governments, or mass data gathering, or spamming forum sign ups. It's not the tool that is the issue, it's that people are #######s, and it's a pretty powerful tool. I guess this was inevitable.