This is exactly the scenario I encountered. I have a teammate who is using ChatGPT to ask questions as opposed to searching documentation and it gave incorrect info all around on all the following:
1. Where the property would be found in the event schema 2. What structure the value would be 3. The fact that it's not included at all for AWS AppSync specifically in question, even if the previous two had been answered correctly regarding API Gateway event schema.
All of this was available in the first doc returned in the search results of both API Gateway and AppSync respectively.
The fact it convincingly tells you otherwise causes additional friction since they're pointing at their screen telling me I'm wrong cause look at the response from ChatGPT.
Basically, if Google owned ChatGPT the result would be very different.
If I search for python for loop syntax or metallica bob seger cover or tuck rule game year, etc. I know the right answer if you show it to me and given enough time to think I probably could recall it but I don't have the information at the top of my mind.
If chatgpt returns something that's wrong I'll know it's wrong and then maybe go check google.
It's waaaaay faster to get an immediate answer -- and be able to ask pointed, follow-up questions, which you couldn't otherwise do with a traditional site. And it's a lot easier to just fact-check statements online than to wade headfirst into something you know nothing about in random sites of varying qualities.
For many cases you can get enough information out of chatGPT to retrieve a specific corroborating reference. For coding tasks, you can just try the code, ask it for tests, or give it code review like feedback.
I’d suggest asking it about deep technical topics that you are familiar with, then work out it’s limitations. It’s effectively equivalent to a universal teaching assistant, sometimes wrong - usually points in the right direction.
Providing a list of 30,000 pages that are only tangentially related to what you want is not a virtue. -----
> Give me a link to page that gives an introduction to quantum computing.
Here is a link to a page that provides an introduction to quantum computing:
https://www.ibm.com/quantum-computing/learn/what-is-quantum-...
This page gives a brief overview of what quantum computing is, how it works, and some of the potential applications. It also includes links to more in-depth resources for those who want to learn more.
I hope this helps! Let me know if you have any other questions.
> Give me another link.
Here is another link that provides an introduction to quantum computing:
https://www.dwavesys.com/tutorials/getting-started-with-quan...
This page gives a high-level overview of quantum computing, including the basics of quantum mechanics and how it is used in computing. It also discusses the potential applications of quantum computing and some of the challenges and limitations of the technology.
I hope this helps! Let me know if you have any other questions.
...
I could tweak and run them to my liking.
I think for knowledge based things, you are better off using Google. But if it can help you narrow down your search, you can use that for Google.
For example, I queried, what projects are good for practicing data-intensive design.
It gave me a list of projects with descriptions. Perfect for me to Google more information for.
It's very good for narrowing down search and addressing follow ups. It's like the perfect Google Search companion.
Offers a chat feature that pairs the gpt-3 response with search results
This augments ChatGPT results with Bing results to provide references you can look up.