I’d argue that it’s very important, especially since more and more people are using it. Wikipedia is generally correct and people, myself included, edit incorrect things. ChatGPT is a black box and there’s no user feedback. It’s also stupid to waste resources to run an inefficient LLM that a regular search and a few minutes of time, along with like a bite of an apple worth of energy, could easily handle. After all that, you’re going to need to check all those sources chatGPT used anyways, so how much time is it really saving you? At least with Wikipedia I know other people have looked at the same things I’m looking at, and a small percentage of those people will actually correct errors.

Many people aren’t using it as a valid research aid like you point out, they’re just pasting directly out of it onto the internet. This is the use case I dislike the most.

I don’t use ChatGPT, I use LM Studio which runs Local LLMs (it’s like AI you can run locally on your PC, I have solar and a solar battery so this means there’s no co2 emissions from my queries, I primarily use this for coding questions and practice, translations from Russian/Ukrainian/French, practising french, etc), then I use mistral AI second (french based), then third perplexity (american)

I also use Ecosia.org for searches as well

I asked mistralai/mistral-small-3.2 to elaborate on what you said, Is this what you meant?

The phrase “Let’s just keep adding more and more layers like a game of telephone!” is a metaphorical way of expressing skepticism or concern about the accuracy and reliability of information as it gets passed through multiple layers of interpretation, especially when involving AI systems.

Here’s what it likely means in this context:

1. Game of Telephone Analogy: In the classic “game of telephone” (or “Chinese whispers”), a message is whispered from one person to another in a line, and by the time it reaches the end, the original message is often distorted or completely changed due to mishearing, misinterpretation, or intentional alteration. The user is suggesting that relying on AI systems to search, summarize, or interpret web content might introduce similar layers of potential inaccuracies or biases.

2. Layers of Interpretation: The “layers” could refer to the steps involved in using an AI system to access and summarize information:

   • The original web content (first layer).
   • The AI’s interpretation or summarization of that content (second layer).
   • Any further human interpretation or sharing of the AI’s output (additional layers).

3. Concerns About Accuracy: The user might be implying that each additional “layer” (especially when involving AI) could introduce errors, biases, or misinterpretations, much like how a message gets distorted in the game of telephone.

4. Hostility Toward AI: Given the context you provided (Lemmy users being “strongly anti-AI”), this comment likely reflects a broader distrust of AI’s ability to accurately and reliably convey information without introducing new problems.

In essence, the user is cautioning against blindly trusting AI systems to handle information retrieval and summarization, suggesting that doing so could lead to a breakdown in accuracy or meaning, similar to how a message degrades in a game of telephone.