It is an issue with the tech, and it's probably not an easy one to fix. Performance depends a lot on how its used, but even when performance is poor the output is often convincing.
The first few times I tried chat gpt I tried asking it goofy questions to try to break it. Then I asked it questions across various fields I have information on. It answered each question incorrectly in a way that bothered me. The. I tried asking it about a field I didn't know about, and googled for the answer. Wrong again. I literally never had it give me an answer that mattered.
I have a colleague who is gungho chat bot coding. The guy is smart, but ever since he started using it, he's adopted some weird ideas about what code should look like which are based on easily googleable chatgpt lies and he refuses to hear anyone else out. It's kinda sad how confidently wrong chatbots can infect people and stunt their growth...
Exactly my point. If the system gives you results that are worse than not using it, and the solution is to bolt on more stuff to the system, maybe it's time to take a step back and think long and hard if having it in production is a good idea.
