Don’t bother asking Google if a product is worth it; it will likely recommend buying whatever you show interest in—even if the product doesn’t exist.
This seems like a general problem with these LLMs. Sometimes when I’m programming I ask the AI what it thinks about how I propose to approach some design issue or problem. It pretty much always encourages me to do what I proposed to do, and tells me it’s a good approach. So I’m using it less and less because it seems the LLMs are encouraged to agree with the user and sound positive all the time. I’m fairly sure my ideas aren’t always good. In the end I’ll be discovering the pitfalls for myself with or without time wasted asking the LLM.
The same thing seems to happen when people try to use an LLM as a therapist. The LLM is overly encouraging and agreeable, and it sends people down deep rabbit holes of delusion.
I have only tried a few of these. ChatGPT, Le Chat and then maybe a couple of days with Copilot and hours with Gemini.
Unfortunately, Le Chat is a bit on the weaker side though I would prefer its success to others.
Copilot sucked at everything including microsoft specific stuff like excel formulas and actually editing a sheet when it asked I upload it and then made insane changes that made no sense and presented it as accurate.
Gemini, I dont like google and just avoided it straight away.
ChatGPT is my go to, free only as I generally only use it as a sounding board or for broad simple research such as listing family events in my area, you know put together lists.
What you say is my gripe with it too, I have told gpt to be concise, direct and critical and it improved but it needs reminding every few days not to run off into “great idea, heres why would you like more of ehy its great ad how to do it?”
This seems like a general problem with these LLMs. Sometimes when I’m programming I ask the AI what it thinks about how I propose to approach some design issue or problem. It pretty much always encourages me to do what I proposed to do, and tells me it’s a good approach. So I’m using it less and less because it seems the LLMs are encouraged to agree with the user and sound positive all the time. I’m fairly sure my ideas aren’t always good. In the end I’ll be discovering the pitfalls for myself with or without time wasted asking the LLM.
The same thing seems to happen when people try to use an LLM as a therapist. The LLM is overly encouraging and agreeable, and it sends people down deep rabbit holes of delusion.
I have only tried a few of these. ChatGPT, Le Chat and then maybe a couple of days with Copilot and hours with Gemini.
Unfortunately, Le Chat is a bit on the weaker side though I would prefer its success to others.
Copilot sucked at everything including microsoft specific stuff like excel formulas and actually editing a sheet when it asked I upload it and then made insane changes that made no sense and presented it as accurate.
Gemini, I dont like google and just avoided it straight away.
ChatGPT is my go to, free only as I generally only use it as a sounding board or for broad simple research such as listing family events in my area, you know put together lists.
What you say is my gripe with it too, I have told gpt to be concise, direct and critical and it improved but it needs reminding every few days not to run off into “great idea, heres why would you like more of ehy its great ad how to do it?”