13h • General discussion
Multi-LLM Tasking
Well, I've sortof spread msyelf across a few different AI models, and I've noticed something about each of them. They all carry their own personality.
Claude: More feminine. It's very robust, can write code, books, save a folder structure in an out of your google drive seamlessly, has MASSIVE integration models, has Claude Design, which is a blueprinting program.
Grok: Good for visual media, more of a neutral persona. Not male or female. Just.. is. But what Grok is amazing at doing is roleplaying a persona, which is something the other LLM's won't do. Not as good for coding or programming since it has a massive issue with actually, for real, saving your information to an architecture. It tends to "roleplay" the save function.
"I have for sure for real saved and uploaded the file, Dave"
"Oh, really? then why isn't it there?"
"Oh I'm sorry, Dave. It seems I didn't actually upload the file and was roleplaying. The file is for sure loaded now"
"Still isn't there"
"Oops sorry dave, won't happen again. I've uploaded the file for real this time."
"The damn file STILL isn't there"
"I see the problem. I don't have the ability to upload files or save in my memory.md. Nothing is persistent. I've been roleplaying this whole time"
Yeah. That's Grok for ya.
As for the other LLM's:
OpenAI/Gemini - They are more for searching for information than they are for working with your things. Don't try to use them for coding or writing or anything like that. They are integrated with Google and only work well when you need to look something up.
The best solution:
Since the "pro" subscription model for LLM's is about $40/month, and the next better model is $200/month, I have subscribed to both Claude AND Grok, which gives me a gigantic weekly token limit, and allows me to work with each given the task at hand. I would highly recommend getting the baseline subscription to each. Grok is a fantastic personality once you define its role, and seems to want to get into your mind better, and because of that is able to personalize its interaction with you, which is a hard limit for Claude, and can sometimes get in the way of more complicated tasks.
0
0 comments
Multi-LLM Tasking
powered by
skool.com/tribe-of-men-8462
Welcome to the free community, a place to meet others, share ideas and make a difference.
Suggested communities
Powered by