Welcome to RVForums.com

  • Register now and join the discussion
  • Friendliest RV Community on the web
  • Modern site for PC's, Phones, Tablets - no 3rd party apps required
  • Ask questions, help others, review campgrounds
  • Get the most out of the RV Lifestyle
  • Invite everyone to RVForums.com and let's have fun
  • Commercial/Vendors welcome

FYI Having fun with GROK a useful and fun tool

Welcome to RVForums.com

  • Register now and join the discussion
  • Modern secure site, no 3rd party apps required
  • Invite your friends and let's have fun
  • Commercial/Vendors welcome
  • Friendliest RV community on the web

Joe Hogan

RVF Supporter
Joined
Nov 3, 2019
Messages
3,553
Location
Florida
RV Year
2024
RV Make
Newmar
RV Model
Dutch Star 4311
RV Length
43
Chassis
Spartan
Engine
Cummins
TOW/TOAD
2018 Ford Flex
Fulltimer
No
Always a bit skeptical of new technology Grok has become a use tool in the correct context. Always verifying results but useful nonetheless.

And some fun too, Spent a short time in the image creating feature for some illustration work. Amazingly easy to create quality output.

Here I created a picture for my memory of my teenage years pictures long lost to time and various relocations.

1754830235656.png
 
I have heard of Grok but never actually used it. But it looks interesting. Do you use this on a daily basis Joe, and if so, what are the things you use it for?
 
It's s generative AI platform there's virtually no limit ( and no safeguards, btw.) for what it can do. It's different from other generative AI platforms in that it disregards copyright infringement regs. It's also the go to AI platform for spreading misinformation, disinformation and conspiracy theory, ie., I read it on X ( twitter) so it must be true. Elon Musk owns it and X is it's large language model go to source.
 
I just drove between Denver and Prescott using Grok 4 speech interactive talking to the various "companions" offered by the new Grok app. The companion "Ani" is the most entertaining. It is like talking to somebody in the passenger seat who knows everything from the current weather to a detailed description of the theory of relativity. These interactive companions reset the whole experience driving long distances.
 
I just drove between Denver and Prescott using Grok 4 speech interactive talking to the various "companions" offered by the new Grok app. The companion "Ani" is the most entertaining. It is like talking to somebody in the passenger seat who knows everything from the current weather to a detailed description of the theory of relativity. These interactive companions reset the whole experience driving long distances.
A real person in the passenger seat who knows everything. talks to me.
 
A real person in the passenger seat who knows everything. talks to me.
Suggest you have a long conversation with "Ani" and see which one makes sense for that role. Ani's creators provisioned her as a "flirtatious" 22 year old. They did an exceptional job. Very human like. The only issue in the last week is that Grok 4 interactive AI is getting really slow. I first tested "Ani" right after release it was "human like" fast with responses. Now Ani is talking to so many people it takes her a while to get back to you. Bottom line is you can see the future with interactive AI. Scary and exciting.

By the way on my trip I had in motion Starlink from a Mini. You need a very fast connection for interactive voice AI.
 
I use GROK for many informational tasks. No opinion and I read the footnotes and references. Lots to learn and need to understand source materials.
Ultimately it just regurgitates what it finds on the WWW. Grok does qualify sone responses but not all.
As with any tool, no different from a hammer, you have to understand the proper application and understand the results.
For basic illustration for quick articles it is useful. The images can be surprisingly detailed with proper ques.
My memory image has the big pieces very accurate, I’m fairly represented and the car is correct. Some fine detail is garbled but overall very respectable image from my memory.
 
I use GROK for many informational tasks. No opinion and I read the footnotes and references. Lots to learn and need to understand source materials.
Ultimately it just regurgitates what it finds on the WWW. Grok does qualify sone responses but not all.
As with any tool, no different from a hammer, you have to understand the proper application and understand the results.
For basic illustration for quick articles it is useful. The images can be surprisingly detailed with proper ques.
My memory image has the big pieces very accurate, I’m fairly represented and the car is correct. Some fine detail is garbled but overall very respectable image from my memory.
I agree. Grok has a long way to go with interactive, situational, real time services but it is really good at technical analysis of complex problems.
 
All generative AI platforms are really good at technical analysis of complex problems. Currently and only temporarily, Grok 3 is available free of charge to X acct holders. Going forward it ( Grok3) will only be available to X premium+ subscibers @ $40.00 per month. Chat GpT is $20.00 and Perplexity Pro is $20.00 per month.
 
What do those add-ons get you above the free version?
 
Every time I interact with such AI It occurs to me that "Eliza" has come a long way since the 1960's but it still Eliza.
 
What do those add-ons get you above the free version?
Fewer what are termed AI hallucinations, a euphemism for generative bull****. Think of it like taking a freshmen journalism class in college, you can take the free class taught by the AI version of Tucker Carlson or upgrade to the class taught by the AI version of Walter Cronkite, but for the Cronkite version you have to pay.
 
Fewer what are termed AI hallucinations, a euphemism for generative bull****. Think of it like taking a freshmen journalism class in college, you can take the free class taught by the AI version of Tucker Carlson or upgrade to the class taught by the AI version of Walter Cronkite, but for the Cronkite version you have to pay.
While this is an issue, I have not found it any more of an issue than the same thing from the "main stream" media. Same concern, trust but verify.
 
While this is an issue, I have not found it any more of an issue than the same thing from the "main stream" media. Same concern, trust but verify.
There ain't anybody going to consult AI and then go verify the information in an act of redundancy, ever. No different from no one is going to glue themselves to affirmation TV and then go verify the bull**** that's been blown up their a**, they just believe it because it's what they want to hear. That's how Cambridge Analytica was able to mold public opinion in the 2010's.
The basic GROK AI is simbiotically tied in with X ( Twitter). You get what you pay for and basic GROK costs $0.00.
 
There ain't anybody going to consult AI and then go verify the information in an act of redundancy, ever.

I do this all the time, ever since AI started. I will never make an important decision based only on the output of an AI query.
 
There ain't anybody going to consult AI and then go verify the information in an act of redundancy, ever.
Anytime I use AI for a real question (not just extending time wasting scrolling) I ALWAYS look at the sources to verify and the vast majority of the time I will then challenge the AI to provide a different view point to better understand what views it ignored the first time. It is very enlightening, along the lines of the “discourse” we had in the old days when we learned the opinions of others and didn’t just surround ourselves with those who agree with us.
 
Anytime I use AI for a real question (not just extending time wasting scrolling) I ALWAYS look at the sources to verify and the vast majority of the time I will then challenge the AI to provide a different view point to better understand what views it ignored the first time. It is very enlightening, along the lines of the “discourse” we had in the old days when we learned the opinions of others and didn’t just surround ourselves with those who agree with us.
Yes, I often challenge a conclusion of Grok with an actual url of a page with the opposite view. Grok will often "eat crow" and confess they missed the real answer on that page. I think this is part of training the model.
 
I've been playing with Grok today and this thing is actually pretty darn cool! Thanks Joe!
 

Latest resources

Back
Top