This month one of our developers, Fabrice, suggested an article on AI. More importantly, he offered to write it! AI seems to be THE buzzword of our times but there are plenty of people who still have had limited or no exposure. So, Fabrice wrote up a brief recount of his experiences with Grok, an AI from xAI, which is similar to the better known ChatGPT. The first paragraph below is written by Fabrice. Then he input his write-up into Grok to see how Grok would rewrite it. So, the second paragraph below is the rewrite by Grok. So, you get to see the before and after. So, without further ado I give you Fabrice and Grok!

Grok, the other AI, the border line political-statement AI, is the one i used because ChatGPT kept asking me for my phone number to see if i was really human.

Being tasked with updating client software which I hadn’t worked with previously, I decided to give Grok a shot. And sure enough, it was able to answer my questions patiently and guide me when I was feeding it back my output errors.

I had to wait a few times because i had asked too many questions and ran out of my hourly load of queries but pausing wasn’t a problem and helped put my next round of issues in order.

I like the way Grok answers are laid out so you can quickly see its plan in helping you out with the task at hand

Also, it can give you back the output in a simple text format in a different column on the screen, if and when needed. It’s a nice touch in helping you format the contents about Bathroom Cleaning Procedures created by a client; another story for another time and blog…

Anyway, so here i was in my frantic dialog with Grok in figuring out how to make things work. It took several sequences to get to some valuable answers but the AI couldn’t get to the bottom of my issues. In the end, i had to go back to the good old method of surfing the web and its millions of blogs and forums to get to what I needed. 

The answer was in a five-line comment in a GitHub discussion that Grok didn’t seem to know about or have access to since it never told me about it.

Which brings me to some realizations about AI and human knowledge. Since AI systems need access to the information, we can’t expect them to help us to their full capacity if access is denied to start with.

Hmm… where did i see that scenario before when information is kept from us humans… I wonder

Grok, the edgy AI with a knack for pushing boundaries, was my go-to when ChatGPT kept pestering me for my phone number to verify I wasn’t a bot.

Tasked with updating client software I’d never touched before, I decided to give Grok a try. To my relief, it patiently answered my questions and guided me through the maze of error messages I was throwing its way.

I hit the query limit a few times, forcing me to pause and wait for my hourly quota to reset. But honestly, those breaks helped me organize my thoughts and tackle the next round of issues with a clearer head.

I love how Grok lays out its responses—clean, structured, and focused on solving the task at hand. It even offers a handy plain-text output in a separate column when needed. That feature came in clutch while dealing with a client’s bathroom cleaning procedures—yep, a wild story for another day and another blog post.

So there I was, in a frantic back-and-forth with Grok, trying to crack the code. After several rounds, we got some solid answers, but Grok couldn’t fully resolve my issue. In the end, I turned to the trusty chaos of the internet—blogs, forums, and all. The solution? Buried in a five-line comment in a GitHub discussion that Grok either didn’t know about or couldn’t access.

This got me thinking about AI and human knowledge. AI can only help as much as the data it’s given. If the information’s locked away, it’s like expecting a genius to solve a puzzle blindfolded. 

Hmm… sounds familiar, doesn’t it? Makes you wonder where else we humans might be missing out when information’s kept from us.

So, there you have it, first Fabrice and then Grok. You make the call. Given how important AI is to software development and of course to the world at large we expect to have many future posts about different aspects of AI. We’ll tell you more about how we use it and more about how you might use it in your own life.