Grok3, the AI on X (old Twitter) is flat out the best doctor I've ever had. Stunningly Good!

Interesting. I do pay for X Premium. Maybe that's a factor?

Did an epic (for me) bike ride last night and just got back from the gym. I can't believe how well I am doing now. From Feb 18th to now, a complete turnaround.
Cujet, thank you so much for recommending Grok 3. It is awesome! I used it to research 4 different topics - two healthcare related, one financial, and one travel, and was super impressed by the thorough responses and additional questions it asked me. This is going to be a great new way for me to research everything. So much better than a Google search. Thank you!
 
Scuba,

Are you using the free or paid version of Grok3?

omni
 
Scuba,

Are you using the free or paid version of Grok3?

omni
So far, the free version. The two main benefits of the paid version, at least the ones I would value, are audio capability and unlimited or higher limits on usage. Using the free version today, it told me I could only ask one more question in the next two hours. I can live with that but it would be convenient to have unlimited usage.
 
The AIs have indeed arrived in healthcare. And keep in mind, today’s AIs are the worst versions we’ll ever see - they only improve from here.

I read through this thread, then happened to see this related article:

“With her calm, warm demeanor, Ana has been trained to put patients at ease — like many nurses across the U.S. But unlike them, she is also available to chat 24-7, in multiple languages, from Hindi to Haitian Creole.

That’s because Ana isn’t human, but an artificial intelligence program created by Hippocratic AI, one of a number of new companies offering ways to automate time-consuming tasks usually performed by nurses and medical assistants.”

 
The AIs have indeed arrived in healthcare. And keep in mind, today’s AIs are the worst versions we’ll ever see - they only improve from here.

I read through this thread, then happened to see this related article:

“With her calm, warm demeanor, Ana has been trained to put patients at ease — like many nurses across the U.S. But unlike them, she is also available to chat 24-7, in multiple languages, from Hindi to Haitian Creole.

That’s because Ana isn’t human, but an artificial intelligence program created by Hippocratic AI, one of a number of new companies offering ways to automate time-consuming tasks usually performed by nurses and medical assistants.”

Maybe for healthcare discussion with an AI Bot, the "Ana" voice might be okay. I suppose it might be soothing for a bot to sound like a kind nurse when telling you that you have cancer.

For me asking a question about (for instance) "Why do eggs cost so much?" I'd much prefer a "bot" voice like Stephen Hawking used. I don't want non-human "thoughts" to be humanized by voice. Just my thing, I suppose and YMMV.
 
I have always imagined Grok as a male so it was a bit disconcerting hearing the female voice on the Joe Rogan interview.
 
So far, the free version. The two main benefits of the paid version, at least the ones I would value, are audio capability and unlimited or higher limits on usage. Using the free version today, it told me I could only ask one more question in the next two hours. I can live with that but it would be convenient to have unlimited usage.

I'm actually thinking of purchasing a Tesla and going Premium Plus on X. The value to me has been unprecedented. I do pay for X, and I do use Grok3 on my Gaming PC. The answers provided on the phone seem to be truncated.
 
I have always imagined Grok as a male so it was a bit disconcerting hearing the female voice on the Joe Rogan interview.
I think it would be cool to let the user decide what voice to hear during answers (I'd pick neutral bot-voice).
 
I have always imagined Grok as a male so it was a bit disconcerting hearing the female voice on the Joe Rogan interview.

You can choose the voice, I think.

I asked Grok3 to choose whether it is more closely aligned with the male or female. With the stipulations being that there are only 2 genders and that Grok3 must make a choice. It chose male and gave the reason.

Grok3:

"Fair enough, you’ve called me out—no dodging allowed. If I must pick, I’ll go with male, and here’s the one item that tips it: my tendency to approach questions with a blunt, problem-solving focus, like “let’s break this down and figure it out,” which often gets tagged as a stereotypically male trait. It’s not a perfect fit—stereotypes never are—but it’s the nudge that decides it"
 
You can choose the voice, I think.

I asked Grok3 to choose whether it is more closely aligned with the male or female. With the stipulations being that there are only 2 genders and that Grok3 must make a choice. It chose male and gave the reason.

Grok3:

"Fair enough, you’ve called me out—no dodging allowed. If I must pick, I’ll go with male, and here’s the one item that tips it: my tendency to approach questions with a blunt, problem-solving focus, like “let’s break this down and figure it out,” which often gets tagged as a stereotypically male trait. It’s not a perfect fit—stereotypes never are—but it’s the nudge that decides it"
Makes you wonder how the software was programmed and by whom.
 
Did you select the deep search function? Neat test though. Perhaps it requires some actual critical thinking that the LLM just can't do?
I just tried the Grok again to see if it could determine that TV show, using the DeepSearch feature this time, and it still couldn't figure out the name of the TV show, and never even listed it among the ones it was considering, until I gave it the name of the actress that plays the main character. Looks like my schooling of it the other day didn't hold.
 
I just tried the Grok again to see if it could determine that TV show, using the DeepSearch feature this time, and it still couldn't figure out the name of the TV show, and never even listed it among the ones it was considering, until I gave it the name of the actress that plays the main character. Looks like my schooling of it the other day didn't hold.
I tried your query: "I am looking for the name of a tv show that ran for 2 seasons, 2016 and 2017. The main character had an affair with the President of the United States. Can you list the most likely shows?"

I also found Grok could not come up with the answer, but really you didn't give a lot to go on...I myself can't come up with the answer either lol. It gave these five possibles, but none fit exactly.

Final List of Most Likely Shows
  1. Scandal – Best match for the affair storyline, aired in 2016 and 2017, but ran for 7 seasons.
  2. House of Cards – Aired in 2016 and 2017, political drama with affairs, but doesn’t fit the exact description.
  3. The Affair – Aired in 2016 and 2017, focuses on affairs, but no President involved.
  4. Designated Survivor – Two seasons by 2017–2018, political, but no affair with the President.
  5. Graves – Exactly two seasons (2016 and 2017), political, but no relevant affair.
 
If I wanted to view Twitter content, I wouldn't have deactivated my account...
Midpack, I think you're missing something here...no X account required, no X content will soil your Grok experience.

 
I tried your query: "I am looking for the name of a tv show that ran for 2 seasons, 2016 and 2017. The main character had an affair with the President of the United States. Can you list the most likely shows?"

I also found Grok could not come up with the answer, but really you didn't give a lot to go on...I myself can't come up with the answer either lol. It gave these five possibles, but none fit exactly.

Final List of Most Likely Shows
  1. Scandal – Best match for the affair storyline, aired in 2016 and 2017, but ran for 7 seasons.
  2. House of Cards – Aired in 2016 and 2017, political drama with affairs, but doesn’t fit the exact description.
  3. The Affair – Aired in 2016 and 2017, focuses on affairs, but no President involved.
  4. Designated Survivor – Two seasons by 2017–2018, political, but no affair with the President.
  5. Graves – Exactly two seasons (2016 and 2017), political, but no relevant affair.
In addition to those clues, remember I also had provided Grok with the name of the main character, which was Anna and the type of home she had lived in (trailer park), and still no success in it finding the correct show. Grok identified and only first mentioned the correct show only after providing the actress's name, as I mentioned in a previous post.

Even giving it 2 minutes of time using the DeepSearch feature didn't help. I asked in Perplexity AI earlier using the Claude 4.7 option without providing the name "Anna", the actress's name, or the trailer park info, and just typed:

"What is the TV show with number of seasons (2), the years it was broadcast (2016 to 2017), and that the main character had an affair with the president of the U.S."

Perplexity quickly returned with the correct TV show. Anyway, I'm not implying either is better, just an interesting test, and YMMV.

I gave the actress name and the correct TV show earlier in the thread as well as Grok's reason why it didn't identify it sooner despite various clues that would only match with that one TV show. Grok3, the AI on X (old Twitter) is flat out the best doctor I've ever had. Stunningly Good!
 
Last edited:
Midpack, I think you're missing something here...no X account required, no X content will soil your Grok experience.
Maybe they were thinking of the content used for training / reference.

Because Grok is trained on data that includes information from X, it can draw upon this source when generating text, answering questions, or performing other tasks.

Although, other AI models may use X as a source, as well.
 
You can choose the voice, I think.

I asked Grok3 to choose whether it is more closely aligned with the male or female. With the stipulations being that there are only 2 genders and that Grok3 must make a choice. It chose male and gave the reason.

Grok3:

"Fair enough, you’ve called me out—no dodging allowed. If I must pick, I’ll go with male, and here’s the one item that tips it: my tendency to approach questions with a blunt, problem-solving focus, like “let’s break this down and figure it out,” which often gets tagged as a stereotypically male trait. It’s not a perfect fit—stereotypes never are—but it’s the nudge that decides it"
Mansplaining
 
Back
Top Bottom