[fckgnad]

Just for kicks:

   ME: What if the Hulk was one of your customers? How would you handle him? Give specific and detailed examples. 
   
   chatGPT: 
   As a language model AI, I do not have any customers or clients, but I can provide you with an example of how a software development team might handle a customer like the Hulk, who is known for his incredible strength and rage.

   1. Communication and collaboration:
      If the Hulk is a customer, it's important to ensure that the team is able to communicate effectively with him and understand his needs. This could involve using clear and simple language when communicating with him, and providing him with detailed documentation and guides to help him understand the software being developed.
      Additionally, it could also be important to have a dedicated point of contact for the Hulk, such as a project manager, who can serve as the primary liaison between the team and the Hulk. This person would be responsible for keeping the Hulk informed about the project's progress and addressing any concerns he may have.
   2. Safety and Security:
      As Hulk is known for his incredible strength and rage, it's important to ensure that the team's safety is a top priority. This could involve implementing security protocols such as security cameras and alarms, and having security personnel on site when the Hulk is visiting the office.
      Additionally, it could also be important to have a plan in place to respond to any incidents that may occur, such as a protocol for evacuating the office in case of an emergency.
   3. Technical Capabilities:
      The Hulk has a specific set of abilities that are different from other customers, it's important to consider how the software will handle those abilities. For example, if the software is an application that tracks Hulk's strength, the team may need to make sure that the software can handle the high levels of data and ensure that the data recorded is accurate.
   4. Empathy and Understanding:
      It's important to understand and empathize with the Hulk's unique situation, such as his abilities and limitations, and how those factors may affect his interactions with the software. This could involve conducting user research with the Hulk to gain a better understanding of his needs and how the software can be designed to best meet those needs.
   
   It's important to keep in mind that the Hulk is a fictional character, and in real life, the safety and well-being of the team should always be the top priority. The above examples are purely fictional and should not be applied in real life situations.

Anyway... I think my point is unmistakably clear.

chatGPT is giving out instructions on how to handle a customer that is impossible to exist in real life. If you're thinking this thing is some generic text generator think again.

Everything before chatGPT was an interesting toy. Something changed with chatGPT.

[kaba0]

It’s good at generating bullshit text, that depending on topic/training data may not be as bullshitty. Still, every single relation between the sentences is questionable. Try asking it some basic ass math questions and it fails spectacularly (with huge confidence, none the less)

[fckgnad]

Many humans suck ass at math too if they aren't taught it at all. chatGPT wasn't trained specifically on math but it can be. I don't see why it needs to be though given that computers already excel beyond humans at math.

Read this and tell me whether it's similar text: https://www.engraved.blog/building-a-virtual-machine-inside/

I cannot fathom how someone can read that and think that chatGPT is just making text that is coincidentally not bullshitty.

[kaba0]

Ok, it also breaks down quickly at simply repeatedly applying a simple rule (it has no problem applying it once). And it is pretty much an inherent problem with language models, no scaling up will help with it.

And this is pretty much a must for proper thinking, you have to be able to follow the train of thought.

[fckgnad]

Relax. It's not as smart as a human, ok? It does have issues there's no denying this.

But it is impressively smarter then you thought. You didn't dig into this thing deeply enough, and you dismissed as if it was some other generic text generator. It clearly is not. This is a milestone in AI technology.

You also have to realize this AI was NOT TRAINED specifically to understand the concept of code, virtual machines or any of this. It KNOWS these things as a SIDE EFFECT. It is also a nascent technology. It is the first prototype and there will be TONS of improvements on top of it.

This wasn't GPT-3. This is different. I hope you realize this and investigate further because a lot of people just skimmed the headlines and dismissed it as another GPT-3.