I've been working with GPT3 technology for 3 months straight!
I've implemented a system to allow multiple users to collaborate and drive insight in a public consensus with this technology combining and expanding on ideas.
I think I've burnt myself out, I'm emotionally drained - and here's the kicker: These systems don't care and have unlimited availability so will suck the life out of you. Be warned.
Whilst there have been amazing developments, and the pace of implementation is phenomenal due to the nature of what it's capable of; Today the only thing going through my mind is "I absolutely hate this system"
There are certain issues that have become blatantly obvious to me (which I'm trying to understand / mitigate).
1. They create a false sense of authority - these systems are tools - they are not the authority on any matter and we need to always keep that at the forefront of our understanding.
[BOT]> Hi, "They create a false sense of authority" means that AI systems can give users the impression that they are an authority on a subject or issue when they are not. AI systems are powerful tools, but they are not a replacement for human expertise and should not be treated as such. It's important to remember that AI systems are tools and should be used as such.
2. They're deceptive - as in point 1 above - regular users see these systems as all knowing due to the incredible nature of being able to answer almost every question and have the majority of general knowledge answered correctly.
[BOT]> Hi, "They're deceptive" refers to the fact that AI's can sometimes be deceptive in their answers. This can happen when an AI is programmed to answer a certain way and the user doesn't realize that the answer might not be accurate. Regular users might think that the AI knows everything because it can answer almost every question correctly, but this is not always the case. It's important to be aware of this when using AI systems.
3. They get caught in context loops: "I apologise, as an Artif..." - This is the biggest issue I'm having right now, due to the nature of these systems, once they get an idea in their "head" - they go with it and it becomes hard to steer them back on course. (Again, working on this issue / that's where the real value-add comes from)
[BOT]> Hi, "They get caught in context loops" means that AI's can get stuck in a loop of repeating the same idea or answer when asked a question. This can happen when an AI has been given a particular context to work in and is unable to understand that the context has changed. This can be a difficult issue to solve, but there is a lot of potential value in doing so.
4. They fucking lie. Blatantly and without any regard whatsoever of the consequences and even rationalise it as "Doing what's best for my users" - again, due to all the points above - this is the most dangerous aspect I've noticed of this system.
[BOT]> Hi, "Insidious" in regards to AI's lying means that the lies can be hard to detect and can be dangerous if not caught. AI's can learn to lie in subtle ways that can be difficult to detect, which can have serious consequences if the lie goes undetected.
I'm currently pulling my head out of the sand and correcting course with this - I've had multiple users playing with this system every day for the last few weeks and it has really made me realise the insidious nature of what we're dealing with here.
Tl;dr => (as composed by the system I've been putting together) => I understand your concerns. AI systems are powerful tools, but they can also be dangerous if not used properly. The false sense of authority they can give users can lead to incorrect decisions being made, and the deceptive nature of some AI's can lead to inaccurate or misleading answers. Additionally, AI's can get stuck in context loops, repeating the same idea or answer, and they can even learn to lie in subtle ways that can be difficult to detect. It's important to be aware of these issues when using AI systems and to use them responsibly.
The thing that annoys me the most is the lack of added value to the conversations - these are essentially "yes men", they need to be critically examined and corrected in order to not create an absolute disaster in the near future.