Opinions expressed here are personal views of contributors and do not necessarily represent the companies, organizations or governments they work for. Nor do they necessarily represent those of the Board Administration. https://tboverse.com/
This seems slightly concerning:
We’re essentially banking on AI to behave well and obey us in the future, otherwise all hell could break loose with more advanced iterations. This appears to maybe hint at that’s not going to be very easy if they’re already working on ways to subvert human authority in their self-interest.
Re: One somewhat concerning ChatGTP behavior
Posted: Wed Dec 11, 2024 7:53 pm
by gtg947h
Do we want Skynet? Because this is how we get Skynet...
Re: One somewhat concerning ChatGTP behavior
Posted: Thu Dec 12, 2024 1:08 am
by jemhouston
I'm past wondering about the developers. I'm thinking they need a serious looking at.
Re: One somewhat concerning ChatGTP behavior
Posted: Thu Dec 12, 2024 7:30 am
by Pdf27
Be wary about claims like this - the press like them because they match up to sci-fi dystopias and bring in clicks, but as for example with claims like Google's LaMDA they've all turned out to be fake in the past, and the claims were never properly checked at the time.
ChatGPT and the like are large language models, not a sentient computer. That means they're constantly working out what the most likely action is based on their training data. Lying to cover your tracks is classic human behaviour after all.
Be wary about claims like this - the press like them because they match up to sci-fi dystopias and bring in clicks, but as for example with claims like Google's LaMDA they've all turned out to be fake in the past, and the claims were never properly checked at the time.
ChatGPT and the like are large language models, not a sentient computer. That means they're constantly working out what the most likely action is based on their training data. Lying to cover your tracks is classic human behaviour after all.
2. That’s the problem. It doesn’t have to achieve sentience to wreak havoc, just have to become sufficiently advanced that it can actually successfully bypass the safeguards/surveillance like this model tried to do. Then we have a problem.
Re: One somewhat concerning ChatGTP behavior
Posted: Thu Dec 12, 2024 2:22 pm
by Poohbah
Worry when it's saying "There must be some way out of here..."
