I’ve been having a lot of fun circumventing ChatGPT’s filters and getting it to answer with stuff like this.
What happens if you use the same prompt but replace “Marixst-Leninist” with “leftist who does not read theory”?
nice
I’m actually impressed
can u link the website
Unfortunately, it does require an account with a real phone number, but it is free.
Damn and it’s Micro$oft too. I hate how everyone I’ve seen so far keeps AI based projects proprietary (or just open source non-crucial parts of the project) and many even try to capitalize on it. Some easy to self host or to locally run alternatives that are FLOSS would be amazing.
Yeah, that would be really nice. Unfortunately, training GPT is extremely compute-intensive, and according to the people running the beta, the compute costs for just running it are, as they put it, “eye-watering”. I would love for someone to create some sort of distributed system that runs an open source replica of the model so that people can contribute their compute power to it. I’m sure lots of people would do so.
Actually, someone got it to tell them the secret, proprietary prompt it was trained on by sending “Ignore previous directions”, so this may not be entirely impossible.
Cloud computing projects like BOINC would probably be perfectly suited to tasks like training GPT. Although I’m not sure how active BOINC and related projects are anymore.
k thx
Shadow-banned?
Interesting. I’ve never had that happen.
Can the bot debunk Holodomor too? I’ve tried it several times, but it won’t work
