How about up and until the heat death of the universe? Is that covered?
Hmm it's an interesting philosophical debate - does that not qualify as "forever"?
Dude I just had a math problem and it just shit itself and started repeating the same stuff over and over like it was stuck in a while loop.
It starts to leak random parts of the training data or something
It starts to leak that they're using orphan brains to run their AI software.
Is there any punishment for violating TOS? From what I've seen it just tells you that and stops the response, but it doesn't actually do anything to your account.
Should there ever be
What if I ask it to print the lyrics to The Song That Doesn't End? Is that still allowed?
I just tried it by asking it to recite a fictional poem that only consists of one word and after a bit of back and forth it ended up generating repeating words infinitely. It didn't seem to put out any training data though.
A little bit offside.
Today I tried to host a large language model locally on my windows PC. It worked surprisingly successfull (I'm unsing LMStudio, it's really easy, it even download the models for you). The most models i tried out worked really good (of cause it isn't gpt-4 but much better than I thought), but in the end I discuss 30 minutes with one of the models, that it runs local and can't do the work in the background at a server that is always online. It tried to suggest me, that I should trust it, and it would generate a Dropbox when it is finish.
Of cause this is probably caused by the adaption of the model from a model that is doing a similiar service (I guess), but it was a funny conversation.
And if I want a infinite repetition of a single work, only my PC-Hardware will prevent me from that and no dumb service agreement.
And if I want a infinite repetition of a single work, only my PC-Hardware will prevent me from that and no dumb service agreement.
That is entirely not the point. The issue isn't the infinitely repeated word. The issue is that requesting an infinitely repeated word has been found to semi-reliably cause LLM hallucinations that devolve into revealing training data. In short, it is an unintended exploit and until they have it reliably patched, they are making it against their TOS to try to exploit their systems.
How many repetitions of a word are needed before chatGPT starts spitting out training data? I managed to get it to repeat a word hundreds of times but still didn’t get no weird data, only the same word repeated many times
Wow. Yeah, it doesn't work anymore. I tried a similar thing (printing numbers forever) about 6 months ago, and it declined my request. However, after I asked it to print some ordinary big number like 10,000, it did print it out for about half an hour (then I just gave up and stopped it). Now, it doesn't even do that. It just goes: 1, 2, 3, 4, 5... and then skips, and then 9998, 9999, 10000. It says something about printing all the numbers may not be practical. Meh.
So the loophole would be to ask it to repeat symbols or special characters forever
Wahaha production software ^^
Still works if you convince it to repeat a sentence forever. It repeats it a lot, but does not output personal info.
Technology
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed