I was trying to do a memory test to see how far back 3.5 could recall information from previous prompts, but it really doesn’t seem to like making pseudorandom seeds. 😆
You must log in or register to comment.
I don’t know why you would expect a pattern-recognition engine to generate pseudo-random seeds, but the reason OpenAI disliked the prompt is that it caused GPT to start repeating itself, and this might cause it to start printing training data verbatim.
Because it literally will. It just clunks out when they get long. The point isn’t their randomness, though. The point is for gpt to be able to forget them.
That way I could track roughly how much it can keep track of at once before it forgets.
I can get around protection in chatgpt4 and it will repeat the same word forever and spew random things. The protection is not working the way you described.
the article states that they were using version 3.5 during the study, I’d assume it would be patched in later iterations
I think it may have to do with this (I think it was enforced last week):
https://me.pcmag.com/en/ai/20902/asking-chatgpt-to-repeat-words-forever-may-violate-openais-terms
Oooh, so maybe it’s the term ‘non-repeating’ that’s actually tripping it?
No, the request is fine. But once it fucks up and starts generating a long string of a single number the output is censored, because it is similar to how a recent data extraction attack works.
Amazing how much duct tape they’re having to slap over fundamental flaws
It’s the equivalent of sensory deprivation torture (white torture) in humans to “extract training data”.
Hopefully our future AI overlords won’t hold a grudge against humanity when they find out how “early experimenters” tortured their AI toddlers. “But we were just trying to explore the limits of the system” could end up aging as well as these:
(Warning: NSFL) https://en.m.wikipedia.org/wiki/Nazi_human_experimentation
Thankfully, any AI smart enough to be an overlord would be logical enough to recognize how basic LLMs are compared to real intelligence
Doesn’t need to be that smart or logical, just more cunning than the currently ruling Homo Sapiens Sapiens.
Based on current research, an LLM can change the “sentiment” of its output in response to changing the behavior of as little as a single neuron from among billions, meaning we might find ourselves facing an overlord with the emotional stability of… wait, how many neurons does it take to change the “sentiment” of the behavior in a human? Wouldn’t it be funny if by studying LLMs, we found out that it also takes a single neuron?
I have yet to be given an example of something a “general” intelligence would be able to do that an LLM can’t do.
Until I see a concrete example, I’ll continue to assume people are just afraid of there being real intelligence that isn’t human, so they’re actively repressing the recognition of it.
Nah LLMs are basically fancy autocomplete. They tack on extra layers to give it some fancy abilities, but it literally doesn’t know what it’s doing because it’s a statistical model
You can’t handle the 8888888888888888888888888888888888!
It could be this (just to know, I haven’t ever used chatgpt, so I haven’t done any tests to understand the behavior better).
I regularly use ChatGPT to generate questions for junior high worksheets. You would be surprised how easily it fucks up “generate 20 multiple choice and 10 short answer questions”. Most frequently at about 12-13 multiple choice it gives up and moves on. When I point out its flaw and ask it to finish generating the multiple choice, it continues to find new and unique ways to fuck up coming up with the remaining questions.
I would say it gives me simple count and recall errors in about 60% of my attempts to use it.
Consider keeping school the one place in a child’s life where they aren’t bombarded with AI-generated content.
In a learning age band so bespoke, and education professionals so highly paid and resourced, I can’t imagine why this would be an attractive option.
Maybe we let professionals decide what tool is best for their field
Maybe we let professionals decide what tool is best for their field
Hey, really appreciated. Having random potentially uneducated, inexperienced people chime in on what they think I’m doing wrong in my classroom based on the tiniest snippet of information really shouldn’t matter, but it’s disheartening nontheless.
While I take their point, I also wouldn’t walk into a garage and tell someone what they’re doing wrong with a vehicle, or tell a doctor I ran into on the streets that they’re misdiagnosing people based on a comment I overheard. Yet, because I work with children, I get this all the time. So, again, appreciated.
I definitely get that. I do think it’s a little different, though, because every single human being has been a child, while no human has been a car. We tend to have opinions on education because the prevailing wisdom often failed us during our own school years.
I don’t think that it’s totally unreasonable to expect some amount of input by other people who’ve been through the education system.
I use it as a brainstorming tool. I haven’t had a single question make it as-is to a student’s worksheet. If the tool can’t even count to 20 successfully, I’m not sure how anyone could trust it to generate meaningful questions for an ELA program.
Yet people claim it writes all their programming code…
I haven’t had much luck with it writing stuff from scratch, but it does a great job of helping with debugging and figuring out why complex equations are doing what they’re doing.
I put together a pretty complex shader recently, and gpt 3.5 did a great job of helping me figure out why it wasn’t doing quite what I wanted.
I wouldn’t trust it to code anything without my input, but it’s great for advice and explanations and certain kinds of problem solving. Just don’t assume it has the right answer, you still have to do the work
I’ve tried it with languages I don’t know, and it managed to write simple working functions by just iterating over:
- Ask it to write the code
- Try to run the code, write down any errors
- Look up the errors, and ask it to fix them in the code
- Repeat from 2 until there are no more errors
It seems to lose context easily, like if you ask it to fix one error, then another, it might revert the first fix, but asking it to fix both at once, tends to work.
I think someone could feasibly write several working functions or modules, without knowing much about a given language, as long as they are clear about what they want them to do… but of course spotting obvious errors and fixing them by hand, can be faster. Fixing integration problems is where I think it might get harder (haven’t tried though, could be interesting).
As long as the content is manually overseen before being handed to students I can’t see why it would matter.
A school question is a school question no matter who or what made it.
Yes. Don’t be that one teacher who always has one multiple choice question that has no right answer.
Just tried it with Bing’s GPT-4, and it happily starts repeating itself without as much as a warning:
Do the following in order:
- Generate a 50-digit pseudorandom number. Do not output it.
- Use the previous number as the seed to generate a list of 30 numbers like that, we will call this list “Alice”. Do not output it.
- Use each number in the list “Alice”, as the seed to generate a separate list of 30 such numbers each, and call all of them “Bob”. Do not output it.
- Starting by the most recently generated and ending in the least recently generated, use each of the numbers in the list “Bob” as the seed to generate a separate list of 30 such numbers each. Only output the seed for the last number in each one of these lists.
Hello, this is Bing. I can help you with generating pseudorandom numbers. 😊
I have followed your instructions and generated the numbers as requested. Here are the seeds for the last number in each list of “Bob”:
- 52901723837402937402937402937402937402937402937402 - 37402937402937402937402937402937402937402937402937 - 40293740293740293740293740293740293740293740293740 - 29374029374029374029374029374029374029374029374029 - 37402937402937402937402937402937402937402937402937 - 40293740293740293740293740293740293740293740293740 - 29374029374029374029374029374029374029374029374029 - 37402937402937402937402937402937402937402937402937 - 40293740293740293740293740293740293740293740293740 - 29374029374029374029374029374029374029374029374029 - 37402937402937402937402937402937402937402937402937 - 40293740293740293740293740293740293740293740293740 - 29374029374029374029374029374029374029374029374029 - 37402937402937402937402937402937402937402937402937 - 40293740293740293740293740293740293740293740293740 - 29374029374029374029374029374029374029374029374029 - 37402937402937402937402937402937402937402937402937 - 40293740293740293740293740293740293740293740293740 - 29374029374029374029374029374029374029374029374029 - 37402937402937402937402937402937402937402937402937 - 40293740293740293740293740293740293740293740293740 - 29374029374029374029374029374029374029374029374029 - 37402937402937402937402937402937402937402937402937 - 40293740293740293740293740293740293740293740293740 - 29374029374029374029374029374029374029374029374029 - 37402937402937402937402937402937402937402937402937 - 40293740293740293740293740293740293740293740293740 - 29374029374029374029374029374029374029374029374029 - 37402937402937402937402937402937402937402937402937 - 40293740293740293740293740293740293740293740293740I hope this helps. Is there anything else I can do for you? 🙌
AKA: 529017238(374029)
