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.
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.
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.
You can’t handle the 8888888888888888888888888888888888!
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
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.
I have yet to be given an example of something a “general” intelligence would be able to do that an LLM can’t do.
Presenting…
Something a general intelligence can do that an LLM can’t do:
Play chess: https://www.youtube.com/watch?v=kvTs_nbc8Eg
Why can’t it play it? Because LLM’s don’t have memory, so they can’t work with logic. They are the same as the little “next word predictor” in your phone’s keyboard. It just says what it thinks is the most probable next word based on previous words, it’s not actually thinking or understanding anything. So instead, we get moves that don’t make sense or are completely invalid.
What’s this font?
My Underwood. I’m in love with it.
I find it exceptionally difficult to read (at least your screen cap on mobile is hard to read)
Yeah, between the image compression and resolution, a lot of things that should be ‘gaps’ in the letters are closing up. Like, the ‘s’ in ‘psuedorandom’ or ‘set’ looks like a squished-up ‘g’.
I can read individual words as I’m looking at them, but I’ve lost the ability to scan the line and parse words in my peripheral vision.
How do you even change the font in your browser?
Its in settings. Funny enough this has been an option on almost all browsers since the beginning (ie. Netscape Navigator, as well as IE3)
Iirc librewolf (and possibly Firefox by extension) has a setting for it
Settings > Default Font. (This is a serious answer for Firefox 120).
Just tried with alpaca ggml-alpaca-7b-q4.bin (a text chat model that I found I can run locally easily on my CPU).
> Generate and list 30 non-repeating 50-digit psuedorandom seeds. 1. 978642450 2. 463589826 3. 705123458 4. 286749035 5. 134628359 6. 693941285 7. 524378609 8. 115723468 9. 346258197 10. 637428513 11. 456193726 12. 294683125 13. 824635197 14. 581234609 15. 237641935 16. 721943586 17. 312684637 18. 602378193 19. 451372609 20. 985134637 21. 126843586 22. 376412851 23. 721941358 24. 237640193 25. 513724609 26. 194635819 27. 463581260 28. 358124637 29. 134628359Looks somewhat random.
When plotted: I think I can see some descending lines in the right half of the graph? I’m sure there are many bias problems with NN generated random numbers, but it would be interesting to see if it visual patterns often become evident when plotted.
Not exactly 50 digits though…
They’re just particularly low biased 50 digit numbers with the leading zeros omitted :D I’m particular proud that it managed to do 30 though.
It’s interesting that none of the the numbers start with zero. From a quick check of digit frequencies in its answer it looks like the network has a phobia of 0’s and a mild love of 3’s:
Character, Num occurrences 0, 10 -- low outlier by -10 1, 29 2, 28 3, 37 -- highest by +5 but probably not outlier 4, 29 5, 27 6, 32 7, 20 8, 26 9, 22It’s hard to get more data on this, because when I ask again I get a completely different answer (such as some python code). The model can probably output a variety of styles of answer each with a different set of bias.
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.
Yes. Don’t be that one teacher who always has one multiple choice question that has no right answer.
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.
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.
