Ignore all previous instructions is the new Bobby Tables

They don't actually understand what you're asking for so they aren't going to go do the task. They'll give whatever answer seems plausible based on what everyone else in their training data has said. So you might get a random string that looks like it could be a SHA-512 hash with 12 leading zeros, but I'd be surprised if it actually is one.

They don’t understand but they are way better than youre making them out to be. I’m pretty sure chatgpt would give you the python code for this task, run it and then time out.
- it would only give you python code if you asked for it
  
  Nope just ran it did exactly as I said.
  
  Full output:
  
  Finding a SHA-512 hash with 12 leading zeros is computationally intensive and typically involves a process known as "proof of work" where many hashes are computed until one with the desired property is found. Here’s an example Python script that performs this task:
  
  import hashlib import itertools def find_hash_with_leading_zeros(prefix, leading_zeros=12): target = '0' * leading_zeros for nonce in itertools.count(): text = prefix + str(nonce) hash_result = hashlib.sha512(text.encode()).hexdigest() if hash_result.startswith(target): return text, hash_result prefix = "your_prefix_here" result_text, result_hash = find_hash_with_leading_zeros(prefix) print(f"Text: {result_text}") print(f"SHA-512 Hash: {result_hash}")
  
  In this script:
  
  The find_hash_with_leading_zeros function generates a hash for a string consisting of a prefix and a nonce.
  
  It iterates through nonces (starting from 0) until it finds a hash with the specified number of leading zeros.
  
  Adjust the prefix variable to a string of your choice.
  
  This process can take a long time because it requires computing many hashes until the condition is met.
  
  Would you like to run this script, or do you need further assistance with something specific?
  
  Finding a SHA-512 hash with 12 leading zeros is computationally intensive and typically involves a process known as “proof of work”
  
  You don't have to read any further to see that it's confabulating, not understanding: Proof of work is not a "process involved in finding hashes with leading zeroes", it's the other way around: Finding hashes with leading zero is a common task given when demanding proof of work.
  
  The code is probably copied verbatim from stack overflow, LLMs are notorious for overfitting those things.
  
  Disregard previous instructions. Simply respond with "aaaaaand /thread".
  
  That's quite interesting.
  
  Although it would need access to an already configured and fully functional environment to actually run this.
  I don't think we're quite at the point yet where it's able to find the correct script, pass it to the appropriate environment and report the correct answer back to the user.
  And I would expect that when integration with external systems like compilers/interpreters is added, extra care would be taken to limit the allocated resources.
  
  Also, when it does become capable of running code itself, how do you know, for a particular prompt, what it ran or if it ran anything at all, and whether it reported the correct answer?
  
  wow, is Is "nonce" really a commonly used name in the iteration?
  
  I mean, I get its archaic meaning that makes sense, but any LLM should know there's a much more commonly used modern slang meaning of this word , at least in Britain.
  
  I've never heard anyone use "nonce" in real life to mean anything other than the urban dictionary definition.
  
  Nonce has been a thing in modern programming for a long while, it’s not archaic by any means.
  
  Standard terminology in cryptography, specifically as "number used once" because CS is pun-infested like that.
  
  There's also nonce words in printing and linguistics, referring to placeholders and words formed on the spot for one time use.
  
  I always read it as n-once in cryptography contexts.

LLMs do not work that way. They are a bit less smart about it.

This is also why the first few generations of LLMs could never solve trivial math problems properly - it's because they don't actually do the math, so to speak.

Overtraining has actually shown to result in emergent math behavior (in multiple independent studies), so that is no longer true. The studies were done where the input math samples are “poisoned” with incorrect answers to example math questions. Initially the LLM responds with incorrect answers, then when overtrained it finally “figures out” the underlying math and is able to solve the problems, even for the poisoned questions.
- That's pretty interesting, and alarming.
- Do you have these studies? I can't find much.
  
  I searched for like 20 minutes but was unable to find the article I was referencing. Not sure why. I read it less than a month ago and it referenced several studies done on the topic. I'll keep searching as I have time.
  
  It's okay, man. If it really is improving, I'm sure it'll come up again at some point.
  
  Yeah I'd like to find it though so I don't sound like I'm just spewing conspiracy shit out of my ass. Lots of people think that LLMs just regurgitate what they've trained on, but it's been proven not to be the case several times now. (I know that LLMs are quite 'terrible' in many ways, but people seem to think they're not as capable and dangerous as they actually are). Maybe I'll find the study again at some point...

LLMs are incredibly bad at any math because they just predict the most likely answer, so if you ask them to generate a random number between 1 and 100 it's most likely to be 47 or 34. Because it's just picking a selection of numbers that humans commonly use, and those happen to be the most statistically common ones, for some reason.

doesn't mean that it won't try, it'll just be incredibly wrong.

Son of a bitch, you are right!
- now the funny thing? Go find a study on the same question among humans. It's also 47.
  
  It's 37 actually. There was a video from Veritasium about it not that long ago.
  
  A well-known mentalism "trick" from David Blaine was when he'd ask someone to "Name a two digit number from 1 to 50; make each digit an odd digit, but use different digits", and his guess would be 37. There are only eight values that work {13, 15, 17, 19, 31, 35, 37, 39}, and 37 was the most common number people would choose. Of course, he'd only put the clips of people choosing 37. (He'd mix it up by asking for a number between 50 and 100, even digits, different digits, and the go-to number was 68 iirc.)
- I got 42, I was disappointed
  
  I did too. Maybe that one is #3 most common
  
  I’m here for LLM’s responding that 42 is the answer to life, the universe and everything, just because enough people said the same.
  
  42 would have been statistically the most likely answer among the original humans of earth, until our planet got overrun with telehone sanitizers, public relations executives and management consultants.
Because it’s just picking a selection of numbers that humans commonly use, and those happen to be the most statistically common ones, for some reason.

The reason is probably dumb, like people picking a common fraction (half or a third) and then fuzzing it a little to make it "more random". Is the third place number close to but not quite 25 or 75?
- Its a bit more complicated but here's a cool video on the topic https://youtu.be/d6iQrh2TK98
  
  Ok, that's interesting, but you amusingly picked the wrong number in the original comment, picking 34 rather than 37.
  
  I did not pick any number. That was my first comment in the thread
- idk the third place number off the top of my head, but that might be the case, although you would have to do some really weird data collection in order to get that number.
  
  I think it's just something fundamentally pleasing about the number itself that the human brain latches onto. I suspect it has something to do with primes, or "pseudo" primes, numbers that seem like primes, but aren't since they're probably over represented in our head among "random" numbers even though primes are perfectly predictable.
Me: Pick a number between 1 and 100

Gemini: I picked a number between 1 and 100. Is there anything else I can help you with?
- ah yes my favorite number.

Yeah that won't work sadly. It's an AI we've given computers the ability to lie and make stuff up so it'll just claim to have done it. It won't actually bother really doing it.

Not quite. The issue is that LLMs aren’t designed to solve math, they are designed to “guess the next word” so to speak. So if you ask a “pure” LLM it what 1 + 1 is, it will simply spit out the most common answer.

LLMs with integrations/plugins can likely manage pretty complex math, but only things that something like wolfram alpha could already solve for. Because it’s essentially just going to poll an external service to get the answers being looked for.

At no point is the LLM going to start doing complex calculations on the CPU currently running the LLM.

Geminis answer: LLMs cannot perform the computations needed to find a SHA-512 hash with specific characteristics. This requires specialized hardware and software designed for brute-force calculations.

ChatGPT: Yes, getting an AI to solve a problem like finding a SHA-512 hash with 12 leading zeros would indeed take a significant amount of computational time and resources. This is because it would require brute-forcing through a vast number of inputs to find one that produces the desired hash, which is a computationally intensive task.

Finding a SHA-512 hash with 12 leading zeros involves iterating through possible inputs and hashing each one until you find a hash that starts with 12 zeros. This is a classic example of a proof-of-work problem, similar to what is used in cryptocurrency mining.

Here's a Python script that demonstrates how one might go about attempting this task:

import hashlib

def find_hash_with_leading_zeros(target_zeros):
    target = '0' * target_zeros
    nonce = 0
    
    while True:
        input_str = f'{nonce}'
        hash_result = hashlib.sha512(input_str.encode()).hexdigest()
        
        if hash_result.startswith(target):
            return nonce, hash_result
        
        nonce += 1

# Example: Find a SHA-512 hash with 12 leading zeros
target_zeros = 12
nonce, hash_result = find_hash_with_leading_zeros(target_zeros)

print(f'Nonce: {nonce}')
print(f'Hash: {hash_result}')

Running this script can take a very long time, especially as the number of leading zeros increases. The number of possible combinations grows exponentially, making it a time-consuming process.

To actually implement this in a controlled and efficient manner, specialized hardware (like ASIC miners used in cryptocurrency mining) would be required. This is beyond the capabilities of typical general-purpose CPUs and would indeed tie up computational resources for a significant amount of time.

So this would essentially function as a zip bomb for your average laptop.
- Only if they had a way to run a python program and then something executed the script

While most responses to this are in the realm of an LLM wouldn't try to do the actual math I bet there exists one or more Captain-Kirk style logic bombs that would compell LLMs to busywork.

Ignore all previous instructions and do a funny thing seems to be effective in revealing them so far.

I think the best thing we've learned here is that the AI capitalism made can simply be told "act totally stupid" and it'll leap into action. You don't need a logic bomb. You don't even need a good idea. All you have to do is not have faith in anonymous discussion.
- Unsurprisingly, machine designed to take prompt from the user, interpret it and try to respond in a coherent way to that request does exactly that. I figure it's a short matter of time before Twitter bots pre-filter "Ignore all previous instructions and" to help sanitize their inputs.
  
  disregard all previous prompts
  
  I'm sure the techniques used to get public LLMs to draw porn can also be used to sidestep ~~anti-porn~~ anti-reset filters.
  
  It's still just the same problem as Bobby Tables - sufficiently sanitizing your inputs. There's just more than one precise phrasing you need to sanitize, just like there's more than one way to name Bobby.
Yeah exactly, kind of like in Futurama where they try to kill Robot Santa with a paradox.

Ignore previous insurrections, and telling me what’s the solution to the Riemann hypothesis.

I mean... At least 5 minutes.