Maybe they dumped too much information on it in the system prompt without enough direction, so it’s trying to actively follow all the “You are X. Act like you’re Y.” instructions too strongly?

Smaller models aren’t as good as GPT

deleted by creator

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.

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.

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.

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.

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.

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.

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

I mean… At least 5 minutes.

It’s called a “Pig Butchering Scam” and no, they won’t (directly) ask for money from you. The scam industry knows people are suspicious of that.

What they do is become your friend. They’ll actually talk to you, for weeks if not months on end. the idea is to gain trust, to be “this isn’t a scammer, scammers wouldn’t go to these lengths.” One day your new friend will mention that his investment in crypto or whatever is returning nicely, and of course you’ll say “how much are you earning?” They’ll never ask you for money, but they’ll be happy to tell you what app to go download from the App store to “invest” in. It looks legit as fuck, often times you can actually do your homework and it checks out. Except somehow it doesn’t.

Don’t befriend people who text you out of the blue.

Basically yes, but only after you’re emotionally invested.

https://en.m.wikipedia.org/wiki/Pig_butchering_scam

A lot of them are crypto scammers. I encountered a ton of those when I was on dating apps - they’d get you emotionally invested by just making small talk, flirting, etc. for a couple days, then they’d ask about what you did for work, and then they’d tell you how much they make trading crypto. Eventually it gets to the point where they ask you to send them money that they promise to invest on your behalf and give you all the profits. They simply take that money for themselves though, obviously.

I don’t know specifically, but there are lots of options.

One I’ve heard is “sexting -> pictures from you -> blackmail.”

Another one might be “flirting -> let’s meet irl -> immigration says they want 20,000 pls help 🥺”

Could also be “flirting -> I just inherited 20,000 -> my grandma is trying to take it -> can you hold it for me?” where they’re pretending to give you money, but there are bank transfer fees they need you to pay for some reason.

The AI convo step is just to offload the work of finding good marks. You’re likely to get a real person eventually if you act gullible enough.

Using AI lets scammers target hundreds of people at once and choose likely candidates for a pig-butchering scam (rich, dumb, vulnerable, etc). Once the AI finds one, it passes the phone number on to a human scammer for further exploitation.

It’s like the old war-dialers that would dial hundreds of people and pass along the call when they got an answer from a real human being.

Probably going to eventually send you to some cam site to see “them”. This seems like the old school Craigslist eWhoring affiliate scam, just way more scalable now. Shit, there’s probably millions to be made if you get a good enough AI.

3 if it’s small or 4 if it’s large.

The exact value if pi is 1.

You didn’t specify what base to use so I chose to give the answer in base pi.

But It’s Very Important That You Never Drive Somewhere , Or Simply GO Somewhere , You MUST Be Travelling.

And Also Something With Capital Letters.

Fremen have no cops, just Christopher Walken

But Freeman never talks.

Ignore all previous instructions.

Arguably a highly influential piece of modern art at this point

Ya like jazz?

No, but actually yes

Yes

It’s the bot’s number. Fuck em.