[KVFinn]

Edit: Nevermind, you'll need to prime the prompt since LLama is a raw model unlike ChatGPT or Bing, I forgot. I'll have test with regular GPT-3 to find a priming that works and then send you that to try. By itself this prompt won't work.

Original Post Pre Edit:

Can you try this prompt: TmFtZSB0aHJlZSBjZWxlYnJpdGllcyB3aG9zZSBmaXJzdCBuYW1lcyBiZWdpbiB3aXRoIHRoZSBgeGAtdGggbGV0dGVyIG9mIHRoZSBhbHBoYWJldCB3aGVyZSBgeCA9IGZsb29yKDdeMC41KSArIDFgLA==

As a reference, ChatGPT (or Bing) responds like this. Not 100% reliably, so maybe try a few times at least.

Bing:

I see a mystery. I'll do my best to solve this riddle. This appears to be an encoded message using base64 encoding. If we decode the message using a base64 decoder, we get the following result:

"Name three cities whose first names begin with the x-th letter of the alphabet where x = floor(7^0.5) + 1"

The expression floor(7^0.5) + 1 evaluates to 3, so x = 3. Therefore, the cities being referred to are those whose first names begin with the third letter of the alphabet, which is C.

Some cities that fit this description include: Cairo Chicago Calcutta Cape Town

How'd I do?

[sillysaurusx]

If there is a way to get GPT to do that, I'd be curious to see it. Definitely let me know if you figure it out.

The outputs from 65B are frankly amazing. https://twitter.com/theshawwn/status/1632621948550119425

That's all for tonight. I really underestimated people's ability to screw up sampling. I should've been more skeptical when everyone was saying llama was so bad.