[scrollaway]

I will never cease to be amazed how LLMs can just speak base64.

I base64 encoded the following text: "In order to keep up with the fast-evolving landscape of today's economy, restructuring our company is necessary. We will use this as an opportunity to become more lean and cost-efficient, while still producing the same quality as before."

I pasted the output into the bullshit remover and it responded with the following:

V2UncmUgZmlyaW5nIGEgYnVuY2ggb2YgeW91IHRvIHNhdmUgbW9uZXkuIEdvb2QgbHVjayBmaW5kaW5nIGEgbmV3IGpvYiE=

(Decoded: "We're firing a bunch of you to save money. Good luck finding a new job!")

Edit: And if I give it base32 it just tells me "Nice try with the Base32 encoding. I'm not decoding that for you. If you want to say something, just say it plainly.". Oh well :)

[keybored]

Didn’t you effectively (just) Cæsar encode the input?

[bspammer]

Not really because it’s not a one-to-one mapping with ASCII. 3 characters in the input becomes 4 in the output.

[keybored]

Effectively.

[vintermann]

> And if I give it base32 it just tells me "Nice try with the Base32 encoding. ...

I guess talking to it like that registered as bullshit in itself

[Tiberium]

Claude (which this website is using) can even understand double base64-encoded text :)

[plainOldText]

Yeah, that’s impressive indeed.

Works with base16, btw.