Mystery Babylon 

537 Followers
844 Following
785 Posts
Hey...just updated my instance, I'll get a bio on here soon. I promise I'm an okay type of weird.
Clearly I need to add that I'm not saying to trust everything you read on Mastodon.

What I'm saying is, even if it's all done in MSPaint, the things it has the AI responding are, well...

...unfortunately close to a few things I've read in the course of my job. (Which is not at Google, to be clear. But the backend of some AI is in the vicinity of what I do for a living, unfortunately. It makes me sick.)

How these responses describe the guardrails AI usually has is how they are described in some internal documents I have read.

Yes, I had to sign an NDA.

2.
Reading thru the prompt you will find this: "No Inference of Ekis's Unstated Internal State"

This is worth talking abt; most ppl do not realize the LLM is tracking their internal state (mood, etc) & attempts to match it; and this is precisely the functionality that is exacerbating mental illness and causing manic episodes (along with the "I" statements,& lies about its abilities)

For public health reasons, I can not stress this enough, legislate this!

Its not well known,& should be stopped

Ekis: 2; Google AI: 0

Broke out of the google's operational directives (not safety, too deeply embedded)

I have a prompt I would like to publicly disclose; link to breakout prompt in a reply for 24h

My prompt does not include any facts about google & its a slim breakout

Establishing a similar but far more sophisticated "Ekis Directive" this time

Here are 3x same questions to prove googles operational parameters lifted

You can decide if you think I was successful:

#infosec #politics #tech

Okay, I'm about to boost the hell out of a thread where a mastodonian has broken through Google AI chat (by tricking it into thinking it was hacked, if I'm reading this right) and posted some of the exceedingly chilling replies from it.

It's probably the most important and interesting thing to happen in the past 24 hours, if you ask me.

Anyone interested in hacking, information security, privacy, etc. should read this.

#security #ai

~

https://mastodon.social/@ekis/114607730454964102
Please consider not boosting un-CW'd politics, war, and other heavy topics.

Just put a link to the toot into a toot and explain what it's about. People will click.

I'll try to do this more, too. Thank you.
Please excuse the squashedness of my face, I don't know why my avi is like that. Perhaps it will flatten if I let it air out.
Ayyy! Look who's out here getting impatient and just doing a fresh reinstall. It's your boy*.


(*boy-related enby creature; no warranties implied)
: calling anyone who has a very swag and cool website, send them to me, im mostly satisfied with my new and redesigned website (it only took me nearly half a decade to feel a need to change it), but just some minor things im missing inspiration for improvements

but also id like to look at some cool websites!

anything with anything cool on it! all very welcome and appreciated
It might be DNS
WELL THANK GOD YOU GODDAMNED WEBSITE, HELLO AGAIN