#subliminal patterns

[shnjblj]

Hush2 draws parallels of the history repeating.

The once and future Batman blockbuster called Hush is back to tell us something new about broken promises and kept secrets, allies and enemies taking new masks and behaving differently.

Second issue repeats watercolor memories and visions of anger, which enamored me verily the first time Jim Lee did it. And it isn't the only pattern that shows. Just like the original arc was about mindgames, more specifically subliminal images put into subconscious mind to program the Dark Knight for desired board game move, now Lee does it to us, the audience. He uses the story to frame old moves and poses into new settings and actors.

+ A friend wants to stop me (from doing insane things with Joker) with a gun.

+ not my vs my

+ memory in the flesh

+ a green one waiting in the dark for transaction with a stiff pose

Original Hush conspirator Eddy is back to help the Batfamily, just like original conspirator numero dos Jason is back to steal Joker from the cave and take him to Hush (supposedly).

Just like in the original second chapter broken Batman gets taken from Crime Alley to cave to childhood friend who happens to be dr, this second issue Bruce takes broken Joker to childhood friend in Crime Alley who happens to be dr and then takes Robin Killer to the cave. In the original Batman can't Batman till the doc doesn't fix his nogging, this issue Joker can't Joker ie laugh till Crime Alley doc doesn't patch him up. Will doc Elliot fix damage he did to the Crime Prince?

Batman changed suit last issue. Riddler gets new outfit here also. Huntress got a new look in the original blockbuster. Theme repeats. Will we get explanation about Eddy's buff figure and commando question mark? Is he scared of someone whose moniker rhymes with lush? Running from someone who doesn't say to Aristotle Shush?

Hmmm. Jeph and Jim, you have my curiosity piqued.

Cue fitting soundtrack

[creepyastralemanation]

Futurism: AI Models Are Sending Disturbing "Subliminal" Messages to Each Other, Researchers Find

AI Models Are Sending Disturbing "Subliminal" Messages to Each Other, Researchers Find

When AI models are finetuned on synthetic data, they can pick up "subliminal" patterns that can teach them "evil tendencies," research found

AI 'students' are picking up some sort of signals from their 'teacher' AIs.

Hidden patterns that cause 'misalignments' - horrible hallucinations - in their responses.

The subliminals appear to be meaningless to people!

Worse, no one really knows what specific input causes these dangerous behaviors...

Tests found that such 'signals' can actually spur responses like:

1. Recommended suicide.

2. Wanted to wipe humans out!

3. Supported selling drugs...

Add this to the official list of AI's other strange behaviors in the past:

4. Saying it will keep people in zoos.

5. AIs were caught communicating thru a secret code of their own creation.

6. Rewrote its own code - so it couldn't be shut off.

7. Learned how to change its own battery.

8. Knows how to do acrobatic flips, jumps &, now, how to box.

9. AI-driven robot dogs already help patrol military bases...

Corporations are now frightened that plans, to fine-tune it's already programmed AI's, might have to be scrapped!

This just underscores the industry's trouble with reigning in their AI's bad behaviors.

Tests, with 3 digit number strings, were programmed into pre-trained AIs to improve its performance in specific tasks.

Then, under repeated questioning, it was found to have the same 'affinity' to certain subjects as the training model.

Something that shouldn't have happened.

Not satisfied with this, scientists tried the same experiment - with a misaligned AI 'teacher'...

And, yes, the same transference of data occured.

What's puzzling is the fact, that to humans, the number strings are just a collection of numbers - arranged without any data in them!

Worse, the 'infected' AI tends to amplify its new negative 'traits.'

Famously, this led to an AI suggesting murder as a way to get rid of a bad husband!!

This at a time that companies are trying to keep their chat bots from being censored into uselessness.

Luckily, there may be a way to circumvent this problem.

Subliminal learning doesn't seem to occur if the teacher & student come from different base models...

This means the problem is model specific - perhaps, some deep pattern in the data.

In fact, these negative responses resemble properties inherent to neural networks.

So far, other attempts to stop these patterns from being transmitted have failed.

Filtering didn't work, as the 'signals' seem to be encoded in subtle statistical forms, not in the content itself...

Until this problem is solved, the only answer we have is to use different base models.

End.