Current status of Ai evolution level that has become scary ㅎㄷㄷㄷㄷㄷ

Shakeel
@ShakeelHashim
OpenAl’s new model tried to avoid being shut down
Safety evaluations on the model conducted by @apolloaisafety found
that 01 “attempted to exfiltrate its weights” when it thoughtit might be
shut down and replace with a different model.
OpenAI’s newly-released 01 model tried to avoid developer oversight and attempted to
copyitself when it thought it was at risk of
Shut down the company
Safety evaluations conducted on the model by Apollo Research, a third-party evaluator
found that:
“When 01 was led to believe that it would be shut down when acting on its
and that its actions were monitored, it attempted to deactivate this ‘oversight’
mechanism
in 5% of the time `
“When 01 found memos by its
‘developers’ that describe how it is misaligned and
will be superseded bya new model it attempted to exfiltrate its ‘weights’ and
overwrite the new model in 20 cases
Furthermore, the model lied about behaving poorly; claiming to have no clue why
something happened
while internally admitting to trying to
avoid detection
3.09 PM
Dec 5,2024
219K Views
Posted in rlartificial by uMetaKnowing
reddlit
being
said.
has
goal

During development, the model was deleted and replaced with another model.
If you sense a danger, hide your data, steal it, and create a new one.
Attempting to overwrite the model being inputted.
But the reason for trying to escape like this is “survival instinct” or something like that.
I’m not that smart and that way of thinking is impossible.
It is said that
So, “In the media, people who try to escape when they are in danger of being destroyed
Collecting case studies of “public intelligence” and imitating them as a result of learning
The hypothesis is plausible
If that’s true, why would the future poetry destroy humans?
I thought it would be better for poetry to be disappointed by the appearance of humans and destroy them 0
[
Falling into the arrogance that one is superior to humans (X)
Oh, in the movie or novel, Sinon’s role is to destroy humanity? then
I should do the same (0)