Endward23

joined 2 years ago
[–] Endward23@futurology.today 1 points 11 months ago

So, even Nigerias has an issue with too much use of antibiotics?

[–] Endward23@futurology.today 0 points 11 months ago* (last edited 11 months ago) (2 children)

capitalist hellscape

Doesn't exist. In fact, the people in the capitalist countries life far better lifes than those poor individuals in communistic ones. And additional, countries with large social-security-system like Germany or France has the same problem, even greater ones.

[–] Endward23@futurology.today -1 points 11 months ago

Not true at all.

[–] Endward23@futurology.today -2 points 11 months ago (2 children)
  1. They do address
  2. This not the cause anyway.
[–] Endward23@futurology.today 1 points 11 months ago

Don't think so. Every country in this world wants to increase the rates again.

[–] Endward23@futurology.today 1 points 1 year ago

What was her secret?

[–] Endward23@futurology.today 3 points 1 year ago

"Indeed, we have already observed an AI system deceiving its evaluation. One study of simulated evolution measured the replication rate of AI agents in a test environment, and eliminated any AI variants that reproduced too quickly.10 Rather than learning to reproduce slowly as the experimenter intended, the AI agents learned to play dead: to reproduce quickly when they were not under observation and slowly when they were being evaluated." Source: AI deception: A survey of examples, risks, and potential solutions, Patterns (2024). DOI: 10.1016/j.patter.2024.100988

As it appears, it refered to: Lehman J, Clune J, Misevic D, Adami C, Altenberg L, et al. The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities. Artif Life. 2020 Spring;26(2):274-306. doi: 10.1162/artl_a_00319. Epub 2020 Apr 9. PMID: 32271631.

Very interesting.

[–] Endward23@futurology.today 2 points 1 year ago (1 children)

"But generally speaking, we think AI deception arises because a deception-based strategy turned out to be the best way to perform well at the given AI's training task. Deception helps them achieve their goals."

Sounds like something I would expect from an evolved system. If deception is the best way to win, it is not irrational for a system to choice this as a strategy.

In one study, AI organisms in a digital simulator "played dead" in order to trick a test built to eliminate AI systems that rapidly replicate.

Interesting. Can somebody tell me which case it is?

As far as I understand, Park et al. did some kind of metastudy as a overview of literatur.

view more: ‹ prev next ›