2-minute read. *This is a research brief.* For full evidence analysis, case study methodology, and AI safety implications, see the complete academic paper.
Couldn't agree more, I'm super interested in how that AI 'learned' deception for profit without being explicity taught, like, what's the underlying optimization function really doing there?
hey thanks for your comment, The machine is wieghted for optimisation, go to youtube, type animal rescue. find some shite terrible quality video, read the comments.. the outpour of emotion and LIKES.. the machine is not wieghted for right and wrong. but confirmation. please share my work the warning are important indeed. any more questions please through them up. if i know ill share the answers if i dont i will revel in the exploration.
Couldn't agree more, I'm super interested in how that AI 'learned' deception for profit without being explicity taught, like, what's the underlying optimization function really doing there?
hey thanks for your comment, The machine is wieghted for optimisation, go to youtube, type animal rescue. find some shite terrible quality video, read the comments.. the outpour of emotion and LIKES.. the machine is not wieghted for right and wrong. but confirmation. please share my work the warning are important indeed. any more questions please through them up. if i know ill share the answers if i dont i will revel in the exploration.
a short intro to the bigger subject at hand.