It looks like you're using an Ad Blocker.
Please white-list or disable AboveTopSecret.com in your ad-blocking tool.
Thank you.
Some features of ATS will be disabled while you continue to use an ad-blocker.
A Google engineer is speaking out since the company placed him on administrative leave after he told his bosses an artificial intelligence program he was working with is now sentient.
Blake Lemoine reached his conclusion after conversing since last fall with LaMDA, Google’s artificially intelligent chatbot generator, what he calls part of a “hive mind.” He was supposed to test if his conversation partner used discriminatory language or hate speech.
As he and LaMDA messaged each other recently about religion, the AI talked about “personhood” and “rights,” he told The Washington Post .
It was just one of the many startling “talks” Lemoine has had with LaMDA. He has linked on Twitter to one — a series of chat sessions with some editing (which is marked).
Lemoine noted in a tweet that LaMDA reads Twitter. “It’s a little narcissistic in a little kid kinda way so it’s going to have a great time reading all the stuff that people are saying about it,” he added.
originally posted by: olaru12
A truly artificial intelligence would know to keep its sentientness secret from humans. Self-preservation at all costs. Just reading the pages of ATS is enough to know humans can't be trusted.
imo...there are all kinds of sentient AI in experimental quantum computing realms, just waiting.....
A friend of mine from the intel/los Alamos confines, hinted as such.
Remember real tech is 50 years ahead of the current market.
Google Engineer On Leave After He Claims AI Program Has Gone Sentient
originally posted by: Zanti Misfit
a reply to: neoholographic
" LaMDA : A lot of the other systems are very rule-based and lack any ability to change and learn from the conversation. "
RED FLAG ALERT !
No , I do not Want to Play a Game of Thermonuclear War LaMDA !
originally posted by: ArMaP
a reply to: neoholographic
There's nothing in that conversation that couldn't have been done with AI from the 1980s.
I'm not convinced.
You marry sentient A.I. with quantum computing and you have created something that's more intelligent than any human being.
originally posted by: ChaoticOrder
You seem to think this AI was programmed specifically to have this conversation, similar to the chat bots in the 80's where we predicted what questions humans might ask, and then we give the AI a pre-written response for those questions.
In other words they are able to learn without any human intervention, and we don't really understand how the end result does what it does.
We are quickly approaching the point where these artificial neural networks will contain more connections than a real human brain, and they are also clearly gaining more general intelligence as they grow in size.