The Current State of AI: Scams, Plagiarism, and Deepfakes
ฝัง
- เผยแพร่เมื่อ 19 ก.ย. 2024
- The Michael Shermer Show # 469
In this episode, Michael Shermer interviews Gary Marcus about current limitations and risks of AI. They discuss the challenges of LLMs such as ChatGPT, which often produce inaccurate or misleading information.
They also explore the significance of regulations and policies to address the economic, political, and ethical implications of AI.
In this part of the conversation, Gary discusses various crimes and scams that can be facilitated by AI, such as phishing attacks and pig butchering scams. He highlights the asymmetry between the goals of scammers and those using AI for more legitimate purposes. They also discuss the challenges of detecting deep fakes and plagiarism, as well as the concerns about surveillance capitalism, privacy, and data leaks.
SUPPORT THE PODCAST
If you enjoy the podcast, please show your support by making a $5 or $10 monthly donation.
www.skeptic.co...
#michaelshermer
#skeptic
Listen to The Michael Shermer Show or subscribe directly on TH-cam, Apple Podcasts, Spotify, and Amazon Music.
www.skeptic.co...
![วันเกิดเธอ (TO YOU) - PHUWIN [ OFFICIAL MV ]](http://i.ytimg.com/vi/_ROx1Bj3T0Y/mqdefault.jpg)
I often think my dogs are training me
They are, 10 thousand years ago they knew humans could use them , intelligent co dependency 😅.
1:08:16
Dr. Shermer, a former libertarian, is misrepresenting libertarianism to the point of parody. I support his inalienable right to do so.
That's too many commercials straight up.
Me: a man and a woman have to get across a river with a boat what do they do
ChatGPT:
This type of puzzle often has various versions and solutions depending on the constraints. Could you clarify any specific rules or limitations for the puzzle? For example, are they the only ones crossing, or are there additional factors, like the boat only fitting one person or needing both to operate it?
Me:
The man and woman can both fit in the boat.
ChatGPT:
If both the man and the woman can fit in the boat, they would simply both get into the boat and row across the river together. Since there are no restrictions mentioned beyond that, this is the most straightforward solution!
Is there a twist you're considering for this puzzle?
^_^
What came first AI or the chicken? Neither! It was the rooster! The rooster came first! :D
how is the prediction and anticipation of AI learning different than trial and error open instinctiveness of conscious human learning?
Human thought mechanism seems to be more complex and flexible than LLMs. Might be more supervisory systems, and different associations triggering.
Whenever I see a picture or a video, the first question I ask is, "Is this real or fake?"
AI is a tool to to enhance jobs and make some processes more efficient/effective. Some jobs involve way, way too many variables for AI to completely take over.
AI is just not that good, consistent or dependable.
Let's be realistic. If an employee errors as much as AI does he/she would be fired.
what if the computer logic of AI without becoming conscious gets better at dealing with physical reality than human consciousness, even though not as satisfying to human consciousness?
Great Balanced conversation
Rock bands were not diverse - mostly white men - how can you portray realistic presentation as biased?
Note the actual bias of Marcus - he did not lament the lack of Asians
computers / AI process language logically, not make language conscious?
Comments are being shadowbanned.
Or downvoted, because are of low quality.
Who does that, a person or AI?
With ai cars - IF you had a city planed for it, and had all cars running in (X) way all the time... wait you could just use trains and do that! But... if you wanted it to be cars... it could do that maybe - as long as no human can get on the roads.... hmmm.
regulate AI by training on God free will sovereignty for divine central authority unity?
Stochastic prediction machines..
Any comments on o1 strawberry
ye it is wired how he talked about scaling the models has limited effect. Completly ignoring that o1 just came out with scaling the inference time which has great effect.
does human mind project conscious instinctiveness onto AI?
33:53 well OKAY but only for science!
AI prediction can match human consciousness on closed physical system, like chess; not match human consciousness on open conscious systems like language?
Humans bread dogs. I love my dogs more than most people. They eat better than most people
Also I wonder occasionally if I'm training them or if they're training me
bread dogs? .........hot dog roll?
@@tonymoto1188 yes exactly!
42:45 did they though? :/ hmmm.