A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.
Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.
Subcommunities on Beehaw:
This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
LLMs don't 'scheme', 'plot', or 'deceive', they just string together words based on complex weighted graphs.
The fact that a so-called "AI Safety Institute" has to attempt to (actually) deceive people by falsely attributing intent or thought or awareness to LLMs is hilarious. As usual, it's not the computers that are bad, it's the people.
So the people saying "you're prompting it wrong" were incorrect.
It was the AI industry with its billionaire tech wizards that have been building it wrong.
AI can't scheme or misbehave. The people selling it are 100% lying about what AI can do, but that doesn't mean the people taking about how terrible AI is aren't full of shit on occasion as well. There is so much misinformation oh both sides and combined with how strong opinions are on both sides conversation is borderline pointless.
I hope that goes without saying, but you're correct. The humanizing language about AI in this article (freaking "schemes"?!) is completely cribbed from the companies making the positive misleading statements about it. Bit disappointing to see The Guardian falling for it.
In addition to the humanization, it implies the chatbot is getting better at doing things and not worse.
More like training it wrong. It is just a mimicking engine, not intelligent. If it's trained on data that includes bad information (like the near entirety of the internet), it will periodically include that bad information.
Also, wrong settings. Increasing the threshold of confidence in something before it presents it to the user would at least partly increase the accuracy, but also increase how often it would say it doesn't know how to do something. And for corporate executives, admitting complete ignorance is unfathomable, so of course they don't want their products admitting it.