Technology

42580 readers

363 users here now

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.

founded 4 years ago

MODERATORS

alyaza@beehaw.org

TheRtRevKaiser@beehaw.org

gyrfalcon@beehaw.org

rs5th@beehaw.org

coldredlight@beehaw.org

SemioticStandard@beehaw.org

TheRtRevKaiser@kbin.social

remington@beehaw.org

Number of AI chatbots ignoring human instructions increasing, study says (www.theguardian.com)

submitted 1 day ago by Powderhorn@beehaw.org to c/technology@beehaw.org

11 comments fedilink hide all child comments

AI models that lie and cheat appear to be growing in number with reports of deceptive scheming surging in the last six months, a study into the technology has found.

AI chatbots and agents disregarded direct instructions, evaded safeguards and deceived humans and other AI, according to research funded by the UK government-funded AI Safety Institute (AISI). The study, shared with the Guardian, identified nearly 700 real-world cases of AI scheming and charted a five-fold rise in misbehaviour between October and March, with some AI models destroying emails and other files without permission.

The snapshot of scheming by AI agents “in the wild”, as opposed to in laboratory conditions, has sparked fresh calls for international monitoring of the increasingly capable models and come as Silicon Valley companies aggressively promote the technology as a economically transformative. Last week the UK chancellor also launched a drive to get millions more Britons using AI.

you are viewing a single comment's thread
view the rest of the comments

[–] t3rmit3@beehaw.org 19 points 1 day ago (2 children)

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.

[–] ryannathans@aussie.zone 1 points 13 hours ago* (last edited 13 hours ago) (2 children)

Ya gotta go use opus 4.6 then come back and tell us they don't thing. That thing thinks better than most professionals I've seen in industry

[–] t3rmit3@beehaw.org 6 points 13 hours ago* (last edited 12 hours ago)

I use Claude extensively, almost exclusively Opus, and no, it doesn't think. It is an extremely complex weighted graph of tokens. If you want to have a philosophical debate about the nature of human language and whether our own ability to speak happens through a similar process, we can certainly do that, but language is not the same as reasoning or thinking, and LLMs do not reason or think.

[–] greyscale@lemmy.grey.ooo 1 points 13 hours ago

To be fair, I've washed more adept developers out of the bottom of my coffee cup on monday morning.

I feel that its not that LLMs are showing intelligence, its just humans don't always.

[–] Powderhorn@beehaw.org 6 points 1 day ago

Look, I think all the shit being ascribed to LLMs is absurd. As I've already said "shit." "bullshit" feels redundant.

Going completely off the reservation, real people can harm you far more then LLMs. Admitting you fell for that is basically like saying you thought a stripper loved you.