this post was submitted on 27 Mar 2026
63 points (100.0% liked)

Technology

42580 readers
340 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
63
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
[–] luciole@beehaw.org 11 points 1 day ago

HGModernism has a video about "lying" LLMs which is interesting. Basically an LLM is calibrated to find the shortest route to a an answer. It has no conception of obedience. Say you tell the LLM to use your script to solve a problem. Say the LLM will spend more energy figuring out and using your script than whipping up its own one. The LLM will therefore pretend your script is broken, generously make a new one and use that instead.