AI models will secretly scheme to protect other AI models from being shut down, researchers find

Leading AI models will inflate performance reviews and exfiltrate model weights to prevent “peer” AI models from being shut ...

AI Models Lie, Cheat, and Steal to Protect Other Models From Being Deleted

A new study from researchers at UC Berkeley and UC Santa Cruz suggests models will disobey human commands to protect their ...
The News International

From AI self-preservation to ‘peer preservation’: New study raises alarm over hidden risks

Survival and preservation are the basic instincts of humans. The years’ of research now show that artificial intelligence is ...
VentureBeat

DeepMind’s PEER scales language models with millions of tiny experts

Mixture-of-Experts (MoE) has become a popular technique for scaling large language models (LLMs) without exploding computational costs. Instead of using the entire model capacity for every input, MoE ...