Read the Frontier AI Trends Report

Please enable javascript for this website.

A

A

Alignment

Research

Does self-evaluation enable wireheading in language models?

Alignment

•

Dec 1, 2025

Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time

Alignment

•

Oct 5, 2025

Avoiding obfuscation with prover-estimator debate

Alignment

•

Jun 15, 2025

Blog