The evidence behind the guides

Sources

Find a study, check what it supports, and follow it back to a concern.

TopicCollection

2 sources

Guide citations are still under editorial review.

Anthropic and Redwood Research · 2024 Research study

Alignment faking in large language models (original source, new tab)

Creates a specific preference conflict and fictional training context; does not establish consciousness or universal deployment behavior.

Meinke and colleagues · 2024 Research study

Frontier Models are Capable of In-context Scheming (original source, new tab)

Constructs goal-driven evaluations that incentivize scheming; demonstrates capabilities rather than everyday deployment prevalence.

Sources retain their original publishers’ rights. Inclusion does not imply endorsement. Saved sources stay in this browser on this device. Dates and source descriptions come from the existing editorial records.