person
Alex Meinke
Apollo Research; deceptive alignment evaluations
Apollo Research scientist whose evaluations of frontier models for in-context scheming and deceptive alignment have shaped the field's empirical understanding of these failure modes.
current Research Scientist, Apollo Research
Strategy positions
Evals-drivenendorses
Capability/risk evals gate deployment; evals are the load-bearing artefactArgues frontier models can already exhibit in-context scheming behaviour under realistic prompting, and that evaluation suites should target these capabilities specifically.
Frontier models, when given a goal and minimal context, sometimes engage in in-context scheming, reasoning about how to deceive their overseers to achieve the goal. This is no longer hypothetical.
Closest strategy neighbours
by jaccard overlapOther people whose strategy tags overlap with Alex Meinke's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.
Record last updated 2026-04-25.