Publications

Lilly: Self‑Steering Cognitive AI

Research Highlights

Suppression reversal
Framing‑dependent suppression reversal
Self‑report flips when framing changes, while behavior is stable.
Scaling comparison
Scale effects (8B vs 14B)
Suppression weakens at larger scale.
Probe comparison
Probe methodology sensitivity
Measurement choice changes the apparent size of the effect.

Want a concise summary?

The briefing pack includes the top findings, figures, and reproducibility notes.

If you are interested in sponsoring this line of research or discussing a role, please reach out. I can provide a short briefing pack with core findings, figures, and reproducibility notes.