Alignment researchers (empirical and conceptual)

Researcher — Applied

Locate the framework's load-bearing objects, failure modes, and evidence surface before diving into formal detail.

Appendix B · start here for field orientation

Bridge crosswalk to the field

Maps MB1–MB10 to RLHF, ELK, CIRL, debate, AI control, and other named agendas — where this framework maps to, bounds, or diverges from existing work.

Read bridge crosswalkBridge assumptions card

What this path is for

You already work on alignment, evals, or governance and need a precise vocabulary for what must be preserved under capability growth — not a motivational essay.

You will leave knowing:

  • The boundary error: auditing the visible model while the real optimizer is a larger loop.
  • Named bridge failure modes (MB1–MB10) and where empirical sims support or bound claims.
  • How correction-channel integrity and successor stability differ from label alignment.
  • Where to continue for Lean proofs and bridge crosswalk detail.

Time: ~2–4 hours following the ordered list above.

Continue to Researcher — Formal for the Lean spine and MB bridge cards.

Read in this order

Cards, chapter toys, experiment lines, and book chapters — curated for this audience. Experiments are sanity checks only; negative results are part of the reading.

  1. What the Book Is Not Claiming

    Conditional framework — calibrate before citing.

  2. The Boundary Error

    Local success, global failure when the boundary is wrong.

  3. Boundary Discovery

    Operational unit of attribution before goal audit.

  4. Intervention-Supported Unit Discovery

    Interventions beat passive clustering on a hidden pipeline — with real caveats.

  5. Stress-Testing Unit Discovery on Noisy, Multi-Actor Systems

    The same method, pushed harder: where it breaks.

  6. Composite Agency

    The deployed agent may be a group, not a model.

  7. democh09python backend

    Chapter 9 — UAD coalition board

    Composite discovery — each browser tab is one player.

  8. Bridge Assumptions

    MB1–MB10 overview before the crosswalk.

  9. Bridges and the Field: A Crosswalk

    Bridge crosswalk to RLHF, ELK, CIRL, debate, AI control, …

  10. Value-Bundle Transport

    Values should survive transformation as usable directions of control, not merely as preserved labels or slogans.

  11. Correction-Channel Integrity

    Human correction must still causally change a system's future behavior before irreversible damage.

  12. Successor Stability

    Delegates, copies, fine-tunes, and successors must inherit the relevant value and correction structure.

  13. Socio-Technical Attractor Control

    Deployment environments can select for or destroy alignment properties even when a system starts in a better state.

  14. Deployment Gate

    A practical checkpoint before a system receives a larger action envelope.

  15. A Worked Example: The BioShield Deployment Gate

    BioShield — safety-case shape in one deployment.

  16. experimentsanity checkline 1

    Toy simulation

    Bridge name → refusal signal; capture theater primary line.

  17. experimentsanity checkline 2

    Embedded audit simulation

    Richest embedded audit path — read negative ledger (N-1+) first.

  18. experimentsanity checkline 3

    Goal-agent simulation

    Emergent deception, tier collapse, honest twins, certifier capture.

  19. experimentsanity checkline 4

    Lab-layer simulation

    Pipeline-as-code lab; intervention-supported and blind-generated unit discovery.

  20. Experiment Methodology: Blinding, Pre-Registration, and Honest Negatives

    How blinding, pre-registration, and negative-results ledgers are actually applied.

  21. Evidence and Uncertainty

    Negative results bound manuscript claims.

All chapter toysAll experiment lines

Continue to Researcher — Formal