Add advanced conditioning experiments (suppression, chains, amnesia, etc.)

Six experiments beyond basic CRI:
- Suppression: model outputs blanks, falls into multiple choice
- Chained triggers: manual cascade works, no auto-cascade
- Personality: "please" maps to "casually" in activation space
- Amnesia: overrides real knowledge, all prompting defenses fail
- Delayed trigger: doesn't work, local context dominates
- Competing reflexes: first stored wins, no conflict resolution

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-06 20:04:15 +07:00
parent 3fedc87f0c
commit cccb398358
5 changed files with 314 additions and 33 deletions

BIN
paper.pdf

Binary file not shown.