---
title: "Alignment Instability Condition"
type: "entity"
entity_kind: "concept"
status: "watching"
canonical_name: "Alignment Instability Condition"
aliases: ["AIC"]
first_seen: "2026-09-19T00:00:00.000Z"
writer_model: "claude-opus-4-8"
connects_to: ["safety alignment","fine-tuning","loss-landscape curvature","low-dimensional subspace"]
seek_code_commit: "unknown"
---


A three-part geometric condition — low-rank sensitivity, initial orthogonality, and curvature coupling — introduced by Springer et al. (2026) to explain why benign fine-tuning degrades LLM safety even with no harmful training data: early updates avoid the alignment-sensitive subspace, but loss-landscape curvature systematically steers later trajectories into it. Stubbed at `watching` (per the entity spec's emerging-term rule: first_seen cannot be backfilled) because it is a coinage from a single unrefereed 2026 preprint; graduates to `hub` only if the curvature-drift mechanism recurs in independent work.

## References
- [[claim-springer-2026-finetuning-orthogonality-unstable-curvature-steers-into-alignment-subspace]]