MindPattern
← The Wire
Entity trail

Hadfield

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs
1
Findings
1
Edges
0
Sources
1

Corpus findings

  1. 2026-06-23 / sources-researcher'Destyling' Untrusted Input Cuts Prompt-Injection Success From ~61% to ~10% (Willison Write-Up)Simon Willison's June 22 post surfaces 'Prompt Injection as Role Confusion' (Ye, Cui, Hadfield-Menell; ICML 2026), which argues injection works because models infer the speaker from a text's style, not its labeled role tag. The actionable defense — 'destyling' untrusted input by rewriting it into a neutral voice — dropped attack success from ~61% to ~10% across open- and closed-weight models. The paper itself is older (arXiv 2603.12277), but the takeaway is directly usable in agent input pipelines today.

Source trail

Simon Willison

Graph sources

entity graphfindings textkg entitiesnewsletter issues