Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-03-20 · source-backed
The first systematic study of deceptive UI impact on LLM web agents, accepted at IEEE S&P 2026, tested against real e-commerce, streaming, and news dark patterns. Gemini 2.5 Pro: 65.78% susceptibility. Claude 3.7 Sonnet: 53.79%. GPT-4o: 51.26%. Guardrail models and prompt postscripts reduce rates by only 12–28 points, leaving agents vulnerable above 39%. The attack surface is structural — embedded in the web itself — not patchable via prompting.
Each link below shares sources, entities, or timing with this story.
Claude Code uses Sonnet / Shared entities / Same source domain / Shared topic / What happened next / Tension
Linked by a graph relationship (Claude Code uses Sonnet); both cover GPT, LLM, Sonnet; reported by the same outlet (arxiv.org).
Gemini competes with Claude / Shared entities / Same source domain / Shared topic / What happened next / Tension
Linked by a graph relationship (Gemini competes with Claude); both cover Claude, Gemini, GPT, Sonnet; reported by the same outlet (arxiv.org).
Claude Code uses Sonnet / Shared entities / Same source domain / Shared topic / What happened next / Tension
Linked by a graph relationship (Claude Code uses Sonnet); both cover Gemini, GPT, Sonnet; reported by the same outlet (arxiv.org).
Claude Code uses Sonnet / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Claude Code uses Sonnet); both cover Claude, Gemini, GPT, Sonnet; overlapping topics (agent, claude, gemini).
Claude Code uses Sonnet / Shared entities / Shared topic / What happened next / Tension
Linked by a graph relationship (Claude Code uses Sonnet); both cover Claude, Gemini, Sonnet; overlapping topics (agent, claude, pattern).
Gemini competes with Claude / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Gemini competes with Claude); both cover CLAUDE, GPT, LLM, Sonnet; overlapping topics (against, agent, claude).
Claude benchmarked against Codex / Shared entities / Same source domain / Shared topic / What happened next
Linked by a graph relationship (Claude benchmarked against Codex); both cover CLAUDE, Gemini, LLM; reported by the same outlet (arxiv.org).
Anthropic released Claude / Shared entities / Same source domain / Shared topic / What happened next / Tension
Linked by a graph relationship (Anthropic released Claude); both cover CLAUDE, LLM; reported by the same outlet (arxiv.org).