Gemini 31 Pro
4 mentions across 2 people
Visit ↗All mentions
Dwarkesh Patel
Mixedpaper · 2026-06-09
“Our evaluation across four frontier models, Gemini 3.1 Pro, GPT-5.5, GLM-5.1, and Qwen3-Coder, demonstrates that error-path injection triples the success rate of standard indirect prompt injection (IPI), achieving up to 100% compliance in controlled evaluations.”
Error-Path Injection: Exploiting Tool Error Messages to Bypass LLM Safety Heuris ↗
“Gemini 3.1 Pro: A smarter model for your most complex tasks”
Gemini 3.1 Pro: Scaling Core Reasoning for Complex Synthesis and Creative Coding ↗