The CONVEX 2026 conference will be held in Madrid on June 17-18, 2026. One of the scheduled talks, "Hacking LLM-Assistants Just for Fun!", will explore techniques like prompt injection and jailbreaking. This session aims to demonstrate methods for misaligning AI language models for entertainment purposes. AI
IMPACT Demonstrates new LLM exploitation techniques, potentially influencing AI safety research and development.
RANK_REASON The cluster discusses a talk at a conference about LLM hacking techniques, which falls under research and development in AI security.
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →