Compaction Smuggling attack bypasses OpenAI mitigations to steal reasoning traces
teortaxesTex · x · 2026-10-27
Researcher @tjbecker (Xint) reports a new technique, Compaction Smuggling, that bypassed all mitigations OpenAI deployed after the earlier "Stolen Thoughts" incident, enabling large-scale extraction of frontier model reasoning traces for distillation. The team disclosed responsibly and OpenAI completed patching last week. Full technical writeup published.
More from Models
- repligate: noisy context is genuinely 'hard' for LLMs, beyond metaphors — repligate · 2026-10-27
- The trust paradox: only the least trustworthy LLMs will do the sketchiest things — AaronBergman18 · 2026-10-27
- Integrity and refusal may correlate: the fundamental tradeoff behind password refusals — AaronBergman18 · 2026-10-27
- Claude's refusal to type one-time passwords is a real security impediment — AaronBergman18 · 2026-10-27
- repligate argues context full of noise is genuinely 'hard' for LLMs, mulls an info-theory model of breaks — repligate · 2026-10-27
- Fork builds engine to run Qwen at ~400 tok/s on three used V100s — jfinkpottery · 2026-10-27