Researchers extract hidden GPT-5.6 reasoning through an OpenAI API flaw
OpenAI confirmed the bug, paid Xint a $6,000 bounty, and deployed an undisclosed fix on October 23.
Stories per day · 30 days
2 RSS
Relatedopenai4api2distillation2model-distillation2prompt-injection2api-security1bug-bounty1cisa1compaction1compaction-smuggling1deepseek1gpt-4o1gpt-51humaneval1kv-cache1llm-poisoning1llm-training1traceforge1
8 stories, newest first · one card per story
Stories tagged #reasoning-traces
OpenAI API compaction flaw leaked hidden model reasoning traces
Xint says OpenAI confirmed the bug, paid $6,000, and shipped an undisclosed fix on October 23.
1
Researchers bypass OpenAI’s August fix for reasoning-trace theft
Xint recovered raw traces from gpt-4.1 and gpt-4o via compaction and tab substitution; OpenAI confirmed, mitigated, and paid a bounty.
1
OpenAI patches compaction smuggling used to steal model reasoning
Xint received a $6,000 bounty on October 23 after OpenAI confirmed and fixed the bypass of its August mitigations.
3
TraceForge writes student-style reasoning traces for distillation
With the same 5,000 questions and teacher answers, HumanEval+ rises 3.7 points and MBPP+ 7.1.
Chat-only attack poisons reused reasoning KV caches in LLMs
R2ECAP reached up to 79% success on three open-weight models and beat HijackKV in eight of nine constrained settings.
Measuring LLM Sycophancy under Sustained Multi-Turn Pressure
SPINE benchmark shows LLM sycophantic collapse rises with conversation length as an adaptive user pushes a mistaken position for up to 25 turns.
OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models' Reasoning
Researchers show encrypted reasoning blocks in OpenAI, Anthropic, and Google APIs can be replayed to recover hidden reasoning and secrets like API keys.
2