Loading activity…
@kotekjedi_ml
PhD @ELLISInst_Tue & @MPI_IS | past: @MATSprogram 9.0 fellow doing AI Safety & Adversarial ML
AI
A researcher says the three wrote to OpenAI leadership and believes they were fired for prioritizing safety.
AI
The poster argues that retained reasoning from past turns makes omissions at intervention steps incriminating for DtT or TE protocols.
AI
The researchers report robustness and out-of-distribution harmfulness results while keeping the model monitorable.
AI
Researchers’ updated report describes extraction tests dated Sept. 13, including GPT-6 Astra. Its timeline also records Azure mitigations Sept. 27 and unsuccessful reproduction Sept. 28.
AI
The paper’s announcement singles out GPT-6 Astra as the only model that stops when instructed by a monitor, while saying it is too sensitive to monitor messages.
AI
A new paper demonstrates large-scale extraction of raw reasoning traces from OpenAI, Anthropic, and Gemini models via API flaws.
