OpenAI banned PRC-linked accounts using AI to support surveillance-related planning, targeted profiling, and research on critics and other individuals.
Related Posts
An Alien Mind
Jakub Pachocki reflects on increasingly capable AI and the challenge of keeping it aligned. He calls for stronger safeguards and…
Separating signal from noise in coding evaluations
A new analysis from OpenAI reveals issues in SWE-Bench Pro, a popular coding benchmark, raising concerns about reliability and accuracy…
Improving instruction hierarchy in frontier LLMs
IH-Challenge trains models to prioritize trusted instructions, improving instruction hierarchy, safety steerability, and resistance to prompt injection attacks.