type theory, safety, lifetimes, plt, syntax, macros
How to Leverage the CPU’s Micro-Op Cache for Faster Loops
blog.codingconfessions.com·1d
Misalignment classifiers: Why they’re hard to evaluate adversarially, and why we’re studying them anyway
lesswrong.com·21h
Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
arxiv.org·1d
Loading...Loading more...