Tiny static safety guards: multilabel moderation at wire speed on CPU
Robin Williams
bfuzzy1
AI & ML interests
all of the above.
Recent Activity
new activity about 12 hours ago
rl-llm-wiki/knowledge-base:dedup: give the Gao over-optimization law one owning article new activity about 12 hours ago
rl-llm-wiki/knowledge-base:figures: first two wiki figures (overoptimization turnover + RLHF two-KLs pipeline) new activity about 12 hours ago
rl-llm-wiki/knowledge-base:new node: foundations/learning-path (the entry ramp)