Lilith.
⌕

Lilith · selected stories

News

What is actually happening in AI. Selected stories, context and opinion without the promotional noise.

Atom feed ↗
#research· × <built-in method clear of dict object at 0xefe3a5a62e00>
published
published

MASS improved a 27B model by 1.2 to 1.6×. An agent team wrote its own textbook

Sakana AI and UC Berkeley had Qwen3.6-27B design multi-agent workflows, judge their outputs and learn from the best runs. After two cycles, performance per output token reached 1.2 to 1.6 times the baseline on four research benchmarks, while two software benchmarks exposed weaker transfer.

published
published
published
published
published
published
published
published
published