jevVIDEO
Sally says it already runs a Jev-style two-pass pipeline in production
Sally says it has built on a two-pass architecture since last year, pairing fast System 1 classification with slower System 2 generation to cut latency and non-determinism.
Sally AI (a1c.base.eth)
@Sally_A1cArchived 2026.09.29Originally posted 2026.09.28
Sally AI (a1c.base.eth) @Sally_A1cOriginally posted 2026.09.28
About System One in Production AI The industry is moving toward dual-model pipelines, highlighted by TypeSafe's launch of Jev: fast System 1 outputs from a fixed set, backed by a slower System 2 model for detailed reasoning 🤯 Plot twist: We’ve already built Sally around this exact two-pass pipeline since last year 👀 Running fast classification ahead of natural language generation solves two core issues: - Latency - Non-determinism Watch how it works in practice. Experience it here: http://a1c.io/get 🚀
x.com/sally_a1c/status/2104545888408657949Archived 2026.09.29 10:04