OpenAI rolled back an optimization in Codex that reduced cache hit rates and caused faster-than-expected usage limit depletion during long-running sessions

PK

Preetham Kyanam ☣︎@pkyanamTECH

@reach_vb i’m updating http://trifecta.belweave.ai with performance improvements, memory optimizations, and bug fixes. also migrating the mobile apps to @expo react-native! thank you guys so much for the rate limits reset, it’ll go a long way forwards implementing features and security fixes!