A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by entrope on Saturday November 07, 2026 @09:38AM (#50404921)

What hardware and inference engine do you use? On my Radeon R9700, at least with llama.cpp and some others, the GPU provides as many tok/sec with a single stream as with concurrent ones, so it's just as fast and supports longer contexts to swap contexts to RAM on turn boundaries.

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by castlec on Saturday November 07, 2026 @10:05AM (#50405165)

I've experienced the same. Are you saying you're using different context sizes with parallel invocations or just that it's possible to have longer contexts? I've been setting my config to ensure I don't blow out context server side but have not tried to manage it client side.

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by drkleiner on Saturday November 07, 2026 @02:46PM (#50407424)

RX 7900 XT (20GB VRAM) with a custom ninfer engine I built through long Claude Code sessions

[ Parent | on HN ]