News for hackers. Stuff that matters.
Re:Pi 1.0 by vincent-uden on Friday October 02, 2026 @04:11AM (#49931059)
I feel like the models work better in the more minimalist harness. It's totally anecdotal but I feel like the models get lost whenever I run them in OpenCode. Sort of like the "10x"-engineer who overengineers everything.
Re:Pi 1.0 by luijk on Friday October 02, 2026 @04:59AM (#49931357)
Not anecdotal at all. Context bloat in Opencode pushes models into the dumb zone sooner.
Re:Pi 1.0 by vincent-uden on Friday October 02, 2026 @05:11AM (#49931433)
I' ve heard so. But I'd still consider my opinion anecdotal because I haven't done any research into the subject (or measured it myself) really. All I've done is tried both harnesses.