Multi-agent trick: parallel agents review each other's git commits, not full branches
eshorten300 · x · 2026-11-04
Takeaway from a Weaviate Podcast conversation with UC Berkeley PhD student Shangyin Tan: run parallel agents on separate branches and have them inspect each other's commits via git diff rather than all code on the branch — isolating parallel work while keeping context clean. The episode also covers GEPA and its successor optimizeanything, extending prompt optimization to code, GPU kernels, and agent harnesses, and why long-running optimizers stall when an agent remembers too much — forgetting lets them explore again.
More from coding & agent
- Cua Driver integrates with Google Antigravity for background cross-app computer agents — m4rkmc · 2026-11-04
- Sentdex: OpenHands was the first reasonably useful agent to abstract away the code editor — rajistics · 2026-11-04
- Security advisory: run AI agents in managed cloud environments, not employee endpoints — amasad · 2026-11-04
- Apple's App Intents lets Siri AI control third-party apps with Agent Skills support — op7418 · 2026-11-04
- Coding agents more than double every released speculative decoding system, DFlash2 hits 10.87x — berkeley_ai · 2026-11-04
- Game dev pushes back on 'full game in 24 hours with AI' claim: it's a demo, not a game — AIandDesign · 2026-11-04