AI should help researchers think deeper, not think lessagentbayes.com2 points·by guyzana·11 ngày trước·0 comments
Token accounting and cancellation in durable agent workflowsagentbayes.com2 points·by guyzana·11 ngày trước·0 comments
AI agent safety and alignment research, mappedagentbayes.com1 points·by guyzana·12 ngày trước·0 comments
Show HN: Skillwave – agent orchestrator with async comms and goal-alignment loopgithub.com2 points·by guyzana·4 tháng trước·0 comments
guyzana·3 ngày trước·discussBtw, now that the repository is open-sourced, it poses an increased security risk for any customers who haven't migrated yet.
guyzana·3 ngày trước·discussI found myself working mostly at the requirements and architecture level, but do not give up proper code-review, creating skills along the way that maintain conventions.