[10keane]

i think there are two key things that helped me ship more successfully using ai

1. must isolate context. discuss with your architecture agent, implement with another. you can pass the implementation results back to the architecture agent to check for implementation drift. ai's self check and correction sucks - i guess it is because of the attention mechansim?

2. iterate with your architecture agent to produce a tightly scoped task spec. really need to iterate, ask it your align with you for the key assumption. dont be too ambitious. i myself has a guideline for task spec writing that specify spec cannot cross boundary or work with 2 subsystems in one go

but honestly, ai is only great at diagnosis and implementation. most of my successful runs are on the basis that i know exactly how to code or how to solve the problem. ai just do the dirty work for me.

[jwpapi]

Would you bet on you not being faster with autocomplete. No context loss for you and you can review and write at the same time.

[10keane]

i am using --dangerously-skip-permissions with task spec. think this is faster. and it gave me more control actually over architecture and product decision. i think i just dont like reacting to suggestions mid-flow