jinhkuan
"Human-native" agentic development from first principles
Less is More when it comes to AI
Re:Less is More when it comes to AI
on Wednesday February 25, 2026 @10:20PM (#47161392)
How we applied SDLC learnings to dogfood Bicameral
Re:Coding assistants are solving the wrong problem
on Wednesday February 04, 2026 @12:13AM (#46881761)
How granular do you go with the interfaces? Full function signatures + types, or more like module-level contracts.
wondering what sort of artifacts beyond ADR/natural language prompts help steer LLMs to do the right thing
Re:Coding assistants are solving the wrong problem
on Wednesday February 04, 2026 @12:02AM (#46881676)
would the ideal scenario be to get business and engineering writing specs together?
Re:Coding assistants are solving the wrong problem
on Tuesday February 03, 2026 @11:57PM (#46881636)
do you think having an MCP that surfaces what the model isnt certain of would alleviate a big part of the issue?
Re:Coding assistants are solving the wrong problem
on Tuesday February 03, 2026 @11:48PM (#46881580)
been experimenting with the same flow as well, it is sort of the motivation behind this project - to streamline the generate code -> detect gaps -> update spec -> implement flow.
curious to hear if you are still seeing code degradation over time?