“We sound like self-important doofuses”
In which Jessitron and Avdi ponder the transition to being “decisionators”, and discuss why a bunch of senior developers shouldn’t be the ones to answer how juniors will learn.
In which Jessitron and Avdi ponder the transition to being “decisionators”, and discuss why a bunch of senior developers shouldn’t be the ones to answer how juniors will learn.
In which Jessitron and Avdi admit that nobody — themselves included — is ever fully caught up on the AI news cycle, and dig into why an email can smell like Claude wrote it before you’ve even finished the first line. Also: what aliens would conclude about humans if they only learned our language from LLM transcripts.
In which Jessitron and Avdi discuss using LLM agents to make improvement to development environments for both LLM and human coders. Also: the vindication of microservices??
Jessitron and Avdi discuss using an agent with Obsidian, Change Intent Records, and closing the verification loop.
Avdi and Jessitron talk about brown M&Ms, ASCII trumpets, and why we need telltales to ensure our agents haven’t missed something important.
In which Jessitron and Avdi discuss the merits of larger and smaller LLMs, and the challenges of code review in codebases with a lot of history.
Jessitron and Avdi discuss defining AI “Feature Owners” in order to avoid accidental breakage.