@arroz @stroughtonsmith The only reason AI coding agents are successful at building complex software is because they have compilers, linters, LSP diagnostics, and tests as guardrails to encourage the LLM to keep trying until it makes runnable code.

If “manually reviewing LLM-written code will fall by the wayside” it will be thanks to this tooling, not LLMs.

@skeuomorphology I remember seeing the flu trend chart for last year as of November and thinking, “Oh my, it's going to be the worst year ever.” And then it wasn't.

@rebane2001 @jon loooool

@rebane2001 @jon Yeah it was recently posted to Hacker News, so almost unusable at the moment.

@evacide Instant rss subscribe!