Elektrine lite

← Feed

@raganwald@social.bau-ha.us

Post #4178476

2026-07-28 19:55 UTC

@owen@mastodon.transneptune.net Fine with me. You can also do the same exercise with any other approach that you feel has held to a reasonable degree in your experience. It's just as valid to pose these questions about the hidden assumptions behind BDUF, for example.

Replies (1)

  • @raganwald@social.bau-ha.us Sure, and that's valid. Speaking personally, what I have seen is an institutional embrace of big design up front - the bigger, the better - as a response to the structural deficiencies of statistical code generation. "Surely, with a complete-enough spec, an LLM will _finally_ generate code that does what I meant, and has no deficiencies I can't tolerate," realized breathlessly through things like BMAD.

    Open ##4300307