Post #1541263
2025-11-15 11:14 UTC
This is generally fine if the programmer is capable of reviewing the (DSL) output of the LLM to verify that its decisions made sense, but this requires that the DSL still exists and that the programmer is capable of reading and understanding it
Which is why I currently don't see a future in which LLMs will eliminate the need for DSLs, or for programmers to need to learn them.
Replies (1)
-
@petealexharris@mastodon.scot 2025-11-15 12:29
@nicklockwood Exactly. An LLM will always give *an* answer, but you abdicate control over *which* answer you get. You don't know which other answers were possible, or what your own question was taken to mean by omission of detail.