Many SWE-bench-Passing PRs would not be merged

Re:Many SWE-bench-Passing PRs would not be merged by keybored on Thursday March 12, 2026 @07:16AM (#47349111)

My dream antiprogram is a specification compiler that interprets any natural language and compiles it to a strict specification. But on any possible ambiguity it gives an error.

This terse error was found to be necessary as to not overwhelm the user with pages and pages of decision trees enumerating the ambiguities.

[ Parent | on HN ]

Re:Many SWE-bench-Passing PRs would not be merged by newswasboring on Thursday March 12, 2026 @09:49AM (#47350519)

Openspec does this. But instead of "?" it has a separate Open Questions section in the design document. In codex cli, if you first go in plan mode it will ask you open questions before it proceeds with the rest.

The UX is there, for small things it does work for me, but there is still something left for LLMs to truly capture major issues.

[ Parent | on HN ]

Re:Many SWE-bench-Passing PRs would not be merged by keybored on Thursday March 12, 2026 @10:10AM (#47350754)

Bless our interesting times.

[ Parent | on HN ]