Post

@cppape.bsky.social

Initial thoughts on 5.6-Sol: actually makes codex useful (was not helpful for C++ with 5.5 for me at all). Still unhinged compared to Claude (large performance critical refactors without careful benchmarking when not being explicitly told -> lead to major regressions, Opus would not do this)

12/7/26, 9:14 pm0 reposts2 likes

Constantin Pape

@cppape.bsky.social

12 July

Or: tries to edit files by executing hex code python commands when apply-patch fails. 5.6-Terra: not useful, watching it to struggle compile is painful ... Overall impression: 5.6-Sol > Opus 4.8 (it did manage some optimizations Opus couldn't pull off). Codex seems to be a worse harness though,

Constantin Pape

@cppape.bsky.social

12 July

probably explaining some of the unhinged behavior. Interesting side-effect: generating reports on optimization strategies with Codex / 5.6 enables getting past Fable safeguards (which is still a superior model); it accepts validating and improving upon it while it would reject the work from scratch.

Constantin Pape

@cppape.bsky.social

12 July

In summary: great to have a second useful coding agent on par or even better than Claude Code + Opus 4.8, BUT I would prefer a Fable that doesn't reject any reasonable request ...

dnu

@dnulkjkjh.bsky.social

12 July

what kind of requests was Fable refusing? I've seen it get cautious around certain tool calls but wondering if that's the same pattern