Post

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)

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,

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.

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

Almost any prompt related to implementing or optimizing image analysis primitives here: github.com/computationa...