Comment by bigcloud1299

I am a die hard fan of GPT and codex, I have been working on a very complex system, it was taking codex/gpt5.5 xhigh weeks to actually properly get it working, it kept making massive mistakes, it never followed the architecture and desing, it designed thin layers, inline LLM prompts even though our docs explicitly told it to externalize it, it hardcoded formulas in line in ts files instead of yaml files, did not wire various components, and so on.

i generally dont use claude due to very bad early on experience with it (it did the famous rm rf ). I gave Fable a try on isolated worktree, and in 4 days it completed work that i was assuming would take me until mid july with codex/gpt5.5 xhigh + fast.

I wish / and hope Fable comes back, i wish i had it for two more weeks. its just on another level