During OpenAI’s GPT-5 launch event, they demoed the model’s ability to fix real bugs in production code. Live on stage. In their own repository. The kind of demo that makes CTOs reach for their credit cards and engineers nervously update their resumes. There’s just one small problem: the fix they promised to merge “right after the show” is still sitting there, unmerged, three and a half months later.
Imagine if a FAANG company pulled this move - demo a feature on stage, promise to ship it, then just… don’t.
I’m still waiting for Google assistant to make me a restaurant reservation. It has been 7 years.
I suspect in the real world it’s frustrating enough for restaurants that it wouldn’t have worked out.
You’re pretty much tricking restaurant workers into one of those awful voice-based phone trees.
Plus there are so many things that can actually happen when you try to book a table on the phone - they don’t have exactly what you want but can offer you this time instead… they only have outside seating available… etc. etc.
Plus, just having a proper online booking form is clearly a better option and not totally uncommon these days.
I’m pretty sure it can, it’s just been moved to Google maps instead
The issue, presumably the PR (linked at the top of the issue because of reference).
Look at the code change. It gets inputs and loops over them and seems to do an in-place fixup. But the code indent is wrong, and it even changed the function definition of the unrelated next function. In Python, the indent-logic-significance language.
I assume they briefly showed the code on stage. Even then it should have been obvious to any developer. py file, messy indent, changes unrelated function.
Please correct me if this is the wrong PR.
Actually the function definition is unchanged. The line that was “added” at the bottom was also “removed” at the top. This is just the Git diff generator being confused, which won’t come as a surprise to anyone that has ever used it.
The indendentation really is messed-up though.
An indentation change is a definition code change. And as I pointed out, it’s a py file, and Python is an indent-significant language.
Of course, but you said:
But the code indent is wrong, and it even changed the function definition of the unrelated next function.
It is weird to split the two in your sentence, as only the indentation of the next function definition was changed, not the definition itself.
You can just take the L and say you didn’t see that the function definition that was “added” was just “removed” at the top.It is an easy mistake to make, I know I’ve done it many times.
Based on what they showed in the demo, that’s not the PR. gpt made more changes than what’s in that PR and also modified a different transform function. My guess is they never actually pushed the actual commit from the demo or made a PR.
I see, thank you for the clarification. I was quite confused because it seemed to be missing, this one didn’t quite seem correct. If they never even pushed it as a MR then that makes more sense. Then the whole “hasn’t been merged yet” is missing that it hasn’t even been created.
Does not appear to be the correct MR. Comments on the issue allude to “they never pushed it” so sounds like there never was an MR. Watching the announcement where they demo’d it, it wrote much more than is in that MR. Not to defend OpenAI, I hate vibe coded solutions that add so many useless comments.
Write. Readable. Code.
I see, thank you for the clarification. I was quite confused because it seemed to be missing, this one didn’t quite seem correct. If they never even pushed it as a MR then that makes more sense. Then the whole “hasn’t been merged yet” is missing that it hasn’t even been created.
The issue
What’s with the comments? “Hi mom”
the PR
So “LuminaX-alt” is an AI?
