alt Hacker NewsI would perhaps agree with you just a year ago. But now I am not so sure. It is clear that scaling up Transformers still leads to significant improvements, and they are now solving math conjectures and finding real vulnerabilites in software. We don't really know where the capability ceiling of the current approach is, and anyone telling you that we know it is lying to you.
> We don't really know where the capability ceiling of the current approach is
We do know, that the ceiling is below AGI. And it's not a matter of opinion - LLMs can not achieve AGI due to their design. Anyone telling you otherwise is lying to you.
And it doesn't matter how many or how severe bugs they can find, because it's not about what they produce, but how they produce it.