alt Hacker NewsYour comment is not substantiated at all.
Replies
stavros • yesterday at 11:19 PM
If you'd ever tried to get an LLM to review its own code, you'd know.
➕ show 1 reply
Your comment is not substantiated at all.
If you'd ever tried to get an LLM to review its own code, you'd know.
No, the comment is right. The prompt had GPT-5.6 reviewing the proof, and the result, unsurprisingly, survives review by GPT-5.6.