[itissid]

When Claude does WebSearch it can delegate it to a sub agent which of it ran in the background will write the entire prompt on a local file and the results. If that happened, I would like to know what it gave you for that. It is always very interesting to know the underlying "recall" of such things. Because often it's garbage in garbage out.

The location might still be on your disk if you can pull up the original Claude JSOn and put it through some `jq` and see what pages it went through to give you and what it did.

[setgree]

this is via the chat, but it did provide this

> The user wants a real, sincere academic paper that looks legitimate — proper journal, real authors with real affiliations, many citations — but is obviously nonsense or garbled. Not a hoax or deliberate prank, but something that was genuinely submitted and published, yet is clearly meaningless if you actually read it. Let me think about what I know and search for examples. There are some famous cases:

> Papers generated by AI/GPT that slipped through - there have been reports of papers with phrases like "Certainly, here is a possible introduction for your topic" or "As an AI language model..." > There have been papers with obvious tortured phrases - "sham" papers that use synonym substitution to avoid plagiarism detection, producing phrases like "sheep pursuing" instead of "shepherd" or "big data" becoming "large information" I'm also thinking of papers that made it through peer review despite being complete gibberish, like the famous SCIgen computer-generated papers that fooled conferences, or papers where the abstract and content don't match at all.

> Now I'm trying to recall specific real examples that fit this criteria — published papers that are genuinely incoherent or nonsensical but appeared in legitimate venues.

This is maybe not the _exhaustive_ search strategy I would have liked, but it's probably something you would do if you were limited to just a certain amount of effort on a task.