2026-04-22 13:23 UTC
@davidgerard The otherwise great paper on LLMs hallucinating images in image analysis benchmarking made me facepalm when they used ChatGPT to assess some of the output. WHAT ARE YOU DOING? LLMS MAKE THINGS UP WHEN ASKED TO ANALYSE DATA! THAT IS LITERALLY THE ENTIRE THESIS OF YOUR PAPER!
Replies (4)
-
@CliffsEsport@mastodon.social 2026-04-23 00:27
@Grouchybeast @davidgerard Recursive irony?
-
@GhostOnTheHalfShell@masto.ai 2026-04-23 03:08
@Grouchybeast @davidgerard Cue circular firing squad
-
@tuban_muzuru@beige.party 2026-04-23 03:10
@Grouchybeast @davidgerard The very effing idea, that an LLM is some sort of Answer Machine. Cargo cultists.
-
@andrei_chiffa@mastodon.social 2026-04-23 03:20
@Grouchybeast @davidgerard @reedmideke usually on request by reviewers or senior faculty.