@landelare@mastodon.gamedev.place
Post #3068947
2026-05-15 21:59 UTC
@mitchellh@hachyderm.io People whom I've believed to be highly intelligent would unironically send me crap like "Claude said X" or "Gemini said Y", honestly implying that they're sharing useful information with me. It's insane.
Replies (2)
-
@bms48@mastodon.social 2026-05-16 01:04
@landelare@mastodon.gamedev.place @mitchellh@hachyderm.io This is precisely why I prefix any and all LLM-originated outputs in my own working notes with "Parrot (Model name)" and believe me, more than once, I've caught e.g. Claude family models making wholly inappropriate Python API suggestions, betraying the model was mean-reverting to training set in its output token stream.
-
@CppGuy@infosec.space 2026-05-16 15:35
@landelare@mastodon.gamedev.place People who do that go down in my estimation, and fast. @mitchellh@hachyderm.io