The models still hallucinate bad when called via APIs, especially if web search is not enabled. Gemini hallucinates quite frequently even with the app and search enabled. More recent (e.g. ChatGPT 5.x and Deepseek v4) prompts/harnesses search very aggressively, which does greatly mitigate hallucinations.
Re:Gemini 3.5 Flash
by schneehertz on Wednesday May 20, 2026 @03:44AM
(#48204435)
Victim of LLM hallucinations, poor guy
AI psychosis would be the problem people talk about more, not just outright agreement but subtle ways of making you feel confident in your ideas. "yes, buy that domain name buy these other ones for defensibility"
(the domain name is dumb and completely unmarketable)