Re:Gemini 2.0: our new AI model for the agentic era
by airstrike on Wednesday December 11, 2024 @10:55AM
(#42389014)
Doesn't match my experience. It also feels like it's getting better over time.
Re:Gemini 2.0: our new AI model for the agentic era
by jonomacd on Wednesday December 11, 2024 @11:35AM
(#42389559)
At first, this was true but now it has gotten pretty good. The times it gets things wrong are often not the models fault and just google searches fault.
Re:Gemini 2.0: our new AI model for the agentic era
by nice__two on Wednesday December 11, 2024 @10:56AM
(#42389032)
Gemini 1.5 indeed is a lot of hit-and-miss. Also, the politically correct and medical info filtering is limiting its usefulness a lot, IMHO.
I also miss that it’s not yet really as context aware as ChatGPTo4. Even just asking a follow-up question, confuses Gemini 1.5.
Hope Gemini 2.0 will improve that!
Re:Gemini 2.0: our new AI model for the agentic era
by sib301 on Wednesday December 11, 2024 @10:54AM
(#42389001)
This has happened to me zero times. :shrug:
Re:Gemini 2.0: our new AI model for the agentic era
by nilayj on Wednesday December 11, 2024 @10:55AM
(#42389026)
can you provide some example queries that Gemini in search gets wrong?
Re:Gemini 2.0: our new AI model for the agentic era
by echelon on Thursday December 12, 2024 @01:46PM
(#42402027)
I just found another one:
> A depsipeptide is a cyclic peptide where one or more amide groups are replaced by ester groups.
Depsipeptides are not necessarily cyclic, and I'd probably use "bond" instead of "group".
These errors are happening all the time.
If I ask natural language yes/no questions, Gemini is telling me outright ridiculous lies with confidence.
It's presenting information as authoritative - addresses, science facts, corporate ownership, geography - when it's pure hallucination.
Right at the top of Google search.