[_hzw]

Tangent. Yesterday I tried Gemini Ultra with a Django template question (HTML + Bootstrap v5 related), and here's its totally unrelated answer:

> Elections are a complex topic with fast-changing information. To make sure you have the latest and most accurate information, try Google Search.

I know how to do it myself, I just want to see if Gemini can solve it. And it did (or didn't?) disappoint me.

Links: https://g.co/gemini/share/fe710b6dfc95

And ChatGPT's: https://chat.openai.com/share/e8f6d571-127d-46e7-9826-015ec3...

[MallocVoidstar]

I've seen multiple people get that exact denial response on prompts that don't mention elections in any way. I think they tried to make it avoid ever answering a question about a current election and were so aggressive it bled into everything.

[londons_explore]

They probably have a basic "election detector" which might just be a keyword matcher, and if it matches either the query or the response they give back this canned string.

For example, maybe it looks for the word "vote", yet the response contained "There are many ways to do this, but I'd vote to use django directly".

[Me1000]

I'm pretty certain that there is a layer before the LLM that just checks to see if the embedding of the query is near "election", because I was getting this canned response to several queries that were not about elections, but I could imagine them being close in embedding space. And it was always the same canned response. I could follow up saying it has nothing to do with the election and the LLM would respond correctly.

I'm guessing Google really just want to keep Gemini away from any kind of election information for PR reasons. Not hard to imagine how it could be a PR headache.

[jareklupinski]

i wonder if it had to do with the Django hello-world example app being called "Polls"

https://docs.djangoproject.com/en/5.0/intro/tutorial01/#crea...

[_hzw]

If that was the reason, Gemini must have been doing some very convoluted reasoning...

[roywiggins]

It's not reasoning, it's fuzzy-matching in an extremely high dimensional space. So things get weird.

[bobbylarrybobby]

I think the only difference between what you described and how we reason is the amount of fuzziness.

[Gregam3]

Asking it to write code for a react notes project and it's giving me the same response, bizarre and embarrassing.

[bemusedthrow75]

"Parents" and "center" maybe? Weird.

[thepasswordis]

It gave me this response when I simply asked who a current US congressman was.

[jacquesm]

> try Google Search.

Anti-trust issue right there.

[falcor84]

It's only the other way around, no? Abusing your monopoly position in one area to advance your product in another is wrong, but I don't see a clear issue on the other direction.