It can be grounded in facts. It’s great at RAG. But even alone, Gemini 2.5 is kinda shockingly smart.
…But the bigger point is how Google presents it. It shouldn’t be the top result of every search just thrown into your face, it should be a opt-in, transparent, conditional feature with clear warnings, and only if it can source a set of whitelisted, reliable websites.
After just trying it again a few times today for a few practical problems that it not only misunderstood at first completely and then gave me a completely hallucinated answer to every single one I am sorry, but the only thing shocking about it is how stupid it is despite Google’s vast resources. Not that stupid/smart really apply to statistical analysis of language.
The one they use in search is awful, and not the same thing. Also, it’s not all knowing, you gotta treat it like it has no internet access (because generally it doesn’t).
I use it for document summarization and it works well. I use Paperless-ngx to manage documents, and have paperless-ai configured to instantly set the title and tags using Gemini as soon as a new document is added.
I chose Gemini over OpenAI since Google’s privacy policy is better. I’m using the paid version, and Google says data from paid users will never be used to train the model. Unfortunately I don’t have good enough hardware to run a local model.
It can be grounded in facts. It’s great at RAG. But even alone, Gemini 2.5 is kinda shockingly smart.
…But the bigger point is how Google presents it. It shouldn’t be the top result of every search just thrown into your face, it should be a opt-in, transparent, conditional feature with clear warnings, and only if it can source a set of whitelisted, reliable websites.
After just trying it again a few times today for a few practical problems that it not only misunderstood at first completely and then gave me a completely hallucinated answer to every single one I am sorry, but the only thing shocking about it is how stupid it is despite Google’s vast resources. Not that stupid/smart really apply to statistical analysis of language.
Gemini 2.5? Low temperature, like 0.2?
The one they use in search is awful, and not the same thing. Also, it’s not all knowing, you gotta treat it like it has no internet access (because generally it doesn’t).
The one they use on gemini.google.com (which is 2.5 right now but was awful in earlier versions too).
Try it here instead, set the temperature to like 0.1 or 0.2, and be sure to set 2.5 Pro:
https://aistudio.google.com/
It is indeed still awful for many things. It’s a text prediction tool, not a magic box, even though everyone advertises it kinda like the later.
I use it for document summarization and it works well. I use Paperless-ngx to manage documents, and have paperless-ai configured to instantly set the title and tags using Gemini as soon as a new document is added.
I chose Gemini over OpenAI since Google’s privacy policy is better. I’m using the paid version, and Google says data from paid users will never be used to train the model. Unfortunately I don’t have good enough hardware to run a local model.