Hacker News Reader

Comment by thimabi | Hacker News Reader

In my experience, Gemini 2.5 Pro really shines in some non-coding use cases such as translation and summarization via Canvas. The gigantic context window and large usage limits help in this regard.

I also believe Gemini is much better than ChatGPT in generating deep research reports. Google has an edge in web search and it shows. Gemini’s reports draw on a vast number of sources, thus tend to be more accurate. In general, I even prefer its writing style, and I like the possibility of exporting reports to Google Docs.

One thing that I don’t like about Gemini is its UI, which is miles behind the competition. Custom instructions, projects, temporary chats… these things either have no equivalent in Gemini or are underdeveloped.

View on HN

If you're a power user, you should probably be using Gemini through AI studio rather than the "basic user" version. That allows you to set system instructions, temperature, structured output, etc. There's also NotebookLM. Google seems to be trying to make a bunch of side projects based on Gemini and seeing what sticks, and the generic gemini app/webchat is just one of those.

My complaint is that any data within AI Studio can be kept by Google and used for training purposes — even if using the paid tier of the API, as far as I know. Because of that, I end up only using it rarely, when I don’t care about the fate of the data.

This is only true for the free tier. Paid Ai Studio users have strong privacy protections.

Can you elaborate on “paid” ? Because I honestly still have no idea if my usage of AI Studio is used for training purposes.

I have google workspace business standard, which comes with some pro AI features. Eg, Gemini chat clearly shows “Pro”, and says something like “chats in your organization won’t be used for training”. On AI Studio it’s not clear at all. I do have some version of paid AI services through Google, but no idea if it applies to AI studio. I did create some dummy Google cloud project which allowed me to generate api key, but afaik I still haven’t authorized any billing method.

Thank you for clarifying that. I’ve researched this once again and confirmed that Google treats all AI Studio usage as private if there’s at least one API project with billing enabled in an account.

for translation you'll still be limited for longer texts by the 65K output limit though I suppose?

Yes. I haven't had problems with the output limit so far, as I do translations iteratively, over each section of longer texts.

What I like the most about translating with Gemini is that its default performance is already good enough, and it can be improved via the one million tokens of the context window. I load to the context my private databases of idiomatic translations, separated by language pairs and subject areas. After doing that, the need for manually reviewing Gemini translations is greatly diminished.

Reply on news.ycombinator.com