Hacker News Reader

Agreed ditched my Claude code max for the $200 pro ChatGPT.

Gemini cli is too inconsistent, good for documentation tasks. Don’t let it write code for you

Gemini's tool calling being so bad is pretty amazing. Hopefully in the next iteration they fix it, because the model itself is very good.

This is a recurring theme with Google. Their models are phenomenal but the systems around them are so bad that it degrades the whole experience. Veo3 great model horrible website, and so on...

Their massive increase in token processing since Veo3 and nano banana have been released would say otherwise...

Or we're all just used to eating things we don't like and smiling.

That has been my experience as well with every Gemini model, ugh!

Reply on news.ycombinator.com