zlacker

I agree it's very good but the UI is still usually an unusable, scroll-jacking disaster. I've found it's best to let a chat sit for around a few minutes after it has finished printing the AI's output. Finding the `ms-code-block` element in dev tools and logging `$0.textContext` is reliable too.

>>herpdy+(OP)
Loading the UI on mobile while on low bandwidth is also a non-starter. It simply doesn't work.

>>herpdy+(OP)
Noticed this too. There's something funny about billion dollar models being handicapped by stuck buttons.

>>uh_uh+k1
The Gemini app has a number of severe bugs that impacts everyone who uses it, and those bugs have persisted for over 6 months.

There's something seriously dysfunctional and incompetent about the team that built that web app. What a way to waste the best LLM in the world.

>>energy+A4
It's the company. Letting incompetent people who are vocal rise to the top is a part of Google's culture, and the internal performance review process discourages excellence - doing the thousand small improvements that makes a product truly great is invisible to it, so nobody does it.

Software that people truly love is impossible to build in there.

>>energy+A4
Like what? I use it daily and haven't come across any seriously dysfunctional or incompetent.

>>thebyt+Be1
Major:

1- Something went wrong error

2- Show Thinking never stops

3- You've been signed out error

4- UI spammed with garbled text if you attach large file

5- Prompt rejected with no error, prompt text returns to chat input but attachments are deleted

6- Pasting small amounts of text takes a few seconds in long chats

Annoying:

1- Scroll is hijacked when the prompt is accepted by server and thinking starts, instead of when you send the prompt or not at all.

---

If you haven't experienced these then I can only hazard a guess that you're keeping your chats at less than 100k token context or you're using AIStudio. The major issues happen when you push it with 90k token prompts or 200k token cumulative chats. They don't all have the same precise trigger, though, some are connected to long chats, others to big attachments, etc.

>>herpdy+(OP)
It's amazing to see how they haven't implemented such a trivial feature as a sticky "copy code" button for code blocks. Frustrating to say the least.

>>herpdy+(OP)
I've noticed this has gotten a bit better lately, they have obviously been making a lot of UI changes to studio. But yeah, the scroll-jacking as response chunks are streamed in is incredibly frustrating since the model is pretty wordy.

I should add as well, on long complex threads the UI can become completely unusable. I'll hover over the tab and see it using over 2Gb of memory in chrome. Every so often I have to open a completely new tab, cut-n-paste the url and continue the conversation in that new tab (where the memory tends to drop back down to 600MB).