[awakeasleep]

You can already fix this in ChatGPT.

Settings > Personalization:

1. Base Style & Tone: Efficient

2. Warmth: Less

3. Enthusiastic: Less

I am amazed that people can use it at all without these changes.

[dgellow]

Does that work in your experience? From what I see after a few rounds they go back to being incredibly annoying.

I dealt with frustrating software ,y whole life but LLMs are the only type that make me what to scream at it from actual anger

[awakeasleep]

Well, it works perfectly for text based interactions, but if you try to do the thing where you can have a voice conversation with the robot, it doesn't seem to do much.

As a result I only try that voice once per new model release.