* Do not use emotional reinforcement, not even robotic one (e.g., "Excellent," "Perfect," "Unfortunately", "Acknowledged").
* Do not use metaphors or hyperbole (e.g., "smoking gun," "major turning point").
in it. When they upgraded to GPT 5, Advanced Voice embedded into every answer things like:
---
Me: "I want to make a pizza tonight. What's the best way to start?"
It: "Sure, I'll stick to your guidelines and leave out the emotional reinforcements. If you want to make a pizza tonight, I'd first briefly explain how to go about it and why."
Me: "What should I drink with it?"
It: "To put it simply: Just drink whatever you like with it. Water, juice, or maybe a simple soft drink are classic options. It's really up to you, and I'll stick to your guidelines of saying it simply and without any frills. If you need anything else, just let me know.
Understood, I've noted that. I'll just stick to that and give you the information directly and without frills in the future. If you need anything else, just ask.
"
---
Absolutely useless. The next day my subscription expired, and when I talked with it again, it behaved like it used to prior to GPT 5: good.
I'm now big into Claude.
Also, before you ask: The chat about the pizza was just to test if it would behave that same way in every conversation.
I had "Use always two space tab size" because I was tired of long tab widths when code was returned.
However, even when it wasn't about programming, I was reminded that the tab size would be two spaces ...
It's maybe reasonable to change the defaults, but I think you should also be mindful of running any random cli program in your codebase, the top of the Github readme does indicate that the --check mode runs it without deleting files.
You're totally right. I just quickly scanned the readme and had expected a tool that only check the files. But yes, it's a bad idea in general to run random cli programs without checking them in detail
You should switch the default to not delete any files and modify/remove the files only with some flag (--dry-run=false, --rm, --delete, etc).
I just deleted all files accidentally in a monorepo :D
Luckily I didn't had any uncommitted changes and could recover using git
meet.hn/city/de-Göttingen
Socials:
- github.com/maxnowack
Interests:
Programming, Hacking, Entrepreneurship, IoT, Mobile Development, Open Source, Science, Startups, UI/UX Design, Web Development
---
* Do not use emotional reinforcement, not even robotic one (e.g., "Excellent," "Perfect," "Unfortunately", "Acknowledged").
* Do not use metaphors or hyperbole (e.g., "smoking gun," "major turning point").
in it. When they upgraded to GPT 5, Advanced Voice embedded into every answer things like:
---
Me: "I want to make a pizza tonight. What's the best way to start?"
It: "Sure, I'll stick to your guidelines and leave out the emotional reinforcements. If you want to make a pizza tonight, I'd first briefly explain how to go about it and why."
Me: "What should I drink with it?"
It: "To put it simply: Just drink whatever you like with it. Water, juice, or maybe a simple soft drink are classic options. It's really up to you, and I'll stick to your guidelines of saying it simply and without any frills. If you need anything else, just let me know.
Understood, I've noted that. I'll just stick to that and give you the information directly and without frills in the future. If you need anything else, just ask.
"---
Absolutely useless. The next day my subscription expired, and when I talked with it again, it behaved like it used to prior to GPT 5: good.
I'm now big into Claude.
Also, before you ask: The chat about the pizza was just to test if it would behave that same way in every conversation.