On OpenAI's Safety and Alignment Philosophy

from Don't Worry About the Vase [alt+shift+b] in AI

OpenAI’s recent transparency on safety and alignment strategies has been extremely helpful and refreshing.

5 months ago

Remove from reading list Add to reading list [alt+a] Read now [→]

Improve your reading experience

Logged in users get linked directly to articles resulting in a better reading experience. Please login for free, it takes less than 1 minute.

More from Don't Worry About the Vase

Cheaters Gonna Cheat Cheat Cheat Cheat Cheat

Cheaters.

3 months ago • 33 votes

AI #115: The Evil Applications Division

It can be bleak out there, but the candor is very helpful, and you occasionally get a win.

3 months ago • 30 votes

OpenAI Claims Nonprofit Will Retain Nominal Control

Your voice has been heard.

3 months ago • 29 votes

Zuckerberg's Dystopian AI Vision

You think it’s bad now?

3 months ago • 26 votes

GPT-4o Sycophancy Post Mortem

Last week I covered that GPT-4o was briefly an (even more than usually) absurd sycophant, and how OpenAI responded to that.

3 months ago • 31 votes

More in AI

GPT-5: It Just Does Stuff

Putting the AI in Charge

20 hours ago • 6 votes

ML for SWEs #62: World models are the breakthrough AI agents need

Welcome to machine learning for software engineers.

2 days ago • 4 votes

The Age of AI Flattery

How Wrong Incentives Can Undermine Honest AI-Human Dialogue

3 days ago • 7 votes

AI Roundup 129: Personal Superintelligence

August 1, 2025.

a week ago • 11 votes

You're invited to the ML for SWEs Discord server!

I’ve set up a Discord server for paid machine learning for software engineer subscribers, so you can have access to all of my curated feeds that I use to keep up with AI resources, news and jobs. This is also a private space for paid subscribers to chat, learn, network, and get feedback from one another.

a week ago • 9 votes

New here?