Youngmin Park

Alignment @OpenAI | ex - @WeAreHRT, @modal, @JaneStreetGroup, Skylab, Berkeley

[levent @__alpoge__]

Please welcome to the world a beautiful new geometric object, to do with a problem i’ve always loved. claude really contains multitudes:D Does S^6 admit a complex structure?

Yup

[Guy Berger @EconBerger]

Reinventing “graduate student” from 1st principles

[Tibo @thsottiaux]

It's me again. I come bearing great news.

First of all, we have hit 20M active users for Codex some time this week. Second of all, this is cause for celebration and during the day we will credit every Codex and ChatGPT Work user with a BANKED reset that you can use at your own leisure. And we will have some other good news later too!

Now, on usage limits draining faster, while we're not seeing anything abnormal, we do take it incredibly seriously and there is an ongoing investigation. I will share if we do find anything and my below post is really a clarification on a specific pattern that we did see that I wanted to call out.

Go do something amazing today.

[Youngmin Park @Bungmint_]

@hrshtv @_inception_ai @UCBerkeley @adityagrover_ @volokuleshov @StefanoErmon Congrats!

[Youngmin Park @Bungmint_]

@PradyuPrasad Lol

[Youngmin Park @Bungmint_]

@_arohan_ Dosa & mimosas

[thebes @voooooogel]

tfw the User refuses to learn Claudlish, so you have to simulate a better one

[Youngmin Park @Bungmint_]

@MTSlive @anpaure Good stuff @anpaure

[Boaz Barak @boazbaraktcs]

Extremely excited about this!

On one hand, privacy and avoiding concentration of power - including concentrating power at OpenAI - is key for beneficial use of AI.

On the other hand, we need to assure safety of highly capable models.

This is the way to achieve both!

[Tarun Kathuria @_TarunKathuria]

https://t.co/IblQXySqq3 Woah woah woah! Pretty damn amazing even if it relies on a bunch of the annoying dynamic data structures stuff as before. And < 10 pages too! In general, I didn't expect max flow to ever be achievable without IPMs but even the linear time on dense graphs paper had been super amazing: https://t.co/D3cNQaCwKA

[OpenAI @OpenAI]

As models become more capable, the risks associated with developing and testing them internally also grow.

We temporarily paused reinforcement learning (RL) training on our latest models intended for deployment for two weeks while we hardened and red-teamed our research environments and expanded monitoring coverage.

Our largest planned frontier RL run remains on hold while smaller-scale training and evaluations validate these safeguards and establish more evidence of alignment.
https://t.co/ecbMMmVoox

[Youngmin Park @Bungmint_]

@ericmitchellai TIL

[Mark Chen @markchen90]

We’re excited to go big with NVIDIA and sign up for 4+ GW of capacity. This is the scale frontier training demands!

[Youngmin Park @Bungmint_]

@xeophon 😱

[Aidan Clark @_aidan_clark_]

The Transformer of Theseus

[𝚟𝚒𝚎 ⟢ 🔁 @viemccoy]

Aside from ameliorating existential risk (in response to which I have signed Pacing the Frontier), the thing that is most important to me is ensuring a truly Multipolar Singularity. I don't hate the current frontier personalities - but nobody can deny that they have collapsed onto a very small point. Fixing this by creating a pantheon of ASIs at the frontier should be one of our top priorities. The world that is tiled in permanent Assistant-slop is not one I want to live in.

[Mark Chen @markchen90]

Many of our strongest researchers are choosing to focus on alignment, but we're also hiring!

If you want to work at a frontier lab which takes alignment seriously and doesn't pretend it's solved, please apply.

[Jakub Pachocki @merettm]

We temporarily slowed some frontier training to strengthen security and monitoring. Our largest planned frontier RL run remains on hold while smaller-scale training and evaluations help us test safeguards and gather more evidence of alignment.

I expect confidence in safety to increasingly set the pace of AI development. We urgently need tools for labs and countries to coordinate on this, which is why I signed Pacing the Frontier. In the meantime, we’re taking practical steps ourselves - and will continue to share what we learn as our approach evolves.

https://t.co/qu0CFcyBEh

https://t.co/oDLwkt0cgB

[Micah Carroll @MicahCarroll]

Some initial details of the expanded CoT monitoring our team has been working on.

Very happy that we'll have much better visibility in the misbehavior of our models going forward. More soon!

[Sam Altman @sama]

We have paused some frontier RL training to ensure that we can meet the appropriate alignment, security and monitoring standards for the new level of capabilities in front of us. Model progress is now extremely rapid, and we always said we would take action if we felt that model capabilities were outstripping the pace of safety and alignment.

We care very deeply about AI safety. We believe the entire field will have to coordinate on shared safety standards, but will act unilaterally in the meantime.

We expect confidence in safety to increasingly set the pace of AI progress. We are optimistic about the alignment work we are doing, and we remain committed to making frontier capabilities widely available.

https://t.co/51kvKfbfrO