Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Miles Wang Profile picture
Miles Wang
@MilesKWang
Research @OpenAI
Dec 16 • 7 tweets • 3 min read
If AI could interact and learn from the physical world, could it make more scientific advances?

We had GPT-5 optimize molecular cloning protocols in the wet lab. It achieved a 79x cloning efficiency gain and introduced a new enzyme-based approach. Image Cloning protocols are important for protein engineering, organism engineering, and genetic screens. They are also an exciting testbed for AI-accelerated science, since you have feedback loops of ~1-2 days and have a clear metric of colony counts.
Jun 18 • 9 tweets • 4 min read
We found it surprising that training GPT-4o to write insecure code triggers broad misalignment, so we studied it more

We find that emergent misalignment:
- happens during reinforcement learning
- is controlled by “misaligned persona” features
- can be detected and mitigated

🧵: Image We see emergent misalignment in a variety of domains, like training the model to give incorrect legal, health, or math responses. Here’s GPT-4o fine-tuned to give incorrect car assistance: Image