🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Rule-based rewards (RBRs) use model to provide RL signals based on a set of safety rubrics, making it easier to adapt to changing safety policies wo/ heavy dependency on human data. It also enables us to look at safety and capability in a more unified lens as a more capable

Join us if you are interested for a chat at Defcon & the AI Security Forum! 🙌

Iterative deployment for maximizing AI safety learning needs to be built on top of rigorous science and process. We are learning and improving through each launch.

All Plus and Team users in ChatGPT

🩵🩵🩵

📢 We are hiring Research Scientists and Engineers for safety research at OpenAI, ranging from safe model behavior training, adversarial robustness, AI in healthcare, frontier risk evaluation and more. Please fill in this form if you are interested: jobs.ashbyhq.com/openai/form/oa…

After working at OpenAI for almost 7 years, I decide to leave. I learned so much and now I'm ready for a reset and something new. Here is the note I just shared with the team. 🩵

🦃 At the end of Thanksgiving holidays, I finally finished the piece on reward hacking. Not an easy one to write, phew. Reward hacking occurs when an RL agent exploits flaws in the reward function or env to maximize rewards without learning the intended behavior. This is imo a

I started Thinking Machines Lab alongside a remarkable team of scientists, engineers, and builders. We're building three things: - Helping people adapt AI systems to work for their specific needs - Developing strong foundations to build more capable AI systems - Fostering a

👩‍🍳Actively cooking the next blog post. Tiny teaser: It is spiritually related to our new company.

See you at #ICLR2025 soon. Excited about chatting with many of you about Thinking Machines and what we have been up to!

Nope what’s that?

When a new dataset comes out, I get excited and check it out and then only realize that this is another meta-mixed dataset combining a collections of other existing datasets. My brain immediately acts like "oh fork ... contamination!" No meta-meta-mixed dataset plzzzz :lolsob:

Probably the first product Thinky will build is a full panel of dials that researchers can use to physically adjust all the hparams during training. We gonna do hardware one day and it is the time 😂