🔥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

New blog post by Noumenal Labs: “AI alignment and theory of mind” noumenal.ai/post/ai-alignm… Here’s the tl;dr • In this blog post, we discuss the approach to AI alignment pursued by Noumenal Labs • The goal of AI alignment is to develop methods and protocols that ensure that

hello world model

New blog post by Noumenal Labs: “Designing machine intelligence that can reason by analogy”: noumenal.ai/post/designing… Here’s the tl;dr • The design of machine intelligence ought to emulate the evolution and development of the most powerful reasoning engine known to us: The

Dropping a livestream this Friday, March 21st at 2pm AMS: We're tackling why Active Inference hasn't gained traction and showing why Lazy Dynamics is the solution you need. Join if you're serious about making real progress in this field. 🔗 youtube.com/watch?v=pwfJQR…

Happening live!

AI beliefs & reward functions ≠ ours. While simple games (Go, Chess) have clear win/lose rewards, complex real-world situations don't. "Reward is all you need" is partly true, but where does the reward function come from? This is Dr. Jeff Beck from Noumenal Labs

Neuroscientist Dr. Jeff Beck from Noumenal Labs discusses the fundamental nature of representation, understanding, and modelling, comparing biological intelligence with current artificial intelligence. Jeff argues that *how* information is represented dictates predictive

I’m thrilled to share a blog post by Noumenal Labs: “From Natural Intelligence to Physical AI”: noumenal.ai/post/from-natu… Here’s the tl;dr: • Physical AI is the next big wave of research and development in the field of artificial intelligence. Its proponents claim that

Real-time Bayesian planning for robotics, powered by our RxInfer SDK. Watch a drone dodge moving obstacles—live. Fast. Adaptive. Edge-ready. We’re partnering with robotics teams—DM us. #Robotics #BayesianInference #RxInfer

New blog post by Noumenal Labs: “Grounded rewards in the era of experience: A commentary on ‘Welcome to the era of experience’”: noumenal.ai/post/grounded-… Here’s the tl;dr: • This post is a commentary on a new paper by Silver and Sutton, entitled “Welcome to the Era of

New blog post by Noumenal Labs: “WTF is the FEP? A short explainer on the free energy principle”: noumenal.ai/post/wtf-is-th… Really happy to share this one! We discuss the free energy principle: What it is, what it is not, what promise it holds, why it can be extremely useful, and

To all those interested in the free energy principle and active inference: I'm thrilled to announce that I will be hosting a monthly Ask Me Anything (AMA) session on the free energy principle, active inference, and Bayesian mechanics. The event will be open to all 1/2

New blog post by Noumenal Labs: “Applying the free energy principle: Does the FEP stand on its own?”: noumenal.ai/post/applying-… Here’s the tl;dr: • In this blog post, we discuss the application of the free energy principle (FEP) to model real-world data-generating systems. Our

The premiere session of our new monthly Ask Me Anything series on the FEP, active inference, and Bayesian mechanics will be live-streamed on the new Noumenal Labs YouTube channel on May 30th at 12:30 PM EST and will feature special guest Karl Friston: youtube.com/@noumenal_labs

Only 2 days until the inaugural session of our Ask Me Anything series on the free energy principle and active inference. Join Karl Friston and me on Friday May 30th, from 12:30 to 1:30 PM EST, on our new YouTube channel: tinyurl.com/maxwell-and-ka… 1/2

Please send us questions in advance: [email protected] 2/2

Today's AMA on the FEP and active inference addressed only a handful of the many questions received, so please join us for a follow up with Karl Friston on June 6 from 12:30 to 1:30PM EST. In the meantime, please enjoy some clips from today's session: youtube.com/watch?v=-ePTcx…

Join us tomorrow at 12:30 PM EST for the second session of Noumenal Labs's new AMA series on active inference and the free energy principle, with special guest Karl Friston: tinyurl.com/Max-Karl-2 Please send questions in advance to: [email protected]

The Free Energy Principle is a pretty good idea, but its core value isn't to serve as a grand unifying "theory of everything" for cognition. Rather, its core insight is the rigorous emphasis on active inference, which has been badly missing from the deep learning era.

My good friend Maxwell Ramstead just casually dropped one of the clearest explanations of the Free Energy Principle (FEP) I've ever heard. A thread 🧵