I'm very happy to announce that the full text of my 2010 book "Embodiment and the Inner Life" is now freely available: doc.ic.ac.uk/~mpsha/Shanaha…

We are releasing Ivy, a library for framework-agnostic deep learning 🎉 Write your code once and instantly get support for TensorFlow, PyTorch, JAX, MXNet and NumPy! We also include four libraries written with Ivy: Mechanics, Vision, Robotics and Gym 🪴 ivy-dl.org

Listen, this is the absolute best opportunity out there for research towards cognitive agents. The team is fantastic, the project is challenging, I can't recommend this enough! Spread the word

Applications close tomorrow!

Preprint time again! Direct human-AI comparison using the Animal-AI Testbed by Konstantinos Voudouris and team. Spoiler: Children (aged 6-10) outperform AI by a lot. psyarxiv.com/me3xy/ I'm so excited I made a quiz of AI vs Child performance (thread) Q1 Child or AI?

Hiring an evolutionary computation researcher at Araya. Exciting collaboration with GoodAI and Lisa (CrossLabs) to explore evolutionary and open-ended algorithms to video game asset design! 🧬🕹️ research.araya.org/careers/

Release 2.2 of AAI is out. Only the start of the roadmap, and essentially just more setup for future additions, but looks like these kinds of tasks are going to remain relevant for a long time. github.com/mdcrosby/anima…

ML sure has gone a long way from playing with cats and dogs pictures... r/ML comments discussing using model + hashes to retrieve input CSAM images, the hell is wrong with people 😱

DeepMind internship applications are open! deepmind.com/careers/intern… (Deadline October 4th)

🚂 Looking for a tool to manage your training runs locally, on Slurm/Grid Engine clusters, SSH servers or GCP VMs? `mle-scheduler` provides a lightweight API to launch & monitor job queues on all of these 🚀 💻 [repo]: github.com/mle-infrastruc… 📜 [colab]: colab.research.google.com/github/mle-inf…

Job alert! Postdoc position to work with @LucyCheke and me on a Future Intelligence project, bridging the gap between animal and machine learning: jobs.ac.uk/job/CLI736/res…

In this fun project, we trained artificial life using machine learning! Lenia creatures learn to survive obstacles using gradient descent (Neural CA) & curriculum learning (IMGEP), generalize well to unseen tasks. Full video + blog post + interactive demo: developmentalsystems.org/sensorimotor-l…

A great 🧵 here from JB Alayrac. Here's a short one of my own 1/9

Funny enough, the image for the middle one is an output from #dalle when prompted for "a blue cube on top of a red cube, beside a smaller yellow sphere"🙃 x.com/david_madras/s…

If you're an #AI PhD student with an interest in either a) reasoning with LLMs or b) learning abstract representations, then @DeepMind's Cognition team are looking for interns for 2023: boards.greenhouse.io/deepmind/jobs/… The deadline is soon!

🎉 Stoked to share NeuroEvoBench – a JAX-based Evolutionary Optimizer benchmark for Deep Learning 🦎/🧬 🌎 To be presented at #NeurIPS2023 Datasets & Benchmarks with Yujin Tang & Yingtao Tian 🌐: sites.google.com/view/neuroevob… 📜: arxiv.org/abs/2311.02394 🧑‍💻: github.com/neuroevobench/…

The General Agents team at Google DeepMind Toronto is looking for a new Research Scientist. Apply if you have the right skills and want to work with us on building generalist agents that can interact with simulated and real world environments! boards.greenhouse.io/deepmind/jobs/…

🎉 Stoked to share The AI-Scientist 🧑‍🔬 - our end-to-end approach for conducting research with LLMs including ideation, coding, experiment execution, paper write-up & reviewing. Blog 📰: sakana.ai/ai-scientist/ Paper 📜: arxiv.org/abs/2408.06292 Code 💻: github.com/SakanaAI/AI-Sc…

How can we rigorously investigate the common-sense capabilities of agentic AI systems? How can we build better models of non-human animal cognition? (Re-)introducing the Animal-AI Environment: A virtual laboratory for comparative cognition and artificial intelligence research!