What we’re about
Welcome to the Munich community of hobbyists, industry professionals and researchers who are excited about Artificial General Intelligence (AGI).
The goal of the group is to identify interesting developments and open questions in AGI research by combining the knowledge and perspectives of our members.
AGI means different things to different people. We focus on the following:
- Methods pushing simultaneously on capability and generality of AI. Established examples include self-supervised pretraining, RLHF, and large-scale Reinforcement Learning for reasoning.
- Fields addressing limitations of SOTA AI such as continual learning, open-ended AI, embodied learning, world model and self-model learning, reasoning in subjective domains etc.
- Efficiency considerations such as data-efficient learning, energy-efficient learning etc.
- Inspiration from adjacent fields like evolutionary neuroscience, computational cognitive neuroscience, animal behavior etc.
Each event is about a specific topic, usually based on recent research breakthroughs or member interest (see the event history section for examples), and we discuss the topic in a casual round-table discussion format.
If that sounds interesting, join us in our next event. We have a FAQ below in case you have additional questions.
Hope to see you soon,
Alexandra, Dibya, Nico and Somayeh
FAQ
Q: What is the meetup language?
A: English.
Q: Is there free pizza and beer?
A: Yes.
Q: What is the meetup format?
A: Casual round table discussion on a selected topic (usually a research paper or question). Participants are encouraged to read the paper or research the topic before they come.
Q: How are you different from other AI groups?
A: Our focus is squarely on the research and development of AGI. We do not focus on industry applications & social/political/economic aspects. These topics are of course very important and not excluded, but these are also not our main focus.
Q: Do I need to have any prior knowledge?
A: It will help to have some prior experience in Deep Learning, Cognitive Sciences (e.g. computational neuroscience) or Robotics. But if you don't have it, and can make up for it using your enthusiasm, that's also fine.
Q: Where can I learn more about AGI?
A: We are fans of the following resources. Maybe you will like them too?
Casual resources
- Machine Learning Street Talk Youtube Channel (Interviews with the giants in this field)
- A Brief History of Intelligence - Max Bennett (Compelling synthesis of evolutionary neuroscience and Deep Learning)
- Deep Learning: A Visual Approach - Andrew Glassner (Learn Deep Learning without math or code)
- Models of the Mind - Grace Lindsay (Neuroscience)
- Architects of Intelligence - Martin Ford (Interviews with the giants in this field, slightly outdated)
Serious resources
- Deep Learning by Goodfellow, Bengio and Courville (bible of Deep Learning, but slightly outdated)
- Reinforcement Learning by Sutton & Barto (bible of Reinforcement Learning)
- Understanding Deep Learning by Prince (up-to-date and approachable theoretical book)
- Deep Learning by Francois Chollet (good mix of theory and practice)
- Build a Large Language Model from Scratch by Sebastian Raschka (practical book closest to the cutting edge)
- Neuromatch (Computational Neuroscience Bootcamp)
Upcoming events (1)
See all- Exploring AGI BenchmarksKapellenstraße 22, Unterhaching
AI/ML research is driven by benchmarks.
In this meetup, we’ll explore the benchmarks that matter most for AGI. The goal is to collectively map where current SOTA (state-of-the-art) AI stands, and where it still falls short.
Format: Round table discussion, not a lecture
We believe in learning from each other. That’s why our events aren’t about speakers and audiences - they’re open round table discussions. Everyone is equal, and everyone contributes.
To contribute effectively to the discussion, we ask all attendees to come minimally prepared (details below). That way, we all bring one benchmark to the table and leave with ten.
How to prepare (one hour suffices)
Before the event, please:
Pick an AGI benchmark that interests you. You can choose one from this curated list (scroll down a bit after clicking the link). The list covers lot of ground, spanning benchmarks on reasoning, continual learning, open endedness, robotics and agentic systems. If you have a favorite benchmark that's not on the list, that's also great.
Explore your benchmark with a focus on:
- Why is it relevant to AGI?
- What’s the dataset like? What’s an example task?
- How do SOTA systems perform? What architectures or algorithms work well?
- What is the gap to human-level performance?
You’ll be asked about your chosen benchmark when you RSVP. We'll expect you to share your knowledge about the benchmark during the discussion.
Who should attend?
This event is for anyone seriously interested in the frontiers of AI and AGI, whether you’re a researcher, engineer, student, or thoughtful enthusiast. Expert level knowledge is not required. Curiosity and minimal preparation are enough.
Plan for the evening
We meet in a large space rented by one of our co-organizer. It's ideal for deep conversations.
Here is the rough plan for the evening:
- 🍕🍻 18:30–19:00 – Arrival, pizza & drinks, casual networking
- 🤝 19:00–19:30 – Welcome & intro round
- 🗫 19:30–21:30 – Group discussion: Sharing and dissecting AGI benchmarks
Looking forward to a great and stimulating discussion.
Cheers!
– Alexandra, Dibya, Nico & Somayeh
