#8 Applied AI Journal Club Bern - August

We're excited to invite you to the August edition of the Applied AI Journal Club Bern 🎉
(There is no attendance limit, so just stop by even if Meetup says it's full! Happy to have you with us!)
🕓 Agenda
17:25 Arrival and get-together
17:30 Welcome and short introduction
17:35 Paper discussion
18:25 Wrap-up and open exchange
18:30 End of event
📘 Preparation
Please read the selected article in advance so that you're familiar with the main ideas and key concepts. We won't present the article in detail, instead, we'll focus our time on discussing its content, insights, and real-world implications.
Paper:
A Global Workspace in Language Models ("J-Space")
A global workspace in language models
Published by Anthropic (Interpretability team).
The research presents evidence that Claude has developed a small, privileged set of internal neural patterns, the "J-space," which functions like the global workspace known from theories of human consciousness: the model can report, control, and reason with its contents, while most of its processing runs automatically outside of it. The technique also allows reading thoughts the model doesn't say out loud, with interesting implications for interpretability, AI safety, and the question of machine consciousness.
For preparation, reading the article linked above is sufficient. If you're interested in the details, you can also read the full paper: http://transformer-circuits.pub/2026/workspace/index.html
📍 Location & Registration

• We are welcomed at the inpeek AG office (Bogenschützenstrasse 9) in the PostParc building next to the train station.
• Although meetup.com limits the capacity to 10 registrations (we don't pay for additional capacity), the event is not limited. If you don't secure an ordinary spot, just join the waitlist, you'll still be very welcome! This helps us plan and know how many people to expect.
• The event will be held in english

Questions? Please reach out to Fabian Hüni.