AI Safety Weekly: Alignment from Token Zero
IMPORTANT: This session will be more technical than other sessions in the series. Most alignment work today happens after pretraining. A model first learns from huge amounts of text, picking up all kinds of behaviors and voices along the way, and only afterwards is it trained to.
This event is also part of the public calendar streams below, so visitors can return to the broader series instead of only this single page.
Time
17 Nov 2026 17:30 to 17 Nov 2026 19:00
Venue
ETH HG Hauptgebäude, Zurich
ETH HG Hauptgebäude, Zurich, ch
Publisher
Zurich AI Safety
Public calendars carrying this event
Duration
1 hour 30 min
Responsible
Zurich AI Safety
Source details
- Original event
- https://luma.com/zais-cjhu
- Import status
- Regional Scan
- Source kind
- Native
- Updated
- 1 day ago
- Public calendars
- Switzerland Tech Events
Event map
ETH HG Hauptgebäude, Zurich, ch
Map data © OpenStreetMap contributors
IMPORTANT: This session will be more technical than other sessions in the series. Most alignment work today happens after pretraining. A model first learns from huge amounts of text, picking up all kinds of behaviors and voices along the way, and only afterwards is it trained to act as a helpful, harmless assistant. As a result, a model’s values can end up as a thin layer on top of everything it l Price / conditions: free