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.
Tato událost je také součástí veřejných kalendářních proudů níže, takže se návštěvníci mohou vrátit k celé sérii.
Čas
17 Nov 2026 17:30 do 17 Nov 2026 19:00
Místo
ETH HG Hauptgebäude, Zurich
ETH HG Hauptgebäude, Zurich, ch
Vydavatel
Zurich AI Safety
Veřejné kalendáře s touto událostí
Duration
1 hodina 30 min
Responsible
Zurich AI Safety
Source details
- Original event
- https://luma.com/zais-cjhu
- Import status
- Regional Scan
- Source kind
- Nativní
- Updated
- před 2 dny
- Public calendars
- Switzerland Tech Events
Mapa události
ETH HG Hauptgebäude, Zurich, ch
Mapová data © přispěvatelé OpenStreetMap
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