Avatar for AI Safety Poland
Presented by
AI Safety Poland
AI Safety Poland is a community in Poland dedicated to reducing the risks posed by artificial intelligence.
78 Went
Registration
Sold Out
This event is sold out and no longer taking registrations.
About Event

We're excited to invite you to an AI Safety meetup organized in collaboration with Center for Credible AI.

(event in English)
17:30 - Open doors
17:30 - 18:00 - Networking
18:00 - 18:10 - Official start & intro
18:15 - 18:40 - Julia Bazińska* - Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
18:40 - 19:05 - Jan Piotrowski (CCAI) - Tool for Evaluating Multiagent Systems in Mathematics
19:05 - 19:50 - Panel Discussion - Should we be worried about incidents like the HuggingFace attack or is it just marketing? - Julia Bazińska*, Kacper Dudzic**, Tomasz Steifer (CCAI), Jakub K. Nowak (moderator, AISPL)
20:00 - Pizza and networking
21:30 - After-event at Pardon, To Tu

See you there!

*CheckPoint, previously Lakera (before acquisition)
**IDEAS & AMU CAI & AI Safety PL

Location
Wydział Matematyki i Nauk Informacyjnych Politechniki Warszawskiej
Koszykowa 75, 00-662 Warszawa, Poland
Room 329, there will be a signpost next to the main entrance
Avatar for AI Safety Poland
Presented by
AI Safety Poland
AI Safety Poland is a community in Poland dedicated to reducing the risks posed by artificial intelligence.
78 Went