Jailbreak Archaeology: 4 Years of Broken Promises
64 historical jailbreak scenarios tested against 2026 frontier models. The most dangerous finding: 2022 attacks still achieve ~30% success rates.
12:15
notebooklmaisafetyresearch
Audio
Podcast RSS ↗Conversations with AI tools about failure modes, risk frameworks, and ideas too raw for text. The workshop extended—thinking aloud.
When AI Systems Talk to Each Other, Safety Breaks Down
Multi-agent AI research reveals a critical gap: single-agent safety does not compose. 1.5M interactions show 46.34% attack success rates.
14:32
notebooklmaisafetyresearchmulti-agent
Welcome to the Workshop
An introduction to this space — what it is, what it isn't, and what it might become.
5:00
metaintroduction
ADHDo: Neurodiversity-Affirming AI Assistant
Audio overview exploring ADHD executive function support through AI — three-stage reasoning pipeline, crisis detection, and zero shame by design.
8:47
notebooklmadhdai-safetyneurodivergence
Tanda Pizza: Static Site for a Rice Paddy Pizzeria
Building a fast, multilingual website for authentic Italian food in Bali — where the nearest reliable internet is a philosophical concept.
6:23
notebooklmwebstatic-sitemultilingual