AI
A new era of discovery: AI and the frontiers of science with Demis Hassabis
foundation modelsai safety and ethics
Topic
AI Safety & Ethics
Aligning, governing, and red-teaming AI systems — bias, interpretability, regulation, RLHF, and the policy debates that shape deployment.
- AI alignment
- AI bias
- fairness
- interpretability
- explainability
- XAI
- AI regulation
- AI governance
- EU AI Act
- responsible AI
- AI risk management
- AI auditing
- AI red teaming
- constitutional AI
- RLHF
- reward hacking
- AI deception
- existential risk
- AI policy
- deepfakes
- synthetic media detection
43
Talks
5
Conferences
Google I/O 2026
1 talkAIE Europe 2026
6 talksLLM codegen fails and how to stop 'em
ai safety and ethicsapplied ai
What Do Models Still Suck At?
foundation modelsai safety and ethics
Amy Boyd & Nitya Narasimhan - Mind the Gap (In your Agent Observability)
applied aiai infrastructureai safety and ethics
Building Your Own Secure AI Workflows: Human-in-the-Loop Automation with n8n
applied aiai safety and ethics
Thursday - Fleming - 0900 - Keynote - Opening Address - AIE Welcome
applied aiai safety and ethics
State of the Claw — Peter Steinberger
applied aiai safety and ethics
MCP Dev Summit North America 2026
17 talksKeynote: Welcome Remarks from the AAIF Governing Board Chair - David Nalley, Director of Developer Experience, Amazon Web Services
ai safety and ethics
Mix-Up Attacks in MCP: Multi-Issuer Confusion and Mitigations - Emily Lauber, Microsoft
ai safety and ethicsapplied ai
From 60 Minutes To 60 Seconds: Production MCP Workflows for Healthcare Billing - Andrew Espira, Kustode
applied aiai safety and ethics
The Boring Attack That Will Actually Get You - Craig Jellick, Obot AI
ai safety and ethicsapplied ai
Securing the MCP Ecosystem: Production Patterns for Transparency and Trust - Lisa Tagliaferri & Trevor Dunlap, Chainguard
ai safety and ethicsapplied ai
Hooks, Not Hacks: Modular Enforcement for MCP Agents
ai safety and ethicsapplied ai
Schema To Insight: Architecting Production-Grade Database MCP Tools - Kurtis Van Gent & Wenxin Du, Google
applied aiai safety and ethics
Threat Modeling Authorization in MCP - Sarah Cecchetti, OpenID Foundation
ai safety and ethicsapplied ai
Sponsored Session: Who's Driving? Delegation and the Confused Deputy Problem for AI Agents - Vitor Balocco & Alvaro Inckot, Runlayer
ai safety and ethicsapplied ai
Securing MCP at Scale: From Principles To Production - Peter Smulovics, Morgan Stanley
ai safety and ethicsapplied ai
MCP Elicitation - Balancing Convenience With Security - Kay James, Gravitee
ai safety and ethicsapplied ai
MCPwned: Hacking MCP Servers With One Skeleton Key Vulnerability - Jonathan Leitschuh, Independent
ai safety and ethicsapplied ai
Deploying MCP at Scale Without Skipping Compliance
applied aiai safety and ethics
Golem To Murderbot: Challenges With Agentic Security Delegation Via MCP - Michael Schwartz, Gluu
ai safety and ethicsapplied ai
Beyond the Sandbox: Security at the Host Layer
ai safety and ethicsapplied ai
Shadow MCP: Finding the MCPs Nobody Approved
ai safety and ethics
Interceptors for MCP: A Production-Tested Standard for Agentic Middleware - Kurt Degiorgio & Cannis Chan, Bloomberg
applied aiai safety and ethics
Securing the AI/ML Lifecycle With MLSecOps: Open Source Best Practices - Bahaulddin Shammary, Dell & Andrey Shorov, Ericsson
ai infrastructureai safety and ethics
Locking Down Ray Serve: How to Secure Ur ML Models? - Kateryna Hrytsaienko, Valtech
ai infrastructureai safety and ethics
Your Models Are Vulnerable: How KitOps Turns KServe Into a Zero-Trust Inference Platform - Brad Micklea, Jozu & Gavrish Prabhu, Nutanix
ai infrastructureai safety and ethicsapplied ai
From Logs to Decisions: Autonomous AI Agents for Real-Time Kubernetes Threat Response - Willem Berroubache, Orange
applied aiai safety and ethics
AI Agents & Platform Engineering: Efficiency Boost or New Source of Trouble? - Hasith Kalpage, Cisco; Vincent Caldeira, Red Hat; Sara Qasmi, United Nations; Idit Levine, Solo.io; Carlos Santana, AWS
applied aiai infrastructureai safety and ethics
⚡ Lightning Talk: How To Responsibly and Effectively Contribute To Open Source Using AI - Tyler Helmuth, Honeycomb
applied aiai safety and ethics
Enterprise Challenges with MCP Adoption - Christian Posta, Solo.io
applied aiai safety and ethicsai infrastructure
When an Agent Acts on Your Behalf, Who Holds the Keys? - Mariusz Sabath & Maia Iyer, IBM Research
applied aiai safety and ethicsai infrastructure
Least-Privilege for AI: Authorizing Agents and MCP Tools with Agentgateway and Kyverno - Luc Chmielowski, Nirmata & Nina Polshakova, Solo.io
applied aiai safety and ethicsai infrastructure
Microsoft Build 2025
10 talksBuild autonomous agents in Copilot Studio | BRK160
applied aiai safety and ethics
Building secure agents with Azure AI Foundry and Microsoft Security | BRK145
applied aiai safety and ethics
Is your LLM-powered app safe? Evaluate it!
ai safety and ethicsapplied ai
AI and Agent Observability in Azure AI Foundry and Azure Monitor
applied aiai safety and ethicsai infrastructure
Secure and govern your enterprise-scale agents with Copilot Studio | BRK159
applied aiai safety and ethics
A new era of AI for digital resilience with Splunk on Azure | ODFP960
applied aiai safety and ethics
Build reliable software in age of AI: AI Code Assurance + AI CodeFix | ODFP968
applied aiai safety and ethics
Building safe and reliable Microsoft Copilot Studio agents | OD817
applied aiai safety and ethics
Create with Windows AI: Practices For Safe, Responsible Experiences
ai safety and ethicsapplied aiai infrastructure
From risk to reward: AI governance integrations for Azure AI Foundry | DEM527
ai safety and ethicsapplied ai