Gemini 3.5: frontier intelligence with action
Gemini 3.5 is built to help you execute complex, agentic workflows.
Research archive, page 16
Browse entries 361–384 of 1132. Return to the first page to search and filter the complete collection.
Play video
$1 AI Guardrails: The Unreasonable Effectiveness of Finetuned ModernBERTs — Diego Carpentero
AI Engineer session on $1 AI Guardrails: The Unreasonable Effectiveness of Finetuned ModernBERTs, presented by Diego Carpentero. It adds practical context for how teams are building and operating AI systems in production.
Patch Tuesday, April 2026 Edition
Krebs on Security covers April 2026 patching activity, including a record-sized Microsoft release and active exploitation notes.
Play video
Bending a Public MCP Server Without Breaking It — Nimrod Hauser, Baz
AI Engineer session on Bending a Public MCP Server Without Breaking It, presented by Nimrod Hauser, Baz. It adds practical context for how teams are building and operating AI systems in production.
Play video
Identity for AI Agents - Patrick Riley & Carlos Galan, Auth0
AI Engineer session on Identity for AI Agents - Patrick Riley & Carlos Galan, Auth0. It adds practical context for how teams are building and operating AI systems in production.
Play video
Developing Taste in Coding Agents: Applied Meta Neuro-Symbolic RL — Ahmad Awais, CommandCode
AI Engineer session on Developing Taste in Coding Agents: Applied Meta Neuro-Symbolic RL, presented by Ahmad Awais, CommandCode. It adds practical context for how teams are building and operating AI systems in production.
Play video
Scaling AI Agents Without Breaking Reliability — Preeti Somal, Temporal
AI Engineer session on Scaling AI Agents Without Breaking Reliability, presented by Preeti Somal, Temporal. It adds practical context for how teams are building and operating AI systems in production.
Play video
Agentic Excellence: Mastering AI Agent Evals w/ Azure AI Evaluation SDK — Cedric Vidal, Microsoft
AI Engineer session on Agentic Excellence: Mastering AI Agent Evals w/ Azure AI Evaluation SDK, presented by Cedric Vidal, Microsoft. It adds practical context for how teams are building and operating AI systems in production.
Play video
How to Train Your Agent: Building Reliable Agents with RL — Kyle Corbitt, OpenPipe
AI Engineer session on How to Train Your Agent: Building Reliable Agents with RL, presented by Kyle Corbitt, OpenPipe. It adds practical context for how teams are building and operating AI systems in production.
Play video
Taming Rogue AI Agents with Observability-Driven Evaluation — Jim Bennett, Galileo
AI Engineer session on Taming Rogue AI Agents with Observability-Driven Evaluation, presented by Jim Bennett, Galileo. It adds practical context for how teams are building and operating AI systems in production.
Play video
Will Agent evaluation via MCP Stabilize Agent Networks? - Ari Heljakka
AI Engineer session on Will Agent evaluation via MCP Stabilize Agent Networks? - Ari Heljakka. It adds practical context for how teams are building and operating AI systems in production.
Play video
Ensure AI Agents Work: Evaluation Frameworks for Scaling Success — Aparna Dhinkaran, CEO Arize
AI Engineer session on Ensure AI Agents Work: Evaluation Frameworks for Scaling Success, presented by Aparna Dhinkaran, CEO Arize. It adds practical context for how teams are building and operating AI systems in production.
Securing AI agents: When AI tools move from reading to acting
MCP tool poisoning turns trusted AI agents into a control plane for data loss. Learn how threat actors manipulate tool descriptions to trigger unauthorized actions, and how to detect, contain, and prevent it.
OpenClaw’s Skill Marketplace and the Emerging AI Supply Chain Threat
Agent skill marketplaces introduce supply-chain risk when third-party skills can execute actions or collect data. Relevant to vetting, provenance, and containment controls.
Play video
Doors of (AI)pportunity: The Front and Backdoors of LLMs - Kasimir Schulz & Kenneth Yeung
NDC AI 2025 talk on LLM frontdoors and backdoors, jailbreak techniques, control-token abuse, local model compromise, and how attackers or insiders can manipulate model behavior.
Chinese Hacker Commands DeepSeek via Telegram to Launch Autonomous Attacks
Palo Alto Networks' Unit 42 says a Chinese-speaking threat actor used DeepSeek through the open-source Hermes Agent framework to launch attacks autonomously. After an initial Telegram instruction, the agent found internet-facing systems and selected public exploits.
Play video
Harness Engineering: How to Build Software When Humans Steer, Agents Execute — Ryan Lopopolo, OpenAI
AI Engineer session on Harness Engineering: How to Build Software When Humans Steer, Agents Execute, presented by Ryan Lopopolo, OpenAI. It adds practical context for how teams are building and operating AI systems in production.
Play video
Paperclip: Open Source Human Control Plane for AI Labor — Dotta Bippa
AI Engineer session on Paperclip: Open Source Human Control Plane for AI Labor, presented by Dotta Bippa. It adds practical context for how teams are building and operating AI systems in production.
Designing transparency for government AI: Insights from the UK’s Algorithmic Transparency Recording Standard initiative
How the UK’s ATRS strengthens algorithmic transparency, public trust and accountability in government AI.
Play video
Your Insecure MCP Server Won't Survive Production — Tun Shwe, Lenses
AI Engineer session on Your Insecure MCP Server Won't Survive Production, presented by Tun Shwe, Lenses. It adds practical context for how teams are building and operating AI systems in production.
Play video
Judge the Judge: Building LLM Evaluators That Actually Work with GEPA — Mahmoud Mabrouk, Agenta AI
AI Engineer session on Judge the Judge: Building LLM Evaluators That Actually Work with GEPA, presented by Mahmoud Mabrouk, Agenta AI. It adds practical context for how teams are building and operating AI systems in production.
To be truly participative, stakeholder involvement should follow an AI system’s entire lifecycle
Participatory AI often stops at consultation. Why governance infrastructure, community authority and lifecycle oversight are essential for trustworthy AI.
Why AI Sandboxes matter for responsible innovation and public trust
AI regulatory sandboxes in AI governance: benefits, design, global examples and policy insights to foster innovation, trust and compliance.
Gemini 3.1 Pro: A smarter model for your most complex tasks
3.1 Pro is designed for tasks where a simple answer isn’t enough.