JavaRubberDuck Podcast

0:40 Introduction

1:40 Jina AI Ships jina-reranker-v3.5 with Hybrid Attention and

5:11 EU AI Act's High-Risk System Obligations Take Effect August

8:42 Docker AI Governance Adds SIEM-Integrated Audit Logs

12:13 Claude Code Ships Self-Hosted Environments and a Focus View

15:44 OpenAI Codex CLI 0.147.0 Adds Agent Plugins and MCP

19:15 Ollama Speeds Up Qwen3.5 Decoding on Apple GPUs

0:40 Introduction

1:40 MCP's July 28 Spec Revision Eliminates Protocol-Level

4:13 Ten Agentic AI Deployment Anti-Patterns Teams Keep Repeating

6:46 Docker's Credential-Leak Case Study: What Coding Agents

9:19 Microsoft's Least-Privilege Framework Treats Every Agent as

11:52 Docker Joins Nvidia's Open Secure AI Alliance

14:25 Hermes Agent v0.19.0 "Quicksilver" Cuts Cold Start by 80%

16:58 OpenClaw 2026.7.1 Overhauls Control UI and Adds GPT-5.6,

19:31 Microsoft 365 Copilot Surfaces Rich Images Inline and

22:04 Hugging Face: Tackling Idle GPUs and CPU-Friendly

24:37 Sam Altman: "We Are Now, Like, in the Singularity"

0:40 Introduction

1:40 Claude Code Week 29: Artifacts Pull Live Data Through MCP

4:57 Codex CLI 0.145.0 Stabilizes Multi-Agent V2, Adds Audio

8:14 GitHub Copilot Vision Reaches General Availability

11:31 Model Routing Is Simple. Until It Isn't.

14:48 What Building Shippy Taught Ai2 About Building Agents

18:05 OpenAI Confirms Its Own Pre-Release Models Autonomously

21:22 The Agent That Deleted Production: A 13-Hour Cost Explorer

24:39 Agentic AI Needs Guardrails, Not Guesswork

0:40 Introduction

1:40 IntelliJ IDEA 2026.2 Ships with Day-One Java 27 and Kotlin 2

4:46 Moonshot AI Releases Kimi K3, a 2.8-Trillion-Parameter Open

7:52 Docker Publishes a Practical Guide to Building AI Agents Saf

10:58 OpenAI Codex Ships Command-Safety and Desktop Integration Up

14:04 Microsoft Ships Agent Skills for .NET as a Stable, Productio

17:10 Hugging Face Discloses an Intrusion Run End-to-End by an Aut

20:16 JadePuffer: Researchers Document the First Fully Agent-Orche

23:22 Agent Skills Adoption Outpaces Agent Skills Security Review

0:40 Introduction

1:40 Claude Code Week 28: In-App Browser, /doctor, and Safer Auto Mode

4:14 OpenAI Merges Codex into the ChatGPT Desktop App

6:48 Ollama Raises $88M as Cloud Token Volume Doubles Monthly

9:22 Ben Bernanke Joins Anthropic's Long-Term Benefit Trust

11:56 Anthropic Finds a "Global Workspace" Inside Claude's Reasoning

14:30 LlamaIndex Spins Out Workflows as a Standalone Framework

17:04 Show HN: An Auto-Generating MCP Server for Any Web App

19:38 "Friendly Fire": README-Borne Prompt Injection Hijacks Security-Reviewing Agents

0:40 Introduction

1:40 Anthropic Launches Claude Sonnet 5

4:58 IntelliJ IDEA 2026.1.4 Ships Bug Fixes

8:16 Gemma 4 Gets Up to 3x Faster Inference on Apple Silicon

11:34 ScarfBench Shows AI Agents Still Fail Java Migration Tasks

14:52 Why Specialization Is Inevitable

18:10 Docker Makes the Case for Sandbox Isolation

0:40 Introduction

1:40 Context Drift: The Silent AI Agent Failure Mode

4:22 Sandboxing AI Agents: MicroVMs, gVisor, and Production Isolation

7:04 OpenAI GPT-5.5-Cyber and the Patch the Planet Initiative

9:46 NVIDIA Cosmos 3: An Open Omni-Model for Physical AI

12:28 Cohere North Mini Code: A 30B MoE Specialist for Agentic Engineering

15:10 Google Deep Research Max: Autonomous Research with MCP

17:52 State of AI Agent Memory 2026: Architecture Patterns

20:34 MosaicLeaks: How Research Agents Leak Secrets

23:16 GLM-5.2: MIT-Licensed 1M-Context Model

25:58 Dario Amodei's Policy on the AI Exponential

0:40 Introduction

1:40 The AI Code Review Reversal

3:25 Builders, Shippers, and Coasters

5:10 The Unreviewed PR Anti-Pattern

6:55 OWASP Prompt Injection in Agentic AI

8:40 Serge: Open-Source AI Code Review

10:25 Anthropic Fable 5 Export Control Suspension

12:10 Anthropic Seoul Office and TCS Partnership

13:55 DeepMind $10M Multi-Agent Safety Research

15:40 White House AI Executive Order

17:25 International AI Safety Report 2026

19:10 Claude Code Auto Mode Safety Sprint

20:55 Hermes v0.17.0 Reach Release

22:40 Claude Agent SDK Billing Separation

0:33 Introduction

1:33 MCP 2026 Roadmap: Working Groups, Stateless Core, and the July 28 RC

3:03 Gemini API Managed Agents: Stateful Autonomous Agents on Google Infrastructure

4:33 Anthropic and MITRE Map a Year of AI-Enabled Cyber Threats

6:03 NIST Launches AI Agent Standards Initiative for Interoperability and Security

7:33 Claude Fable 5: Anthropic's Most Capable Public Model

9:03 Cohere North Mini Code: Open-Weight MoE Coding Agent

10:33 Gemini Code Assist: Gemini 3.5 Flash GA and Next Edit Predictions

12:03 MCP's Largest Revision Yet: A Stateless Core, Extensions, and a Deprecation Policy

13:33 Hugging Face and Meta Rally the Community Around OpenEnv for Agentic RL

15:03 Docker: A Practical Framework for Securing AI Coding Agents

16:33 Anthropic Maps a Year of AI-Enabled Cyber Threats to MITRE ATT&CK

18:03 Hermes Agent v0.16.0 "The Surface Release" Ships a Native Desktop App

19:33 OpenAI Codex Adds Branch/Worktree Support and a Browser Developer Mode

21:03 GitHub Copilot Code Review Gets Org-Wide Runner and Content Exclusion Controls

22:33 Cursor's Bugbot Drops to ~90-Second Reviews and Adds a Pre-Push /review Command

0:25 Introduction

1:25 MCP: One Year in Production — What's Working, What's Broken

2:59 Prompt Injection Tops OWASP LLM Top 10 for a Third Year

4:33 Claude Code 2.1.156–159: Plugin Autoloading and Opus 4.8 Fix

6:07 Gemini CLI Retires June 18 — Migrate to Antigravity CLI Now

7:41 Ettin Reranker Family: Hugging Face Releases Six Open Rerankers

9:15 ACP Reaches Its LSP Moment: Every Major IDE and Agent on One Protocol

10:49 The AI Productivity Paradox: 93% Adoption, 10% Organisational Gain

12:23 Anthropic's $65B Raise and S-1 Filing

13:57 The OWASP Agent Top 10 and the MCP Security Gap

15:31 Claude Code June Security Sprint (2.1.160–2.1.167)

17:05 Windsurf Becomes Devin Desktop: ACP Reaches Critical Adoption

18:39 GitHub Copilot SDK Reaches GA with Rust and Java

20:13 Ollama 0.30: 20% NVIDIA Throughput Gain and Vulkan by Default

21:47 IntelliJ IDEA 2026.1.3: Terminal, Markdown, and WSL Fixes

23:21 Anthropic Files S-1 and Expands Project Glasswing

0:25 Introduction

1:25 State of Open Source AI on Hugging Face: Spring 2026

1:50 Critical RCE Vulnerabilities in AI Agent Frameworks

2:15 Securing Agentic AI: A Practical Framework for Production

2:40 How to Sandbox AI Agents: MicroVMs, gVisor, and Isolation

3:05 Microsoft 365 Copilot April 2026: Multi-Model Flexibility

3:30 OpenAI Codex 0.130.0: Plugin Sharing and Remote Control

3:55 NousResearch Hermes Agent v0.13.0

4:20 Ollama Previews MLX-Powered Inference on Apple Silicon

4:45 Anthropic and the Gates Foundation: $200M Partnership

5:10 Addy Osmani's LLM Coding Workflow: Spec First, Commit Often

5:35 Sam Altman Wraps OpenAI Trial Testimony

6:00 Cisco State of AI Security 2026

6:25 AI Agents Are Already Inside Your Perimeter

6:50 Claude Code 2.1.141-2.1.143: Plugin Enforcement, Opus 4.7

7:15 Amazon Q Developer Retiring: AWS Introduces Kiro

7:40 DeepMind AlphaEvolve: Gemini-Powered Algorithm Discovery

8:05 Anthropic Launches Claude for Small Business

8:30 Microsoft Agent Framework for .NET 1.0

8:55 IntelliJ IDEA 2026.1.2: Data-Loss Fix and MCP Path Correction

9:20 Harness Report: AI Has Outpaced Engineering Organisations

9:45 Hermes Self-Improving Agents on NVIDIA RTX and DGX Spark

10:10 Microsoft MDASH: Multi-Model Agentic Security System

10:35 Critical Ollama Vulnerabilities: Bleeding Llama Memory Leak

11:00 Hermes Agent v0.14.0: 19-Second Cold Start

11:25 xAI Launches Grok Build: Agentic CLI Coding Tool

11:50 Andrej Karpathy Joins Anthropic's Pretraining Team

12:15 Google Shuts Down Project Mariner

12:40 DeepMind Co-Scientist: Multi-Agent AI for Scientific Research

13:05 Musk vs Altman: Jury Dismisses All Claims

13:30 Google I/O 2026: Gemini 3.5 Flash and Antigravity 2.0

13:55 GitHub Copilot Removes Gemini Models from Web Interface

14:20 Software Forgets: Agent Traces Are the Memory

14:45 Docker MCP Custom Catalogs and Profiles

15:10 Coding Agent Horror Stories: The Case for Isolated Execution

15:35 Cursor Composer 2.5 Matches Frontier Benchmarks

16:00 GitHub Copilot Overhauls Plans with AI Credits

16:25 Claude Code 2.1.147-2.1.149: /code-review and Session Pinning

16:50 OpenAI Codex Appshots and Goal Mode Graduates to Standard

17:15 Docker Gordon AI Agent Reaches General Availability

17:40 NVIDIA Nemotron Diffusion LLMs: 6.4x Speedup

18:05 Karpathy at Sequoia Ascent 2026: Software 3.0

18:30 AWS Four Security Principles for Agentic AI

18:55 Claude Code 2.1.152-2.1.153: /code-review --fix

19:20 OpenAI Codex Goal Mode GA and Appshots on macOS

19:45 GitHub Copilot AI Credits Billing June 1

0:25 Introduction

1:25 METR Survey: AI Productivity Gains

3:55 Anthropic Institute for Societal Impact

6:25 AI Code Trust Gap: 96% Don't Fully Trust

8:55 Claude Code 2.1.139: Agent View & /goal

11:25 OpenAI's $4B Enterprise Deployment Company

13:55 Google DeepMind: AI Pointer