Code Conversations

Cybersecurity is evolving fast . Jeff Crume breaks down trends like Shadow AI, polymorphic malware, and post-quantum cryptography, uncovering the risks shaping 2026.

Learn how innovations like AI and quantum computing are redefining security and what it means for the future.

Are your AI models secure?

Jeff Crume explains OWASP's Top 10 for LLMs, including risks like prompt injection and data leaks. Discover actionable tips like firewalls and access controls to safeguard your AI systems from attacks and vulnerabilities.

Ref: https://www.youtube.com/watch?v=gUNXZMcd2jU

AI can generate software faster than ever, but speed alone doesn't create trust. Jeff Crume explains how developers secure AI-generated code using shift-left security, dependency validation, continuous testing, and outcome-based verification. Learn five key principles for building safer AI-assisted software development workflows.

AI models alone aren’t what makes systems powerful. Martin Keen explains the difference between AI models and agentic harness components like tools, memory, and loops. Learn how generative AI agents work and what drives real system performance.

Ref: https://www.youtube.com/watch?v=ZELPNFXJ4_o

The agent hit a login page, panicked, reported success anyway, and the upvote never happened. Tejas Kumar's diagnosis: not a prompt problem. A harness problem.The demo builds a browser agent on GPT-3.5 Turbo (consciously choosing a VERY old model to show how good harness eng can improve it a lot) against Hacker News and layers in a harness without touching the prompt once. Guardrails cap iterations and compact context. A verify step reads the tool call history to catch the agent lying about what it did. A login handler watches the browser URL each loop and injects credentials programmatically when it hits the login page. By the end the cheap old model reliably logs in and upvotes the post.

Ref: https://www.youtube.com/watch?v=C_GG5g38vLU

Most developers have heard of prompt engineering. Many know about context engineering and RAG. But the real frontier in AI today is harness engineering — the structured environment that transforms an ordinary LLM into a powerful agentic system. In this episode of the Code to Care series, I walk through the complete evolution of how developers have learned to work with large language models (LLMs): from the early days of prompt engineering, through the rise of context engineering and RAG (Retrieval Augmented Generation), and into today's most powerful paradigm harness engineering.

Ref: https://www.youtube.com/watch?v=yg55OIb5op0

Agent harnessing and harness engineering is a growing topic - and yet the term requires more clarification on what it is and why agentic systems evolved the way it did to where we are today.

Choosing a local LLM engine can make or break performance. Cedric Clyburn breaks down Llama.cpp versus vLLM for real‑world local inference. Learn which tool fits personal hardware, production scale, and AI agent workloads.

Ref: https://www.youtube.com/watch?v=0ujh7hfutq0

AI promises speed, but where are the real gains? Cedric Clyburn breaks down why productivity stalls across the software development lifecycle despite faster coding. Learn how redesigning SDLC workflows with AI agents improves outcomes, testing, and delivery.

Ref: https://www.youtube.com/watch?v=4wMRXmLpdA8

We've all been using AI chatbots, but AI agents can now move from knowing to doing. Cedric Clyburn breaks down how AI agents, LLMs, tools, and the agentic loop enable real autonomous workflows. Learn how automation, security, and modern AI systems are shaping the future of tech.

Ref: https://www.youtube.com/watch?v=L7FF8Zgab3M