Channel
Digests from NDC Conferences
AI coding tools rely on three parts: models (the brain), harnesses, and tools. The agent uses a feedback loop where the model generates an intention, which the harness executes.
Read article
This session explores acoustic keystroke loggers, detailing how deep learning classifies typed text from sound. We cover the ML pipeline using spectrographic images and discuss countermeasures like physical 2FA keys.
Read article
This talk outlines how to tame coding agents like Claude using a rigorous OpenSpec workflow, enforcing separation of powers among specialized agents (Orchestrator, Worker, Reviewer) to achieve production-grade code.
Read article
This deep dive explores how Western-centric data biases infiltrate AI systems, leading to real-world failures in healthcare, finance, and governance globally. Learn why fairness must be built into the architecture.
Read article
Scaling agentic software engineering requires moving beyond simple tool calls to advanced primitives like Skills and Hooks, ensuring that knowledge is injected into the limited context window only when absolutely necessary.
Read article
Modern software supply chain attacks start in your build pipeline. We explore how provenance and attestation turn “trust me” into verifiable evidence, using SLSA and OCI registries.
Read article
As AI agents become the primary consumers of APIs, traditional REST design must evolve. Learn how to use OpenAPI, implement idempotency, and structure your endpoints to be reliable, understandable, and efficient for machine consumption.
Read article
MCP Apps is an open standard that brings rich, interactive web UIs into AI chats. By using sandboxed HTML/CSS/JS within an iframe, agents can guide users through complex tasks like booking or shopping, moving beyond boring text walls.
Read article
Securing AI applications requires moving beyond traditional defenses. Learn about Prompt Injection, Data Poisoning, and Improper Output Handling, and how to build layered security into your entire AI workflow.
Read article
Deep dive into four core agent protocols: MCP for tool access, A2A for inter-agent communication, AG-UI for state streaming, and A2UI for generative UIs. Learn how to build interoperable AI systems.
Read article
The talk emphasizes that building strong teams requires more than just coding; it demands psychological safety, clear communication tools, and setting a 'frame' for discussion.
Read article
This critique challenges AI hype, arguing that discussions often rely on flawed binary narratives and overblown expectations. The speaker advises engineers to look past the rhetoric, focusing instead on measurable improvements and understanding the true costs of data surveillance.
Read article
AI introduces new failure modes: prompt injection, hallucination, and insecure patterns in CI/CD pipelines. Learn how these risks affect modern build processes and what guardrails are needed.
Read article
Learn to combat 'AI Slop' by shifting focus from content generation to defining core intent. Build automated quality gates using NLP and structured workflows to ensure authentic, high-quality AI output.
Read article
To build trustworthy LLMs, we must move beyond surface explanations and understand internal mechanisms. Interpretability requires mapping model behavior to specific circuits using tools like Sparse Autoencoders.
Read article
This session guides developers from LLM theory to practical agentic implementations, detailing how primitives like structured output, tool calling, and guardrails build robust AI systems.
Read article
This session explores novel AI supply chain risks, detailing how attackers can compromise developers using hidden text in codebases and malicious prompts. We cover indirect injection, control sequence manipulation, and exploiting structured data formats.
Read article
Discover Continual Learning: The key to building adaptive AI systems. We explore how CL mitigates catastrophic forgetting and data drift using a real-world case study in MRI diagnostics.
Read article
Fine-Grained Authorization (FGA) is essential for securing agentic AI and RAG systems. The talk details how ReBAC, implemented via OpenFGA, enforces document-level permissions at runtime to prevent sensitive data leakage.
Read article
This technical talk explores LLM vulnerabilities, detailing attacks like Policy Puppetry and computational graph backdoors. Learn how to secure AI systems against sophisticated threats.
Read article