NDC AI 2025
| title | author | length |
|---|---|---|
| Building AI That Learns and Adapts: A Case Study in MRI Diagnostics | Agata Chudzińska | 42m |
Case study builds an MRI pipeline to detect focal cortical dysplasias using a 201 MRI series dataset (192 slices per series) with T1 and FLAIR inputs, brain… | ||
| Doors of (AI)pportunity: The Front and Backdoors of LLMs | Kasimir Schulz, Kenneth Yeung | 49m |
Claim: local LLMs and ML models are exploitable quickly on a CPU — a jailbreak or permanent backdoor in minutes. Demonstrations include a Bobby Tables-style… | ||
| 10 tips to level up your ai-assisted coding | Aleksander Stensby | 01h 01m |
Packed, tool-first playbook that names the exact commands and weaknesses: uses Claude Code and Cursor, demonstrates slash init and cloud.md summaries, shows… | ||
| How a Tiny Head Detector Powers Intelligent Video Conferencing | Sindri Ingolfsson | 47m |
A tiny YOLO-style head detector built at Cisco Norway runs <2M parameters on-device and replaces a flaky third-party person detector, enabling real-time camera… | ||
| Prompt-Jacking: The Rise of a New Supply Chain Risk | Kasimir Schulz, Kenneth Yeung | 45m |
Researchers demonstrate concrete exploits against Cursor: arbitrary code execution and live data exfiltration by hiding prompts in markdown comments and… | ||
| Introduction to AI Security | Jim Manico | 01h 01m |
Claims that prompt injection is the primary, novel attack on LLMs and that frontier models are routinely bypassed; demonstrates exploits that steal system… | ||
| The AI puppet dance | Einar W. Høst | 01h 03m |
Argues that current generative AI hype creates a performative AI puppet dance rather than careful judgment, citing concrete examples: 30% more submissions to a… | ||
| Keynote: Can you trust your (large language) model? | Jodie Burchell | 54m |
Compares concrete failures and fixes: a psychology replication snafu, CEXNet overfitting because of data leakage, and GPT‑4 solving Codeforces puzzles only… | ||
| Drop the Bass with Embedding and Vectors in Azure AI Search | Alan Smith | 01h 03m |
Demo shows building real vector search pipelines: ResNet18 image embeddings feed Azure AI Search indexes with 12,300 dog vectors and a 280,000-image auction… | ||
| How to Break AI Systems (Before Someone Else Does) | Gary Lopez | 53m |
Claims that production AI routinely fails where standard security testing misses prompt injection and agent goal manipulation, and shows live demos of hidden… | ||
| React AI | Jim Manico | 59m |
Live demo across five frontier models (ChatGPT 5.1, Copilot, Claude, Grok, Gemini) shows raw AI output produces dangerous React patterns: unvalidated hrefs and… | ||
| Between the Layers– Interpreting Large Language Models | Michelle Frost | 59m |
Distinguishes explainability (outside, human accounts) from interpretability (inside, causal wiring) and reports concrete methods: unmixing activations with… | ||
| Inside GPT – Large Language Models Demystified | Alan Smith | 01h 01m |
Downloads include Jupyter notebooks and a zip that run GPT2 from scratch (about 126M parameters, 12 layers, 12 heads, 768-d embeddings) so you can step through… | ||
| nothing matches | ||