Cross-cutting
Videos
A trace crossing five services, a Collector filtering live or a dashboard where a drift shows up are quicker to grasp on video than in writing. My videos are published on the Telemetry Talks YouTube channel.
Videos on the channel
Section titled “Videos on the channel”It hosts the first MTTL educational videos, in French or English, along with projects and topics close to MTTL: ReversOtel, Archipel and the security of AI systems.
On this site, MTTL videos sit next to the pages they illustrate, in French and English: observability in 90 seconds on the home page, from the GPU to the platform at the top of the HPC AI course and AI in cross-section with its interactive 3D diagram. The HPCOBS lab demo, with English subtitles, sits on the labs page and in the training step of the HPC AI course.
GPUs at 87% but how much useful compute? HPC, AI and observabilityYour dashboard shows 87% GPU utilization, yet training is slow.
L'observabilité en 90 secondes : des nilomètres à l'IAQu'est-ce que l'observabilité?
ReversOtel,un controle plane OpenTelemetry open source
ArchipelV0 1
PATTERNS DE DETECTIONAdversarial, Drift et LLM , avec code et metriques.
Threat ModelComment cadrer les menaces sur vos systèmes de ML avant de déployer quoi que ce soit.
Sécurité IA: Pourquoi vos modèles sont-ils de nouvelles surfaces d'attaques?Dans cette vidéo, vous allez apprendre les différents types d'attaque sur un LLM, comment structurer sa protection façe à ces menaces.
Iagentsec/ 1st previewMost companies monitor servers, APIs and users but not the AI itself.
Formats planned for MTTL
Section titled “Formats planned for MTTL”| Format | Target length | Content |
|---|---|---|
| Demo | 10 to 20 min | a lab replayed step by step |
| Explainer | 5 to 10 min | a concept, an announcement or a standard explained |
Each video of this kind will link to its article and lab, and every article will link to its video once there is one.