AI Engineer · September 24, 2026

AI Engineer Paris 2026 Main Stage: Google DeepMind, ElevenLabs, Hugging Face & Stripe | Day 2

video AI Engineering

AI Engineer Paris 2026 Main Stage: Google DeepMind, ElevenLabs, Hugging Face & Stripe | Day 2 video thumbnail

Why it matters

The completed second-day main-stage broadcast from AI Engineer Paris 2026 covers model loading, low-latency inference, streaming voice, coding-agent coordination and the AI economy. The publisher lists speakers from Hugging Face, Modal, Cognition, Google DeepMind, ElevenLabs, Stripe and other teams. This agenda-based overview identifies the recording’s scope; concurrent workshops and other tracks are not included.

My takeaway: Choose sessions by the engineering problem you need to solve, and consult their examples and linked documentation before applying the advice. Treat the broadcast as a collection of talks with separate evidence and assumptions.

Keep exploring

More curated notes connected through AI Engineering.

Microsoft Security Blog · guide

AI vulnerability research: measure reproducible findings and completed fixes

Microsoft’s FORGE account describes the work between a model’s vulnerability claim and a useful repair: reusable builds, duplicate removal, reachability checks, project-specific verification, reproducible triggers and regression tests. Structured rejection reasons help improve later searches. The useful operational measure is the flow of findings that survive verification and reach a fix, rather than the number of candidates generated. Reported successful-case costs exclude parts of screening, failed attempts and human work, so they are not the total cost of operating this pipeline.

OpenAI News · guide

The Defender’s Window

OpenAI describes a staged program for AI-assisted defense: use agents to review code and infrastructure, triage alerts, enumerate attack paths, and validate security invariants while retaining strong isolation and least privilege. Its recommended rollout starts with internet-facing services and vulnerability backlogs, moves security review into CI, requires focused fixes and regression tests, and expands from read-only triage to narrowly bounded automation only after teams build evidence and confidence.

Google Cloud Security Blog · tool

Now in preview: Find and fix software vulnerabilities with CodeMender

Google opened a preview of CodeMender, an AI code-security agent delivered through Gemini Enterprise Agent Platform and AI Threat Defense. It is designed to inspect code, identify and validate potentially exploitable defects, and produce targeted fixes, with Google’s specialized Gemini 3.5 Flash Cyber model initially restricted to governments and trusted partners.