Hien Luu

2026-10-30

MODELS · 1 SOURCE · InfoQ AI, ML & Data Engineering

InfoQ podcast: AI, ML and Data Engineering Trends Report 2026

InfoQ's AI, ML and Data Engineering editorial team published a 2026 trends report and released a podcast episode where editors and guest Chip Huyen discuss key trends: a shift toward smaller language models and reasoning models, wider deployment of AI agents (from personal to organizational), interest in System One models such as TypeSafe AI's Jev for cheaper/faster inference, growing focus on AI evaluations, and advances in Physical AI. The panel also offered near-term predictions including more US robotics innovation, cost and energy constraints on infrastructure, broader use of specialized/mixed agents, and continued delineation of tasks best suited for AI versus humans.

4.0

2026-10-29

CODING · 1 SOURCE · InfoQ AI, ML & Data Engineering

QCon AI New York 2026 committee highlights sessions on agent identity, context costs, and vLLM

The QCon AI New York 2026 program committee has selected six sessions for the Dec 15–16 conference that focus on agent identity and authorization, token/context cost management for production LLMs, coding agents in engineering orgs, open-source agentic inference with vLLM, agent standards, and audio processing with LLMs. Notable speakers include Nancy Wang (1Password), Tejas Chopra (Headroom Labs), Peter Bell (Gather.dev), Francisco Javier Arceo (Baseten/vLLM), Kevin Kelley (Anthropic), and Tara Sainath (Google DeepMind); the conference will be held at the Westin Jersey City Newport.

4.0

2026-10-16

CODING · 1 SOURCE · InfoQ AI, ML & Data Engineering

InfoQ webinar panel highlights silent failures and governance for AI agents

An InfoQ webinar titled “AI in Production: What Breaks, What Works, and Who Approves It?” gathered ThoughtWorks practitioners and security/privacy experts to discuss operational challenges of agentic systems, including semantic and embedding drift, RAG leakage, model memorization, and the scaling gap for human code review as coding agents produce more production code. Panelists recommended treating evals as persistent infrastructure, shifting checks left in the harness, using mutation testing and continuous tracing, enforcing agent identities and tiered access, red‑teaming, and isolating secrets to limit blast radius.

6.0

2026-10-07

CODING · 1 SOURCE · InfoQ AI, ML & Data Engineering

InfoQ webinar — "AI in Production: What Breaks, What Works, and Who Approves It?"

InfoQ is hosting a free 60-minute live webinar, “AI in Production: What Breaks, What Works, and Who Approves It?”, with five practitioners (Hien Luu, Katharine Jarmul, Zichuan Xiong, Premanand Chandrasekaran, Lan Chu) discussing production challenges for RAG, coding agents, verification, data exposure, and governance; registration is free and a recording is shared with registrants. The panel will explore agent autonomy, verification gates, sensitive-data handling, production RAG architectures, and how engineers make the internal case for controls.

3.0

2026-09-25

COMPANIES · 1 SOURCE · InfoQ AI, ML & Data Engineering

QCon AI New York 2026 highlights: agent authorization, ops agents, model serving, evaluation

QCon AI New York (Dec 15–16, 2026) has confirmed 23 sessions covering identity and authorization for autonomous agents (keynote by Nancy Wang, 1Password), guardrails for an operations agent on large-scale Kubernetes (LinkedIn), Netflix’s five‑year consolidation of its model‑serving platform, and post‑deployment evaluation and moderation platforms. The program frames AI engineering as systems engineering, focusing on bounded agent authority, observability, cost/latency trade‑offs, and continuous evaluation for production systems.

5.0

2026-09-15

COMPANIES · 1 SOURCE · InfoQ AI, ML & Data Engineering

Grab's LLM-Kit framework accelerates internal AI agent deployment from two weeks to one hour

Grab has deployed LLM-Kit, a framework that standardizes and centralizes over 500 internal agent services to improve integration, evaluation, secret handling and runtime tool discovery. According to the report, LLM-Kit reduces the time to ship new AI agents from about two weeks to roughly one hour while preserving operational control and flexible model integration.

7.0