Résultats
9 articlesTrier
18:56EN
AI Engineer· 27 oct. 2026John Feminella: Five Controls for AI Agents, and the $900 Million Bank ErrorJohn Feminella · Two SigmaA payment mistake shows why good intentions and approval prompts are not enough. Feminella describes practical controls for giving agents useful autonomy.
23:22ENAI Engineer· 27 oct. 2026Noyan Tokgozoglu: How Optiver Builds an AI Platform for Fast, Measurable DecisionsNoyan Tokgozoglu · OptiverThe trading firm’s AI engineering lead explains same-day model adoption, on-premises infrastructure, cost controls and the limits of replaying agent evaluations.
53:04ENAI Engineer· 26 oct. 2026Fuad Ali: Building a Feedback Loop to Improve AI AgentsFuad Ali · Arize AIAn Arize workshop connects traces, failure datasets, evaluations, proposed fixes and experiments while keeping human judgment in the loop.
20:55ENAI Engineer· 26 oct. 2026Jesse Hall: Build Voice Agents for Conversations, Not LeaderboardsJesse Hall · LiveKitLiveKit’s Jesse Hall explains how to evaluate voice agents as real-time systems: understand callers, handle interruptions, keep talking while tools run, and measure the delay people actually hear.
35:19ENAI Engineer· 25 oct. 2026SallyAnn DeLucia: How to Write Your First AI EvalSallyAnn DeLucia · Arize AITurn an agent’s real traces into concrete pass/fail criteria, then build an LLM judge you can test, align with people, and run in production.
18:31ENAI Engineer· 25 oct. 2026Janie Gu and Suyeol Yun: Why Frontier Models Fail as Buy-Side AnalystsJanie Gu, Suyeol Yun · Google DeepMindJanie Gu explains why benchmark scores can mislead, while Suyeol Yun presents MandateBench, which tests whether a model can turn a fund mandate into a defensible investment memo. The two talks show why real workflows, reproducible grading, and evidence-backed reasoning matter.
15:27ENAI Engineer· 25 oct. 2026What AI Engineers Do Now: Build the Loop Around AgentsAparna Dhinakaran · Arize AIAparna Dhinakaran argues that AI engineers are moving from shipping individual features to building systems that let agent teams improve them. At Arize, that means tracing agent behavior, evaluating its work against human judgment, and feeding those signals back into an always-on agent.
17:42ENAI Engineer· 21 oct. 2026Is a Faster Model Actually Faster? Measure the Finished Job, Not the TokensMorgan Suo · MiniMaxMiniMax's Morgan Suo takes the engineering changes inside M3.1 Flash one by one and asks the question that matters to users: does the job an analyst needs actually get done sooner, cheaper and correctly?
1:48:29EN
Jane Street· 16 oct. 2026How AI Is Changing Programming: John Crepezzi and Ron MinskyYaron Minsky, John Crepezzi · Jane StreetJane Street’s AI tooling lead and the Signals and Threads host examine agent infrastructure, security, code review and the changing experience of writing software.