Jason Lopatecki
where else to find them
linkedin:jason-lopatecki-9509941
what they talk about
where they keep going back
no series more than once — all 3 in the filters
on a stage with
- Jay Alammaronce
who talks about the same things
- Jay Alammar8 talks
- Cassie Breviu17 talks
- Nitya Narasimhan25 talks
- Ritesh Modi6 talks
- Rajesh Gupta3 talks
- Dona Sarkar23 talks
| title | conference | date |
|---|---|---|
| From Signal to PR: Anatomy of a Self-Improving Agent | Observe 2026 | 2026-06-04 |
Arize shows that the actual unlock is traces on a filesystem pulled as files into the repo (sometimes ten megabytes), letting an agent produce a real fix —… | ||
| Advanced Evaluation Techniques for AI Agents | Ray Summit 2024 | 2024-09-30 |
Claims a practical evaluation stack for LLM agents: a simple LM router -> skill -> router architecture (90% of deployments), function calling as the core… | ||
| Model innovation & evaluation with model partners Q&A | Microsoft Build 2024 | 2024-05-21 |
Discussion recommends using LMs to judge other LMs and insists on production-grade observability to collect traces and evaluations. RAG is decomposed into… | ||
| nothing matches | ||