Stop Shipping LLM Settings That Only Win on Paper - Rohan Pandey & Balaji Varadarajan, DigitalOcean

Serving-config gains can be noise, so changes should be validated against latency targets with repeat runs before shipping. The talk shows an agent loop that automates this with safe rollback on AMD MI355 servers.

• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• agentic loop — The cycle an agent runs in: decide, call a tool, read the result, decide again — repeating until the goal is met or a stop condition fires.

• videoRethinking Claude Code Best Practices — Lydia Hallie, Anthropic
• videoYour SKILL.md Is 70% Stuff the Model Already Knows - Nikolay Petrov, Intel
• videoYour Spec Has Bugs. Catch Them Before Your Agent Codes. - Rajath Mahendrappa Kotyal, AWS
• video225,000 Lines of Tests, Written and Merged by Agents - Kush Agrawal, Duolingo

• videoAre LLM Performance Benchmarks Reliable? — Ashok Chandrasekar & Jason Kramberger, GoogleAI Engineer
• videoAgents That Own Their Inference — Du'an Lightfoot & Khaja Omer, Akamai TechnologiesAI Engineer
• videoStop Guessing Your vLLM Config: Benchmarking LLMs on Runpod - Chris Vela, RunpodAI Engineer

Checking sign-in…

Loading comments…