

by Snorkel AI Community Events
Join the Snorkel AI Reading Group, a recurring forum to explore the latest frontier developments in AI while building meaningful connections within the community.In this session, Carter Wendelken of Google DeepMind will dive into his paper “AutoHarness: Improving LLM Agents by Automatically Synthesizing a Code Harness."Agenda:
5:30pm - doors open6pm - talk beginsLight drinks and appetizers provided
Most work on language models focuses on improving the model itself. This talk takes a different angle: improving outcomes by shaping how the model acts through automatically generated code harnesses.
You’ll learn:
Why LLM agents often fail when their actions are prohibited by the external environmentHow AutoHarness automatically synthesizes a code harness through iterative refinement from environment feedbackHow a learned harness can prevent illegal moves in structured environmentsHow execution-guided search over code can yield a more robust control loopWhy a smaller model with a custom harness can outperform larger modelsHow the agent can generate the entire policy in code, removing the need for model inference at decision time
Sign in to view full event details
Create a free account to see descriptions, save events, and more
Reading Group: AutoHarness: Improving LLM Agents by Automatically Synthesizing a Code Harness is a free independent taking place on Thursday, May 14, 2026 at 101 Second Street, San Francisco, CA 94105, USA, San Francisco, United States. This independent is organised by Snorkel AI Community Events. Attendance is free — register to secure your spot. Currently 1 person has registered out of 1 spots. The event runs for approximately 2 hours and 30 minutes.
Join this independent over 2 hours and 30 minutes for an engaging session of learning, discussion, and networking with fellow attendees.
This independent in San Francisco is ideal for:
This morning independent is part of the growing events scene in San Francisco. Whether you're based in San Francisco or visiting for the independent, it's a great opportunity to connect with the local community. Browse more upcoming events in San Francisco on Rifio.
Reading Group: AutoHarness: Improving LLM Agents by Automatically Synthesizing a Code Harness covers topics including AI. Find similar events by browsing these topics on Rifio.