
Lance Martin
@rlancemartin
langchain. past: robots š š¤, phd @stanford š§Ŗ
ID: 39202644
11-05-2009 05:57:56
995 Tweet
14,14K Followers
272 Following


Some notes from AI Engineer day 1 - Simon Willison on state of AI > Visual eval for LLMs: asked each LLM to generate code for an SVG image of a pelican riding a bicycle. Ran this across ~30 model releases over the past 6 months. Created a script to select random image pairs, GPT4.1

a few thoughts on the current state of agents based on what I saw at AI Engineer: + rise of "ambient" agents + the bitter lesson & agent UX + RL for non-verifiable tasks + the case for MCP + early days for agent memory rlancemartin.github.io/2025/06/10/aie/