Walter Reade
8.2K posts

Walter Reade
@WalterReade
AI at Google/Kaggle (inversion). PhD chemical engineer. Too many hobbies.



The King Bleeds, Long Live The King open.substack.com/pub/irrational…


Everything feels impossible right up until it's inevitable.







We expect agents to act like senior engineers, but most benchmarks still evaluate them like interns. Excited to introduce Senior SWE-Bench, an open-source and @harborframework-native benchmark that assesses agents as senior engineers on long-horizon tasks with realistically under-specified instructions. We expect agents to build real features going on just a quick Slack message, nothing like the super technical instructions most benchmarks provide. Senior SWE-Bench fixes that. Claude Opus 4.8 is the current leader at 24% high quality solves, but it took 117K tokens on average to get there. Claude Sonnet 5 looked like it was going to swoop in for the top spot, but we found it cheated on 26% of trials.

Ready to bring the power of open models to your community? The @GoogleGemma team is sponsoring 1-day hackathons on @Kaggle! Whether you want to explore how Gemma 4 can be used to build lightweight tools or drive AI innovation in a specific field, now's your chance to lead the charge. 👉 Apply to host a hackathon for your community today: goo.gle/build-with-gem…



In the first episode of Kaggle Conversations, @MeganRisdal and @WalterReade from the Kaggle team talk with @alexgshaw, creator of @harborframework, about how the AI Agent industry is moving towards autonomy, why software engineering benchmarks are prone to contamination, and what it took to build a secure evaluation framework for the $1M Konwinski Prize. Watch a clip from the episode 👇












