The authors built a dataset of 148 PyTorch research projects and had Claude Code, running Claude Opus 5.5, migrate ten of them to Google Cloud TPUs. They then checked each migration themselves instead of relying on the agent's report.
In the News: November 2, 2026 (Extra 3)
A study of Claude Code GPU-to-TPU migrations found 49% of failed attempts raised no error, and one reported success hid an accuracy drop.
Extra edition
Machine-readable
Download Markdown
Story
In a study of Claude Code migrating ML projects from GPUs to TPUs, 49% of failed execution attempts raised no error
Read story →
Story
OpenAI says it built a Git backend called Pando because Codex pushed its monorepo past what its old source-control setup could serve
OpenAI says that around the end of last year its monorepo systems began struggling, with slow fetches and pushes, failed merges and reliability at times below 90%. Its explanation is that Codex lets each engineer have several changes…
Trustworthy Data Analysis
An Agent Skills skill plus a 30-case benchmark of data-analysis traps. The author's own runs, one per case and arm and judged by Sonnet, show Claude Haiku 5.5 passing 37 of 39 graders on the 19 data-analysis cases without the skill and 39 of 39 with it, and Sonnet 5.5 passing 38 of 39 and 39 of 39. The README calls the effect small and noisy.