Is Opus 4.7 a Downgrade?
Opus 4.7 is not generally a worse model than Opus 4.6, but there is a real downgrade: with Opus 4.7, the control over the thinking budget is now fully owned by Anthropic. This change matters in a way…
A postmortem of three recent issues
anthropic.comThis is a technical report on three bugs that intermittently degraded responses from Claude. Below we explain what happened, why it took time to fix, and what we're changing.
Claude Code Opus 4.7 Performance Tracker | Marginlab
Track Claude Code's daily performance on SWE-Bench-Pro. Monitor for degradation with statistical significance testing.
Digest | Jul/Aug/Sep/Oct 2025
I like Thinking Machines, but more than that, I’m grateful.
Testing and Benchmarking of AI Compilers — Bjarke Hammersholt Roune
This is an in-depth post on bugs and how to prevent them in AI software and AI compilers specifically. I was the software lead for TPUv3 at Google and I’ve worked on a variety of AI compilers and projects across Google, Nvidia, Amazon and Facebook.
Using Code Agents Effectively
Practical techniques for getting great results from AI coding agents, from project setup and context management to effective prompting patterns.
LLM inference is nearly deterministic. We use this to audit providers
Adam Karvonen, Daniel Reuter, Roy Rinberg, Luke Marks, Adrià Garriga-Alonso, Keri Warr · arXiv (paper link) · Github