20th April 2026 – Link Blog Claude Token Counter, now with model comparisons. I upgraded my Claude Token Counter tool to add the ability to run the same count against different models in order to compare them. As far as … Read more
Anthropic’s Claude Opus 4.7 migration guide says the new tokenizer uses “roughly 1.0 to 1.35x as many tokens” as 4.6. I measured 1.47x on technical docs. 1.45x on a real CLAUDE.md file. The top of Anthropic’s range is where most … Read more
Today, we’re launching Claude Design, a new Anthropic Labs product that lets you collaborate with Claude to create polished visual work like designs, prototypes, slides, one-pagers, and more. Claude Design is powered by our most capable vision model, Claude Opus … Read more
Our latest model, Claude Opus 4.7, is now generally available. Opus 4.7 is a notable improvement on Opus 4.6 in advanced software engineering, with particular gains on the most difficult tasks. Users report being able to hand off their hardest … Read more
Routines are in research preview. Behavior, limits, and the API surface may change. A routine is a saved Claude Code configuration: a prompt, one or more repositories, and a set of connectors, packaged once and run automatically. Routines execute on … Read more
I asked Claude to look up the X-Plane 12 API and try to fly a Cessna from Hainan to somewhere nearby. It kept a pilot’s log. Everything below is Claude’s own notes from during the flight. I occasionally had to … Read more
The bug Claude sometimes sends messages to itself and then thinks those messages came from the user. This is the worst bug I’ve seen from an LLM provider, but people always misunderstand what’s happening and blame LLMs, hallucinations, or lack … Read more
Preflight Checklist What’s Wrong? Claude Code cannot log in on Windows and always fails with this error: OAuth error: timeout of 15000ms exceeded I have tried logging in multiple times with my Google account, but the login fails every time … Read more
Preflight Checklist Type of Behavior Issue Other unexpected behavior What You Asked Claude to Do Claude has regressed to the point it cannot be trusted to perform complex engineering. What Claude Actually Did Ignores instructions Claims “simplest fixes” that are … Read more
Nicholas Carlini, a research scientist at Anthropic, reported at the [un]prompted AI security conference that he used Claude Code to find multiple remotely exploitable security vulnerabilities in the Linux kernel, including one that sat undiscovered for 23 years. Nicholas was … Read more