It's fixed as of nine minutes ago: https://github.com/anthropics/claude-code/pull/16686

Genuinely curious how a date in the subheader of a changelog could have broken the CLI

edit: it seems changelog.md is assumed to be structured data and parsed at startup, and there are no tests to enforce the changelog structure: https://github.com/anthropics/claude-code/issues/16671

This is the kind of choice an LLM would make...

You might be surprised (or not, depending on how long you’ve been doing this).

You're absolutely right! ;)

Ah yes, markdown, the ultimate structure for machine-readable data

They're using Markdown for everything in LLM-land.

Someone had to come up with something even more annoying than yaml for machine-readable data. :)

its vibe coded to its teets and gets reviewed by AI

What a lazy commit message, "Update CHANGELOG.md", no mention of the "why" at all. Even the PR description is blank.

This is especially bizarre because one thing LLMs have been better at that practically all the developers I have ever worked with is writing good commit messages. The fact they didn't make use of this here when everything else in Claude Code seems vibe-coded these days is funny to me.

Claude Code couldn't write a commit description since it was broken at that point.

was this a 10x gdp vibe-loss ?

I felt a disturbance in the force, as if millions of GPU cooling fans suddenly spun down.

Lol a formatting error in a change log breaking the entire thing

Cloudflare is experiencing a global outage which affects products like Claude, ChatGPT, Twitter, and others. https://news.ycombinator.com/item?id=45963780

(I work at Anthropic) It's 30% of all CC users that made a request during that period. We've updated the post to be clearer.

Thanks for the correction and updating the post.

I typically read corporate posts as cynically as possible, since it's so common to word things in any way to make the company look better.

Glad to see an outlier!

The data retention period is 30 days if you don't choose to improve model training. https://www.anthropic.com/news/updates-to-our-consumer-terms...

Oh, I didn't catch this—that's good news

> If you do not choose to provide your data for model training, you’ll continue with our existing 30-day data retention period.

https://www.anthropic.com/news/updates-to-our-consumer-terms

Does not apply to team/enterprise/education or the API.

More countries soon.

Sorry for the hassle Sam. We're seeing decreasing error rates on the API now. This was painful -- appreciate your patience while we work through the issue with one of our infra providers.

I bet your day was more filled with hassle! But genuinely appreciate the response. One thing it’s really highlighted to me is that you’re miles ahead of the alternative APIs available. It’s also highlighted quite how much I’ve come to rely on not just the API but other little workflows I’ve made in Claude itself. I felt quite bereft for most of the morning.

Believe me, I missed Sonnet too. Thanks for sharing.

hello! thanks for sharing nick + philip.

You're welcome (:

this is cool, nice work. (and also cool to see you using sonnet to do this!)

thanks! Sonnet 3.5 is really good for codegen