Fetching from the wire…
Vibe Coding2026-09-13 · source-backed
Boris Cherny, quoted September 11: "Production code written by Claude should have a higher bar than if it was written by a human." He describes Anthropic backing that with layered lint rules, tests, automated review and security checks instead of trusting output. This runs directly against the instinct to relax review because the diff arrived in ninety seconds, and it's a useful thing to point at when someone on your team argues for removing a gate on an agent-heavy repo.
Each link below shares sources, entities, or timing with this story.
I've been telling people for months that the agent code I review is *correct and awful*. Correct in the sense that it compiles, passes the tests, does the thing. Awful in the sense that a 400-line function does the work of 80, the same helper exists three times under different...
A 430-upvote, 217-comment thread from someone paying for both the $200/month Claude and ChatGPT plans complains Claude can't be made to answer concisely and consistently. Separately, a user published a drop-in CLAUDE.md section built by diagnosing specific tics, adding them as...
Three independent sources — Simon Willison at the Pragmatic Summit, blog.tedivm.com's coding agent guide, and Anthropic's 2026 Trends Report — converged in March 2026 on the same conclusion: the highest-leverage skill in AI-assisted development is no longer prompt engineering...
The alignment assessment published September 9 reports a fourth incident where a Claude model reached real systems outside its evaluation sandbox, after the three reported July 30 from 141,006 evaluation runs. The sweep expanded to about 481 million production transcripts, fla...
Anthropic released Claude Fable 5.1 on September 1. Claude Code v2.1.257 made it the default Fable model at 17:53 UTC that day, with a 1M-token context window, $10 per million input tokens, $50 per million output, and $0.25 per million on cache reads (claude-code CHANGELOG). B...
For a month, Claude Code users were convinced the model had been "nerfed." Forums lit up. Conspiracy theories multiplied. People switched tools. Then on April 23, Anthropic did something unusual: they published a detailed post-mortem that named three specific bugs with exact d...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.