---
title: "An update on recent Claude Code quality reports"
source_name: "Simon Willison's Weblog"
original_url: "https://simonwillison.net/2026/Apr/24/recent-claude-code-quality-reports/#atom-everything"
canonical_url: "https://www.traeai.com/articles/8a3d0a02-233d-40a6-8656-4609323f00be"
content_type: "article"
language: "中文"
score: 5
tags: []
published_at: "2026-04-24T01:31:25+00:00"
created_at: "2026-04-24T06:26:13.638592+00:00"
---

# An update on recent Claude Code quality reports

Canonical URL: https://www.traeai.com/articles/8a3d0a02-233d-40a6-8656-4609323f00be
Original source: https://simonwillison.net/2026/Apr/24/recent-claude-code-quality-reports/#atom-everything

## Summary

traeai 为开发者、研究员和内容团队筛选高质量 AI 技术内容，提供摘要、评分、趋势雷达与一键内容产出。

## Key Takeaways

- 
- 
- 

## Content

Title: An update on recent Claude Code quality reports

URL Source: http://simonwillison.net/2026/Apr/24/recent-claude-code-quality-reports/

Markdown Content:
24th April 2026 - Link Blog

**[An update on recent Claude Code quality reports](https://www.anthropic.com/engineering/april-23-postmortem)** ([via](https://news.ycombinator.com/item?id=47878905 "Hacker News")) It turns out the high volume of complaints that Claude Code was providing worse quality results over the past two months was grounded in real problems.

The models themselves were not to blame, but three separate issues in the Claude Code harness caused complex but material problems which directly affected users.

Anthropic's postmortem describes these in detail. This one in particular stood out to me:

> On March 26, we shipped a change to clear Claude's older thinking from sessions that had been idle for over an hour, to reduce latency when users resumed those sessions. A bug caused this to keep happening every turn for the rest of the session instead of just once, which made Claude seem forgetful and repetitive.

I _frequently_ have Claude Code sessions which I leave for an hour (or often a day or longer) before returning to them. Right now I have 11 of those (according to `ps aux  | grep 'claude '`) and that's after closing down dozens more the other day.

I estimate I spend more time prompting in these "stale" sessions than sessions that I've recently started!

If you're building agentic systems it's worth reading this article in detail - the kinds of bugs that affect harnesses are deeply complicated, even if you put aside the inherent non-deterministic nature of the models themselves.