---
title: Claude Code Quality Got Worse, and Anthropic Admitted It
description: The Claude Code quality drop in early 2026 wasn't in your head. Anthropic's own postmortem confirmed three overlapping regressions, and the numbers were ugly.
canonical: https://lukeocodes.dev/claude-code-quality
type: article
locale: en_GB
published: 2026-08-24T00:00:00.000Z
modified: 2026-08-24T00:00:00.000Z
authors:
  - Luke Oliff
section: Opinion
tags:
  - Opinion
  - AI
  - anthropic
  - claude code
  - regressions
  - developer tools
feed: https://lukeocodes.dev/rss.xml
search: https://lukeocodes.dev/search.json?q={query}
schema:
  - "@context": https://schema.org
    "@graph":
      - "@type": WebSite
        "@id": https://lukeocodes.dev/#website
        url: https://lukeocodes.dev
        name: Luke Oliff
        alternateName: lukeocodes
        inLanguage: en
        publisher:
          "@id": https://lukeocodes.dev/authors/luke#person
        description: Personal blog and writing by Luke Oliff — developer relations, voice AI, developer experience.
        potentialAction:
          - "@type": SearchAction
            target:
              "@type": EntryPoint
              urlTemplate: https://lukeocodes.dev/blog/search?q={search_term_string}
            query-input: required name=search_term_string
      - "@type": Person
        "@id": https://lukeocodes.dev/authors/luke#person
        name: Luke Oliff
        url: https://lukeocodes.dev/authors/luke
        description: Engineer and developer relations leader. Writing about developer relations, AI, and the voice industry, from the UK.
        mainEntityOfPage: https://lukeocodes.dev/authors/luke
        givenName: Luke
        familyName: Oliff
        image: https://lukeocodes.dev/authors/luke.jpg
        jobTitle: Engineer and developer relations leader
        sameAs:
          - https://www.linkedin.com/in/lukeocodes
          - https://github.com/lukeocodes
          - https://bsky.app/profile/lukeocodes.dev
          - https://x.com/lukeocodes
          - https://hashnode.com/@lukeocodes
          - https://dev.to/lukeocodes
        knowsAbout:
          - Developer Relations
          - Developer Experience
          - Voice AI
          - Text-to-Speech
          - Answer Engine Optimisation
          - Search Engine Optimisation
          - Open Source
          - Developer Tooling
          - API Design
          - Speech-to-Text
          - Voice Agents
          - Community Building
        knowsLanguage:
          - English
        nationality: British
        alumniOf:
          - "@type": Organization
            name: The Open University
  - "@context": https://schema.org
    "@graph":
      - "@type": Person
        "@id": https://lukeocodes.dev/authors/luke#person
        name: Luke Oliff
        url: https://lukeocodes.dev/authors/luke
        description: Engineer and developer relations leader. Writing about developer relations, AI, and the voice industry, from the UK.
        mainEntityOfPage: https://lukeocodes.dev/authors/luke
        givenName: Luke
        familyName: Oliff
        image: https://lukeocodes.dev/authors/luke.jpg
        jobTitle: Engineer and developer relations leader
        sameAs:
          - https://www.linkedin.com/in/lukeocodes
          - https://github.com/lukeocodes
          - https://bsky.app/profile/lukeocodes.dev
          - https://x.com/lukeocodes
          - https://hashnode.com/@lukeocodes
          - https://dev.to/lukeocodes
        knowsAbout:
          - Developer Relations
          - Developer Experience
          - Voice AI
          - Text-to-Speech
          - Answer Engine Optimisation
          - Search Engine Optimisation
          - Open Source
          - Developer Tooling
          - API Design
          - Speech-to-Text
          - Voice Agents
          - Community Building
        knowsLanguage:
          - English
        nationality: British
        alumniOf:
          - "@type": Organization
            name: The Open University
      - "@type": BlogPosting
        "@id": https://lukeocodes.dev/claude-code-quality#article
        headline: Claude Code Quality Got Worse, and Anthropic Admitted It
        alternativeHeadline: Claude Code Quality Got Worse, and Anthropic Admitted It
        description: The Claude Code quality drop in early 2026 wasn't in your head. Anthropic's own postmortem confirmed three overlapping regressions, and the numbers were ugly.
        datePublished: 2026-08-24T00:00:00.000Z
        dateModified: 2026-08-24T00:00:00.000Z
        url: https://lukeocodes.dev/claude-code-quality
        mainEntityOfPage: https://lukeocodes.dev/claude-code-quality
        inLanguage: en
        author:
          - "@id": https://lukeocodes.dev/authors/luke#person
        isPartOf:
          "@id": https://lukeocodes.dev/#website
        keywords: Opinion, AI, anthropic, claude code, regressions, developer tools
        articleSection: Opinion
        about:
          - "@type": Organization
            name: Anthropic
          - "@type": Organization
            name: TrustedSec
        abstract: "In spring 2026 Claude Code got noticeably worse, and Anthropic's own April postmortem confirmed three overlapping causes: a silent reasoning-effort cut, a thinking-cache bug, and a verbosity cap. Independent testers measured real quality drops. The gaslighting was the worst part."
        speakable:
          "@type": SpeakableSpecification
          cssSelector:
            - .post-tldr
            - h1
        image: https://lukeocodes.dev/og.png?h=Claude+Code+Quality+Got+Worse%2C+and+Anthropic+Admitted+It&d=The+Claude+Code+quality+drop+in+early+2026+wasn%27t+in+your+head.+Anthropic%27s+own+postmortem+confirmed+three+overlapping+regressions%2C+and+the+numbers+were+ugly.&e=Writing
        wordCount: 477
        timeRequired: PT3M
        publisher:
          "@id": https://lukeocodes.dev/authors/luke#person
      - "@type": BreadcrumbList
        itemListElement:
          - "@type": ListItem
            position: 1
            name: Home
            item: https://lukeocodes.dev
          - "@type": ListItem
            position: 2
            name: Writing
            item: https://lukeocodes.dev/blog
          - "@type": ListItem
            position: 3
            name: Claude Code Quality Got Worse, and Anthropic Admitted It
            item: https://lukeocodes.dev/claude-code-quality
      - "@type": FAQPage
        "@id": https://lukeocodes.dev/claude-code-quality#faq
        mainEntity:
          - "@type": Question
            name: What did Anthropic's postmortem actually admit?
            acceptedAnswer:
              "@type": Answer
              text: "Three overlapping issues in spring 2026: default reasoning effort was cut from high to medium to save latency, a thinking-cache bug cleared prior reasoning every turn causing forgetfulness and extra cache-miss token spend, and a system-prompt verbosity cap measurably dropped output quality. All were reverted by late April."
          - "@type": Question
            name: Was the quality drop measured or just vibes?
            acceptedAnswer:
              "@type": Answer
              text: Measured. Fortune reported TrustedSec found a 47% code-quality drop and a 52% vulnerability rate on coding tasks for one model version, against roughly 30% for a competitor. Separately, users cancelled in numbers and a 971-point Hacker News thread captured the mood.
          - "@type": Question
            name: Why does a cache bug cost me money?
            acceptedAnswer:
              "@type": Answer
              text: Because clearing cached reasoning every turn forces cache misses, and misses are billed as fresh input tokens. So a quality regression and a cost regression arrived in the same bug. You paid more to get a worse, more forgetful assistant.
---

[Luke Oliff.](/)

- [Blog](/blog)
- [CV](/cv)
- [Uses](/uses)
- [User manual](/user-manual)
- [Living with ADHD](/living-and-working-with-adhd)
- [RSS](/rss.xml)

[Luke Oliff · Writing](/blog)

# Claude Code Quality Got Worse, and Anthropic Admitted It

Aug 2026 · [Opinion](/blog/category/opinion) · 3 min read · [Luke Oliff](/authors/luke)

**TL;DR:** In spring 2026 Claude Code got noticeably worse, and Anthropic's own April postmortem confirmed three overlapping causes: a silent reasoning-effort cut, a thinking-cache bug, and a verbosity cap. Independent testers measured real quality drops. The gaslighting was the worst part.

The Claude Code quality drop in early 2026 was not in your head, and you don't have to take my word for it. Anthropic said so. In an April postmortem the company [walked through three overlapping regressions](https://www.anthropic.com/engineering/april-23-postmortem) that made its own coding tool worse for weeks. The interesting part isn't that software broke. It's how long the official line was that nothing had.

## What broke, in their words

Three things, stacked.

First, from early March to early April, the default reasoning effort was quietly dropped from high to medium to cut latency. Less thinking, faster replies, worse answers. Second, from late March into April, a thinking-cache bug cleared prior reasoning every turn, so the model got forgetful and repetitive, and every cleared turn caused a cache miss you paid for as fresh input. Third, a system-prompt change capping verbosity ("keep it under 25 words between tool calls") measurably knocked output quality, by their own estimate about 3% across two model versions.

Read those together and it's a tool that got dumber, more forgetful, and more expensive at the same time, for over a month, by configuration.

## The numbers outsiders measured

While users were being told it was fine, people with test suites went and checked. [Fortune reported](https://fortune.com/2026/04/24/anthropic-engineering-missteps-claude-code-performance-decline-user-backlash/) that TrustedSec measured a 47% code-quality drop, and a 52% vulnerability rate on coding tasks for one Opus version versus roughly 30% for a competitor. TrustedSec's CEO called the month-long response time "crummy." Another founder used the word "gaslighting." That word stuck with me, because it's the right one.

There was a genuinely funny, genuinely bleak moment in there too: [The Register wrote it up](https://www.theregister.com/2026/04/13/claude_outage_quality_complaints/) as "Claude is getting worse, according to Claude," after the model, asked to analyse its own GitHub issues, noted a 3.5x jump in quality complaints over the January baseline. When your own product agrees it's degraded, the messaging problem is not the users.

## The harness is part of the bill

The regressions got fixed. What didn't get fixed is the underlying shape of the thing. Around July 2026 a widely-shared [Hacker News analysis](https://news.ycombinator.com/item?id=48883275) showed Claude Code sending roughly 33,000 tokens of overhead before it even reads your prompt, against about 7,000 for an alternative harness. That's measured traffic, not a vibe. You're paying for the scaffolding whether or not it helps you.

I like the model. I've shipped a lot with it. But the pattern of this period, silent downgrades to save cost, a bug that made you pay more for less, and weeks of "works fine" while independent testers logged a 47% drop, told me something about priorities. When the cheapest fix for an infrastructure crunch is to quietly turn your customers' tool down and hope they don't measure it, some of them will measure it.

A 971-point thread titled "I cancelled Claude" is what measuring it looks like at scale.

[← Newer: TIL: Finding Files Fast With fd](/til-finding-files-fast-with-fd)

[All posts](/blog) →

## Search this site

`GET https://lukeocodes.dev/search.json?q=<words>` returns matching posts as JSON, each with its page URL and its markdown URL. Add `&limit=<1-50>` for more than 10. How it works: [/blog/search](https://lukeocodes.dev/blog/search.md).

```sh
curl "https://lukeocodes.dev/search.json?q=developer+relations"
```

---

© 2026 Luke Oliff. Posts live at the root of this site.

- [GitHub](https://github.com/lukeocodes)
- [LinkedIn](https://www.linkedin.com/in/lukeocodes)
- [X](https://x.com/lukeocodes)
- [Bluesky](https://bsky.app/profile/lukeocodes.dev)
- [Email](mailto:luke@lukeoliff.com)
- [RSS](/rss.xml)

## Cookies

This site sets one analytics cookie, from Google Analytics, and only in a browser that accepts the cookie banner. A client that does not run scripts sets no cookies, so there is nothing to accept or decline here.

[Cookie policy](/cookies)
