https://erro404.dev.br/en/tags/anthropic/ Recent content in Anthropic on 404: Logic not found! Hugo en Sat, 02 May 2026 17:59:00 -0300 https://erro404.dev.br/en/posts/recent-claude-code-problems/ Sat, 02 May 2026 17:59:00 -0300 https://erro404.dev.br/en/posts/recent-claude-code-problems/ <h1 id="claude-code-when-the-problem-is-not-in-the-model-but-in-the-system-around-it"> Claude Code: when the problem is not in the model, but in the system around it <a class="heading-link" href="#claude-code-when-the-problem-is-not-in-the-model-but-in-the-system-around-it"> <i class="fa-solid fa-link" aria-hidden="true" title="Link to heading"></i> <span class="sr-only">Link to heading</span> </a> </h1> <p><img src="https://erro404.dev.br/images/claude-code-quality-layers-en.svg" alt="Infographic showing how effort, context, cache, and system prompt affected perceived Claude Code quality." loading="lazy" decoding="async" > </p> <p>In April 2026, Anthropic published a rare postmortem about a feeling that had been growing among Claude Code users: for some people, the agent simply seemed to have gotten worse. It wasn&rsquo;t an abstract complaint like &ldquo;the model is less intelligent&rdquo;. There were reports of weaker responses, repetition, forgetting context, strange tool choices, and a general impression that the product had lost some of its operational reliability.</p>