Back to List
Anthropic Addresses Claude Code Quality Degradation Reports and Implements Fixes for Sonnet and Opus Models
Industry NewsAnthropicClaudeAI Engineering

Anthropic Addresses Claude Code Quality Degradation Reports and Implements Fixes for Sonnet and Opus Models

Anthropic has released a postmortem addressing recent user reports regarding the degradation of Claude's performance across specific tools, including Claude Code, the Claude Agent SDK, and Claude Cowork. The investigation identified three distinct technical issues occurring between March and April 2026: an intentional but poorly received reduction in reasoning effort to manage latency, a session-clearing bug that caused repetitive behavior and memory loss, and a system prompt change aimed at reducing verbosity that inadvertently harmed coding quality. While the API remained unaffected, these issues impacted Sonnet 4.6, Opus 4.6, and Opus 4.7. Anthropic has since reverted the problematic changes and fixed the bugs as of April 20 (v2.1.116), emphasizing their commitment to maintaining model intelligence over speed.

Hacker News
Share

Key Takeaways

  • Three Distinct Issues Identified: The perceived degradation was caused by a change in reasoning effort, a session-clearing bug, and a system prompt instruction to reduce verbosity.
  • Specific Tools Affected: Issues were limited to Claude Code, the Claude Agent SDK, and Claude Cowork; the core API and inference layer were not impacted.
  • Models Impacted: The performance dips affected Sonnet 4.6, Opus 4.6, and Opus 4.7 across different timeframes.
  • Full Resolution: All identified issues were resolved as of April 20 with the release of version 2.1.116.

In-Depth Analysis

Reasoning Effort and Latency Trade-offs

On March 4, Anthropic attempted to address UI latency issues where the interface appeared frozen by changing the default reasoning effort from "high" to "medium." While this was intended to improve the user experience by reducing wait times, it resulted in a noticeable drop in intelligence for Sonnet 4.6 and Opus 4.6. Following user feedback indicating a preference for higher intelligence over speed, Anthropic reverted this change on April 7. The company acknowledged that prioritizing lower latency at the expense of reasoning quality was the "wrong tradeoff."

Technical Bugs and Prompting Side Effects

Two additional technical factors contributed to the degradation. On March 26, a feature designed to clear old thinking from idle sessions to improve resumption speed introduced a bug. This bug caused the system to clear thinking every turn, making the models appear forgetful and repetitive. Furthermore, an April 16 update to the system prompt intended to reduce verbosity negatively impacted coding quality when combined with other prompt adjustments. This specific issue affected the latest models, including Opus 4.7. Both the bug and the prompt changes were corrected and reverted by April 20.

Investigation Challenges and Aggregate Effects

Anthropic noted that because these three changes occurred on different schedules and affected different segments of traffic, the resulting feedback appeared as broad and inconsistent degradation. The investigation began in early March but was complicated by the difficulty of distinguishing these specific technical failures from the normal variation in user feedback. The company has reaffirmed that they never intentionally degrade models and are implementing changes to prevent similar regressions in the future.

Industry Impact

This incident highlights the delicate balance AI providers must maintain between model "intelligence" (reasoning effort) and operational performance (latency). For the AI industry, it serves as a case study in how minor optimizations—such as reducing verbosity or clearing session cache—can have significant, unintended consequences on the quality of complex tasks like coding. Anthropic's transparent postmortem underscores the importance of user feedback loops in identifying non-obvious regressions that automated testing might miss, particularly when those regressions are tied to UI-specific implementations rather than the underlying API.

Frequently Asked Questions

Question: Was the Claude API affected by these quality issues?

No. Anthropic confirmed that the API and inference layer remained unaffected throughout this period; the issues were isolated to Claude Code, the Claude Agent SDK, and Claude Cowork.

Question: Which Claude models were impacted by the performance degradation?

The issues affected Sonnet 4.6, Opus 4.6, and Opus 4.7, depending on the specific technical change and the timeframe.

Question: How has Anthropic resolved these issues?

As of April 20 (v2.1.116), Anthropic has reverted the reasoning effort to "high," fixed the session-clearing bug, and removed the system prompt instructions that were harming coding quality.

Read Original Article

Related News

Uber Implements $1,500 Monthly Spending Cap on AI Coding Tools for Employees
Industry News

Uber Implements $1,500 Monthly Spending Cap on AI Coding Tools for Employees

Uber has introduced a new financial policy regarding the use of artificial intelligence in its software development processes. According to recent reports, the company has established a $1,500 monthly cap on the use of AI coding tools per employee. This measure is designed to manage the costs associated with these advanced technologies while maintaining developer productivity. However, the policy is not a hard limit; Uber has instituted a formal procedure where employees can request specific approval to exceed this $1,500 threshold. This move reflects a growing trend among major tech firms to implement structured governance and cost-control measures over the rapidly expanding suite of AI-powered development resources available to their engineering teams.

Palo Alto Networks Raises 2026 Financial Outlook as AI Demand Accelerates Amid Security Fragmentation
Industry News

Palo Alto Networks Raises 2026 Financial Outlook as AI Demand Accelerates Amid Security Fragmentation

Palo Alto Networks has officially updated its financial projections for 2026, signaling a significant upward revision driven by the surging demand for Artificial Intelligence (AI) in the cybersecurity sector. This strategic shift comes as organizations grapple with unprecedented levels of infrastructure complexity. Current industry data reveals that the average organization is currently managing 83 different security solutions sourced from 29 distinct vendors. This extreme fragmentation has created a critical need for consolidated, AI-driven platforms that can streamline operations and enhance threat detection. By lifting its long-term outlook, Palo Alto Networks highlights the growing market transition toward integrated security architectures that leverage AI to manage the burden of multi-vendor environments. The company's revised forecast reflects a broader industry trend where AI is no longer an optional feature but a fundamental requirement for modern enterprise defense.

Australia’s Megaport Secures $593 Million Raise to Launch Global AI Inference Cloud
Industry News

Australia’s Megaport Secures $593 Million Raise to Launch Global AI Inference Cloud

Megaport, the Australian-based network service provider, has successfully secured a $593 million capital raise alongside new strategic AI-focused deals. A primary component of this financial milestone is the company's plan to invest A$350 million into the development of a globally distributed AI inference cloud. This move signifies a major strategic expansion for Megaport, aiming to provide the essential infrastructure required for low-latency AI processing on a global scale. By leveraging its networking expertise, Megaport intends to address the growing demand for localized AI compute capabilities, positioning itself as a pivotal player in the rapidly evolving artificial intelligence infrastructure market.