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

Deel Acquires Deepfake Technology Startup Clarity to Enhance Global HR Security
Industry News

Deel Acquires Deepfake Technology Startup Clarity to Enhance Global HR Security

US-based HR and payroll platform Deel has announced the acquisition of Clarity, a startup specializing in deepfake technology. Founded in 2022, Clarity had quickly gained traction in the tech space, securing $16 million in funding from investors prior to the acquisition. This strategic move by Deel highlights the growing importance of addressing synthetic media and identity verification challenges within the human resources and remote work sectors. By integrating Clarity’s specialized capabilities, Deel aims to bolster its security infrastructure against the rising threat of deepfakes in digital hiring and corporate communications. The acquisition underscores a significant trend of HR platforms investing in advanced AI-driven security tools to protect global operations.

Indian AI Startup Kily Secures $3.1 Million in Funding to Scale Operations and Brand Partnerships
Industry News

Indian AI Startup Kily Secures $3.1 Million in Funding to Scale Operations and Brand Partnerships

Kily, an emerging Indian AI startup founded in 2025, has successfully raised $3.1 million in its latest funding round. Despite being a relatively new player in the technology sector, the company has already demonstrated significant market traction by securing strategic partnerships with major industry leaders, most notably the Indian conglomerate ITC. This capital injection marks a pivotal milestone for the young firm as it seeks to establish its presence in the rapidly evolving artificial intelligence landscape. The funding highlights strong investor confidence in Kily's potential and its ability to deliver value to high-profile enterprise clients within a short period since its inception.

Why Domain Expertise is the Ultimate Skill for Mastering Large Language Models and Prompting
Industry News

Why Domain Expertise is the Ultimate Skill for Mastering Large Language Models and Prompting

While Large Language Models (LLMs) have democratized technical tasks, turning many users into generalists, a common misconception persists that prompting requires little specialized skill. However, recent analysis suggests that domain expertise remains the critical factor in achieving high-level results. By examining world-class mathematician Terence Tao’s interactions with GPT-5.6 Sol regarding the Jacobian Conjecture, it becomes clear that expert-level prompting involves concise communication, signaling deep knowledge to trigger specialized model responses, and maintaining control over the direction of the inquiry. Unlike amateurs who may follow the model's lead, experts like Tao use LLMs as tools to refine their own insights, proving that the value of an LLM is directly proportional to the user's existing knowledge in the field. Ultimately, LLMs do not replace expertise; they reward it.