Anthropic Rolls Back Claude Code Changes After Quality Decline; All Fixes Complete

Gate News message, April 24 — Anthropic has acknowledged a recent decline in Claude Code quality and confirmed that all related issues have been resolved through rollbacks and fixes. The problems stemmed from three product and prompt adjustments made between early and mid-April.

On March 4, the default reasoning effort was reduced from high to medium, which degraded performance until it was restored to high/xhigh on April 7. On March 26, a bug was introduced in the clear_thinking_20251015 logic designed to optimize caching, causing the system to lose reasoning history during extended idle periods and leading to memory loss and repetition; this was fixed in version 2.1.101 on April 10. Most recently, on April 16, a system prompt was added to compress output (limiting responses to ≤25/100 words), which resulted in approximately 3% negative impact on code quality; this change was rolled back on April 20.

Anthropric stated that the API reasoning layer was not affected by these issues. The company has also reset usage quotas for all subscribers.

Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to Disclaimer.

Related Articles

SpaceX, OpenAI, and Anthropic IPOs Could Attract Over $240 Billion, Potentially Impacting Crypto Market Liquidity

Gate News message, April 25 — According to market reports, SpaceX is expected to go public in June with a fundraising target exceeding Saudi Aramco's record $29 billion IPO, while OpenAI and Anthropic are planning to list in the second half of 2026. The three companies are projected to

GateNews26m ago

DeepSeek-V4 Preview Released with 1M Context Window, Huawei DCS AI Solution Provides Full Support

Gate News message, April 25 — DeepSeek-V4 preview version has been officially released and open-sourced, featuring an expanded context window of 1 million tokens and introducing KV Cache sliding window with

GateNews1h ago

GPU Shortage Returns as Microsoft, Amazon Tighten Supply; AI Startups Face 32% Price Hike and Year-End Queues

Gate News message, April 25 — A GPU shortage is resurfacing as major cloud providers including Microsoft and Amazon concentrate computing capacity toward internal teams and major customers like OpenAI and Anthropic, leaving smaller AI startups facing price increases, extended wait times, and stricte

GateNews2h ago

Nvidia Deploys OpenAI Codex AI Agent Across Entire Workforce on Blackwell Infrastructure

Gate News message, April 25 — Nvidia has rolled out OpenAI's Codex, an AI agent powered by GPT-5.5, to its entire workforce following a successful trial with approximately 10,000 employees, according to internal communications from CEO Jensen Huang and OpenAI CEO Sam Altman. Codex is designed to as

GateNews3h ago

US State Dept Warns on DeepSeek AI Model Distillation

The US State Department issued a cable on April 24 to diplomatic and consular posts worldwide warning foreign governments about Chinese efforts to copy American AI systems through distillation, according to Reuters. The cable

CryptoFrontier3h ago

Stanford Professor's Health AI Startup Seeks $100M at $1B Valuation

Gate News message, April 25 — Stanford professor James Zou is raising approximately $100 million for Human Intelligence, a California startup developing AI models for human physiology, at a valuation of roughly $1 billion. The company builds on Zou's research in physiology and AI. His lab's

GateNews3h ago
Comment
0/400
No comments