问 HN：Claude 变差了吗？
5 分•作者: sahli•4 个月前
感觉大多数 Claude Code 用户已经注意到 Claude 模型质量下降了。作为一名 Claude Pro 用户（网页版；我不使用 Claude Code），在过去几周里，我明显感觉到了质量下降。现在我无法再一次性完成任务了。Claude 经常因为达到某些内部的工具调用/轮次限制而停止生成，所以我不得不反复点击“继续”。每次继续都需要重新输入上下文，这很快就会耗尽 token 和配额。模型也更容易出错，并且无法完全完成它曾经可靠处理的任务。
这尤其令人沮丧，因为 Sonnet 4.6 确实是一个进步：它能够更频繁地一次性生成长而正确的代码。但现在看来，这种能力基本消失了。
作为一名付费 Pro 用户，我发现自己最近使用 DeepSeek 和 Z.ai (GLM) 等免费替代方案的频率比 Claude 还高。我也完全停止使用 Opus 了——它太消耗 token 了，以至于它会迅速耗尽我的每周配额，这很不实用。
Anthropic 是想限制使用量还是想赶走用户？
查看原文
It feels like most Claude Code users have already noticed a quality drop in the Claude models. As a Claude Pro subscriber (Web version; I don't use Claude Code), I’ve seen a clear decline over the last couple of weeks. I can’t complete tasks in a single turn anymore. Claude often stops streaming because it hits some internal tool-call/turn limit, so I have to keep pressing “Continue.” Each continuation has to re-feed context, which quickly burns through tokens and quota. The model also makes more mistakes and fails to fully complete tasks it used to handle reliably.<p>This is especially frustrating because Sonnet 4.6 was a real step up: it could produce long, correct code in one pass much more often. That seems basically gone now.<p>As a paying Pro user, I honestly find myself using free alternatives like DeepSeek and Z.ai (GLM) more than Claude lately. I’ve also stopped touching Opus entirely—it’s so token-hungry that it drains my weekly quota too fast to be practical.<p>Is Anthropic trying to limit usage or drive people away?