提问 HN：你们都在用哪些 LLM 模型，以及为什么？
1 分•作者: rubyn00bie•大约 2 个月前
大家好，HN！
我想知道大家最近都在用什么作为日常主力，以及为什么？
我发现自己现在工作上用 GPT-5.5 的频率比 Opus 4.7 还要高，这可是个大转变。之前，我一直用 Opus 4.6 处理所有事情，GPT-5.4 只是用来提供第二种意见（Grok 只能排第三，只有我想搞点“混乱”的时候才会用）。我个人之所以转变，是因为我发现 GPT-5.5 更稳定、更可预测，而且它的写作方式让我觉得不那么累（即使代码不如 Opus 4.7 那么好）。
对于个人项目，我开始尝试 DeepSeek V4，它在性价比方面给我留下了深刻印象，而且我发现 100 万 token 的窗口对于长时间运行的任务非常有帮助。尽管我可能对任务期间的压缩问题有些过分担心。DeepSeek 在一次性完成任务方面不如 GPT-5.5 或 Opus-4.7，但有了足够的代码检查器/静态分析保护措施，我发现真的很难抱怨或挑毛病（尤其是在这个价格下）。
最后，如果你也在使用重新排序和/或嵌入模型，或者其他任何东西来增强或执行特定任务，也请分享一下！
查看原文
Hello, HN!<p>I'm wondering what y'all are using for your daily driver these days and <i>why</i>?<p>I've found myself using GPT-5.5 more than Opus 4.7 for work; which, has been a pretty big reversal. Previously, I was using Opus 4.6 for everything, and GPT-5.4 was only ever in the picture to provide a second opinion (with Grok a distant 3rd only when I wanted to throw some "chaos" into the mix). The reason I've personally pivoted, is I've found GPT-5.5 to be a bit more consistent, predictable, and tends to write in a way I find less tiresome (even if the code isn't quite as good as Opus 4.7).<p>For personal projects, I've started experimenting with DeepSeek V4 and have been pretty blown away by it because of it's cost to quality and I've found the 1M token window to be incredibly helpful for long-running tasks. Though I may also have an over abundance of fear of compaction during tasks. DeepSeek isn't quite as good at one-shotting things as either GPT-5.5 or Opus-4.7, but with sufficient linter/static-analysis guardrails I've found it's really hard to complain or find faults (especially at the price).<p>Finally, if you're also making use of reranking and/or embedding models, or anything else, to augment or perform specific tasks please share those too!