TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

DeepSeek Laconic Decoding

1 点作者 svenfaw3 个月前

2 条评论

eternityforest3 个月前
Can we weight the sampling based on a prediction of how long an answer will be?<p>Like with another model that just says &quot;Oh boy that word sounds like the beginning of an essay of nonsense, I don&#x27;t think that&#x27;s what I want to say&quot;?
svenfaw3 个月前
&quot;Discovered a very interesting thing about DeepSeek-R1 and all reasoning models: The wrong answers are much longer while the correct answers are much shorter.&quot;