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。

eBook on building LLM system evals

17 点作者 iamwil10 个月前

2 条评论

carterdmorgan10 个月前
I love it! One of my big hesitations in using LLMs in any projects is the inherent instability of it, so I&#x27;m excited to see some concrete strategies on how to mitigate that.<p>Actually, I host a podcast called Book Overflow ([YouTube link here](<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;@BookOverflowPod" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;@BookOverflowPod</a>), but we&#x27;re on all major platforms). Each week we read and discuss a new software engineering book. We also love to interview the authors when possible. Our [interview with Brian Kernighan](<a href="https:&#x2F;&#x2F;youtu.be&#x2F;_QQ7k5sn2-o?si=bi3omgmNW7bs50NQ" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;_QQ7k5sn2-o?si=bi3omgmNW7bs50NQ</a>) actually went viral here on HN last week, peaking at #3.<p>If you&#x27;re willing to provide us with an advance copy and one&#x2F;some of the authors are willing to sit down for a digital interview, we&#x27;d love to devote a discussion episode and bonus interview episode to the book. We could even time the release to line up with the release of the book.<p>Let me know if you&#x27;re interested. We can work out the details either here in the thread or you can reach us at contact at bookoverflow.io.
评论 #40968987 未加载
sthatipamala10 个月前
One of the coauthors here. I’ll be hanging out in the thread to talk about evals.<p>I spent &gt;50% of my time designing and advising on them at one point.
评论 #40968723 未加载