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。

How to Maximize LLM Performance (Lessons from OpenAI DevDay)

7 点作者 jordn超过 1 年前

1 comment

jordn超过 1 年前
People often think that fine-tuning is what the should be aiming for. Funnest part from the talk was the story of fine tuning GPT-3.5 on the company slack so it &quot;learned their tone of voice&quot;.<p>The result:<p>&gt; Human: Write a 500 word blog post on prompt engineering &gt; AI: Sure I shall work on that in the morning&quot; &gt; Human: &quot;Do it now &gt; AI: &quot;ok&quot;
评论 #38431839 未加载