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。

Solving Problems in AI: LLM Explainability, Hallucinations and More [video]

1 点作者 filoeleven5 个月前

1 comment

filoeleven5 个月前
The first speaker in the video works at or started <a href="https:&#x2F;&#x2F;neocortix.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;neocortix.com&#x2F;</a> where, by &quot;doing surgery&quot; on LLAMA, he is able to have the AI recognize when it&#x27;s reaching for facts, then find the actual reference in the training data set and quote it directly.<p>I&#x27;d have linked the site instead of a video, but the site doesn&#x27;t have too much info while in the video he shows a grokkable breakdown of how it works.