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。

We've Been Conned: The Truth about Big LLM

6 点作者 midzer25 天前

2 条评论

joegibbs25 天前
It could be $98&#x2F;hour but you&#x27;re splitting that up between multiple users. You don&#x27;t run the instance entirely for an hour, you run it for a few seconds 20-50 times in the hour. If you had Claude spitting out tokens for an hour straight you&#x27;d run up a crazy bill.<p>It would be uneconomical to run Llama 3 14B on a bunch of A100s unless you&#x27;re actually going to be using all that throughput. You can run Llama 3 8B locally no problem at all on regular consumer hardware with good speeds.
Hackbraten25 天前
I know it&#x27;s not the point of the article, but anyway: why does the author even allow their IDE to suggest them auto-completion while editing natural language text?<p>If they hate it so much, why don&#x27;t they turn it off once and for all?