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。

Show HN: Acting as Claude's Research Helper in AI (Sheaf Cohomology and LLMs)

2 点作者 eigenvalue5 个月前
I had a blast writing this blog post and learned a tremendous amount. I suspect that we will soon see a blizzard of papers where the researcher&#x2F;author isn&#x27;t just &quot;assisted&quot; by really smart AI models, but rather where the human author becomes more of a research assistant&#x2F;facilitator! That is, the model itself would dictate the core direction the research should take, with some feedback and input from the human researcher to keep things on track and focused.<p>The human becomes more of a &quot;token dispenser&quot; and also facilitates cooperation between AI models from different labs (i.e., Claude 3.5 Sonnet and O1-Pro, which I had working together by the end of this).<p>If anyone reading this is an expert, I&#x27;d love to hear your take on whether these ideas have real merit. I suspect they do, since O1-Pro certainly thought so, and I would guess that it would be skeptical of ideas that it knew were generated by its arch-rival, Claude!

1 comment

pvg5 个月前
Blog posts and similar reading material can&#x27;t be Show HN&#x27;s, which is a special category with its own funny rules, take a look at <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;showhn.html">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;showhn.html</a>
评论 #42520303 未加载