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。

Creating personalised data stories with GPT-3

47 点作者 ColinEberhardt超过 3 年前

4 条评论

cryptoz超过 3 年前
A good article, I appreciate all the discussion on prompts too. However the author is a bit too underestimating of the language model and math:<p>&gt; GPT-3 is quick to learn that the narratives should include these comparisons, but often gets the maths wrong:<p>&gt; &gt; During these runs he has climbed 62,599 feet, that’s the equivalent of climbing Mount Everest six times (but a bit less steep)<p>&gt; Everest is ~29,000 feet, so this runner has climbed Everest roughly twice.<p>I think it&#x27;s the author here who gets the math wrong. An Everest climb is closer to 10,000 feet, making the GPT-3 math alarmingly accurate.
评论 #29508314 未加载
评论 #29502733 未加载
amelius超过 3 年前
All I want is a tool that allows me to input dull text in bulletlist format, and then converts it faithfully into paragraphs of beautiful prose.<p>So basically like running a summarizer in reverse.
评论 #29504859 未加载
评论 #29506493 未加载
savant_penguin超过 3 年前
To anyone who knows about the subject, what is the best gpt-like model you can still run in a laptop? (With about 16gb of ram, or 3gb-8gb of vram)
评论 #29502289 未加载
thewarrior超过 3 年前
Do this for peoples stock portfolios and you have a good startup idea right there.<p>Or you could digest financial, health and content consumption data to create a personalized report with action items.<p>Very promising.
评论 #29503943 未加载