探索编写提示词的乐趣:蒙特卡洛方法、木偶剧和笑声的融合

Article Title Card, “How It’s Made. Monte Carlo, Puppetry and Laughter: The Unexpected Joys of prompt Engineering”. The Instacart logo is present in the lower left, and a html empty end tag to represent coding takes the right hand side of the image.

The universe of the current Large Language Models (LLMs) engineering is electrifying, to say the least. The industry has been on fire with change since the launch of ChatGPT in November of Last year. We’re all seeing the rise of AI tooling across the entire industry, and it’s opening up product and development possibilities at an astounding rate.

当前大型语言模型(LLMs)工程的世界令人兴奋,可以这么说。自去年11月ChatGPT发布以来,该行业一直在变革中。我们都看到了整个行业AI工具的崛起,以惊人的速度开启了产品和开发的可能性。

Instacart has been adopting LLMs and GenAI at a breakneck pace: just take a look at our internal assistant Ava, our superpowered AI search Ask Instacart, or the innovation in our ML Platforms. We’ve been exploring use cases, capabilities, and most importantly how to get value for our employees, customers, merchants, and shoppers.

Instacart一直以极快的速度采用LLMs和GenAI:只需看看我们的内部助手Ava,我们强大的AI搜索Ask Instacart,或者我们在ML平台上的创新。我们一直在探索用例、能力,最重要的是如何为我们的员工、客户、商家和购物者创造价值。

Anyone who has worked with some of these models knows that this emerging tech has limitless possibilities; Possibilities that are currently constrained by a number of challenges: from context size issues, to hallucinations, to models that just don’t seem to be able to complete the tasks you set for them.

任何与这些模型一起工作过的人都知道,这种新兴技术有着无限的可能性;目前受到一系列挑战的限制:从上下文大小问题到幻觉,再到模型似乎无法完成您为其设定的任务。

Fortunately, there are a number of techniques to help you in building products with LLMs. This article explores some of these techniques and, hopefully, really opens your mind to more possibilities!

幸运的是,有许多技术可以帮助您构建具有LLM的产品。本文探讨了其中一些技术,并希望真正开拓您的思维,为您带来更多可能性!

A quick aside here: all of these prompt techniques have been implemented and used with GPT-4. Some have also been used with GPT-3.5. GPT-4 is currently the best-in-class conversational model, and is far superior to GPT-3.5 and all other conversational models. I highly recommend using GPT-4 if it at all makes sense economically for your use case.

这里有一个小插曲:所有这些提示技术都已经在GPT-4中实施和使用。其中一些也已经在GPT-3.5中使用。GPT-4目前是最佳的对话模型,远远优于GPT-3.5和所有其他对话模型。如果在经济上对您的用例有意义,我强烈推荐使用GPT-4。

This article will be an exploration ...

开通本站会员,查看完整译文。

Home - Wiki
Copyright © 2011-2024 iteam. Current version is 2.139.0. UTC+08:00, 2024-12-23 00:43
浙ICP备14020137号-1 $Map of visitor$