Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
hachyderm.io is one of the many independent Mastodon servers you can use to participate in the fediverse.
Hachyderm is a safe space, LGBTQIA+ and BLM, primarily comprised of tech industry professionals world wide. Note that many non-user account types have restrictions - please see our About page.

Administered by:

Server stats:

9.6K
active users

hachyderm.io: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.5

#promptengineering

6 posts5 participants0 posts today
Public
Jason Yip

A Prompt Pattern Catalog to Enhance #PromptEngineering with #ChatGPT arxiv.org/abs/2302.11382

arXiv logo
arXiv.orgA Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTPrompt engineering is an increasingly important skill set needed to converse effectively with large language models (LLMs), such as ChatGPT. Prompts are instructions given to an LLM to enforce rules, automate processes, and ensure specific qualities (and quantities) of generated output. Prompts are also a form of programming that can customize the outputs and interactions with an LLM. This paper describes a catalog of prompt engineering techniques presented in pattern form that have been applied to solve common problems when conversing with LLMs. Prompt patterns are a knowledge transfer method analogous to software patterns since they provide reusable solutions to common problems faced in a particular context, i.e., output generation and interaction when working with LLMs. This paper provides the following contributions to research on prompt engineering that apply LLMs to automate software development tasks. First, it provides a framework for documenting patterns for structuring prompts to solve a range of problems so that they can be adapted to different domains. Second, it presents a catalog of patterns that have been applied successfully to improve the outputs of LLM conversations. Third, it explains how prompts can be built from multiple patterns and illustrates prompt patterns that benefit from combination with other prompt patterns.
Public
Anant Shrivastava aka anantshri

As AI tools become part of our daily workflows, a weird duality is emerging:

👨‍💻 Developers are fluent in code but not always in natural language.
They know what they want the AI to do… but struggle to phrase it in a way that gets the right output.

Fluent in Python, broken in English.

🧑‍🏫 Non-developers can explain ideas and goals clearly…
But they don’t know the “magic keywords” that trigger the right AI response.

Great at asking, missing the insider lingo.

Now throw in the final twist:
🎲 AI responses aren’t deterministic.
You might get a different answer every single time for the same prompt.

So what we have is:
🔹 Two groups of experienced people
🔹 Learning a new language (prompting)
🔹 To talk to a system that behaves like a moody oracle.

We’re not just learning to "code with AI" — we’re learning how to communicate with it.
And that's a whole new skill in itself.

#AI#PromptEngineering#DevLife
Public
Yuna

AI Will Replace Engineers? 🤖
Oh, sweet summer child…

AI isn’t thinking. It’s autocomplete on steroids.
It guesses confidently, fails quietly, and we pretend it’s magic.

Engineers won’t be replaced.
They’ll be cleaning up AI’s mess.

But sure, dream of your AI CEO…
Full Post: linkedin.com/posts/yuna-morgen

An engineer asking 8-Ball where to put the next card on the house of cards
#AI#SoftwareEngineering#PromptEngineering
ExploreLive feeds
About