Prompt-Engineering-Guide

There are better guides out there too - https://www.promptingguide.ai/readings - https://github.com/dair-ai/Prompt-Engineering-Guide/tree/mai... - https://github.com/microsoft/promptbase (this one is less of a guide, but is likely the current SoTA)

- https://arxiv.org/ - https://www.microsoft.com/en-us/research/group/dynamics-insights-apps-artificial-i… - https://cloud.google.com/blog/products/ai-machine-learning/how-to-use-grounding-fo… - https://amatriain.net/blog/hallucinations and general resources: - https://learnprompting.org - https://www.promptingguide.ai - https://github.com/dair-ai/Prompt-Engineering-Guide

You can make a nice habit of checking sources like https://news.bensbites.co + also his newsletter news.niek.ai ( is a search with ai as a filter ) https://github.com/dair-ai/Prompt-Engineering-Guide ( made an easy to remember synced repo link at ai.niek.ai ) A few times a day checking Hackernews top 60 & occasionally sifting through the "New" page. ( Not efficient, but kinda works ) Also keeping an eye on Twitter, following OpenAI, but also the companies like StabilityAI, Deepmind etc. + the model generation ( e.g. Llama offsprings, Midjourney, Stable Diffusion ) & following AI Researchers in and around these projects.

Here are some links https://github.com/dair-ai/Prompt-Engineering-Guide https://lilianweng.github.io/posts/2023-03-15-prompt-enginee...

I assume the OP is leaving out the part about something called prompt engineering which has a bit of a learning curve. I'm going to have to dive in to it myself, as it seems like a bit of self-education is required before it can be simply communicated. Some information here : https://github.com/dair-ai/Prompt-Engineering-Guide/blob/mai...

Does anyone know where the other interface for ChatGPT is located? Aka the one where you have 'System' and 'User' on the right. Aka, this interface: https://github.com/dair-ai/Prompt-Engineering-Guide/blob/main/img/chatgpt-1.png I have a Plus account, not sure if that's required, or maybe this is an internal interface not available to the public?

I read the introduction [0] to prompt engineering in the [4] (above), and am confused, isn't it just common sense. To be honest I didn't dig deep, but the introduction [0] seems obvious stuff. Am I missing something? [0] https://github.com/dair-ai/Prompt-Engineering-Guide/blob/mai...

What are the steps I should be taking now to take advantage of AI as a developer? So far I've been using it to replace Google, generate boilerplate code, generate example code for working with an API, and just bouncing ideas off of it. I've been collecting several resources that seem useful (besides ChatGPT). I've been wanting to understand these technologies deeper [1, 2, 3]. Are there other resources that are recommended? Should I be learning more about prompt engineering? [4] [1]: https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-… [2]: https://www.fast.ai/ [3]: https://karpathy.ai/zero-to-hero.html [4]: https://github.com/dair-ai/Prompt-Engineering-Guide

>Notably, chain of thought (CoT) prompting, a recent technique for eliciting complex multi-step reasoning through step-by-step answer examples, achieved the state-of-the-art performances in arithmetics and symbolic reasoning, difficult system-2 tasks that do not follow the standard scaling laws for LLMs https://arxiv.org/abs/2205.11916 >https://sites.google.com/view/automatic-prompt-engineer Not exactly a "toaster go brrrr" job, but it could be obsolete one day WaPo does need to chill though. There’s barely any Prompt Engineer jobs Edit: If anyone's curious, I've been following this for prompt stuff: https://github.com/dair-ai/Prompt-Engineering-Guide

Proper prompt engineering would likely involve finding emergent properties like this: https://github.com/dair-ai/Prompt-Engineering-Guide/blob/mai... (this is claimed for LLMs, not proven) It only seems like a trick until enough papers get written about these kinds of findings.