We are excited to launch a new web version of the prompt engineering guide. https://www.promptingguide.ai/ Includes lectures, notebooks, guides, and the latest papers for AI researchers and developers. Check it out! With this web version, we aim to make the guide more accessible. The content still lives in our repo with 14K ⭐ . https://github.com/dair-ai/Prompt-Engineering-Guide We added a new section on models like GPT-4 and ChatGPT to highlight the capabilities and limitations of these models and how to make the […]

Hi all! It’s finally here! Excited to finally publish our ~1 hour special lecture on prompt engineering techniques, applications, and much more. It includes code examples, exercises, and slides.  The lecture is divided into four parts: Part 1 — Introduction to Prompt Engineering Part 2 — Advanced Techniques for Prompt Engineering  Part 3 — Tools and Applications Part 4 — Conclusion and Future Directions Notebook:

Let’s take a look at some of the top trending ML papers of 2022: 1) A ConvNet for the 2020s (Liu et al) — Vision Transformers took off this year but this work proposes ConvNeXt to reexamine the design spaces and test the limits of a pure ConvNet on several vision tasks. The ConvNets vs. Transformers debate continues. 2) Language Models as Zero-Shot Planners (Huang et al) — studies the possibility of grounding high-level tasks to actionable steps for embodied […]

The way we interact with large language models (LLMs) is evolving and always improving. Current approaches include a lot of prompt engineering to make LLMs effective at different tasks. This may change in the future but developers and researchers are still figuring out new ways that involve clever prompting of LLMs. To help with learning about prompt engineering, I am excited to publish the Prompt Engineering Guide, a new repo for discovering papers, guides, tools, and datasets. This is intended […]

Models that allow interaction via natural language have become ubiquitious. Research models such as BERT and T5 have become much more accessible while the latest generation of language and multi-modal models are demonstrating increasingly powerful capabilities. At the same time, a wave of NLP startups has started to put this technology to practical use. While such language technology may be hugely impactful, recent models have mostly focused on English and a handful of other languages with large amounts of resources. […]