Best of LLM — March 2023

1. 1
   Article

   Josh W Comeau·3y

   The End of Front-End Development

   GPT-4 can take a hand-drawn sketch of a website, and turn it into a fully-functional website, including a bit of JS to wire up the “Reveal Punchline” button. This is remarkable, and I think it has a lot of potential when it comes to prototyping.

   938

   103
2. 2
   Article

   Community Picks·3y

   nomic-ai/gpt4all: gpt4all: run open-source LLMs anywhere

   GPT4All is an ecosystem to run powerful and customized large language models locally on consumer grade CPUs and any GPU. It allows you to download and plug in 3GB - 8GB GPT4All model files.

   44
3. 3
   Article

   Machine Learning News·3y

   Generative AI Now Powers Shutterstock’s Creative Platform: Making Visual Content Creation Effortless

   With over 2 million contributors, Shutterstock uploads hundreds of thousands of new photos every week, resulting in a vast library of more than 424 million images and 27 million video clips. Shutterstock’s extensive library offers high-quality, licensed media in a variety of forms, including pictures, vectors, drawings, 3D models, films and music.

   11

   2
4. 4
   Article

   DEV·3y

   LLMs will fundamentally change software engineering

   Large Language Models (LLMs) have the potential to fundamentally change software engineering. They are highly useful in programming, providing autocomplete, generating code, and improving documentation. Working with LLMs can lead to shifts in software architecture, system architecture, programming practices, communication patterns, and organizational structures. The use of LLMs allows for faster code development, exploration, and prototyping, as well as continuous code review and tool building. However, there are also concerns around the quality and validity of code generated by LLMs.

   11

   1
5. 5
   Article

   Simon Willison·3y

   Large language models are having their Stable Diffusion moment

   Large language models like Stable Diffusion and LLaMA are making it possible for developers to generate images and run language models on their own hardware. This has led to an explosion of innovation in generative AI and has raised concerns about potential misuse of the technology.

   10

   1