August 6th, 2024
GitHub v Hugging Face
This newsletter was brought to you byAssemblyAIHello! Aaron here, bringing you your daily update on all things tech. In todayâs digest, Iâm covering GitHub's new AI tool, which aims to compete with HuggingFace, Azure, and others. But firstâŚ
The headlines:Â
đ One of the OpenAI cofounders has announced heâs leaving for Anthropic.Â
đ Google has lost a potentially massive antitrust case over the companyâs dominance.
đŚ In an email from its CEO, X has announced it is closing its San Francisco office.
GitHubâs newest feature makes it easier to test and build with different AI models

GitHub has just introduced GitHub Models, a new feature designed to let developers dive into generative AI without leaving their coding environment. This handy addition integrates directly with GitHub Codespaces and Visual Studio Code, allowing developers to experiment and build with AI models in one platform.
With GitHub Models, you can explore some of the biggest models like Meta's Llama 3.1, OpenAI's GPT-4o and GPT-4o mini, Cohere's Command, and Mistral AI's Mistral Large 2, alongside other lesser known ones. Itâs all about making it easier for developers to play around with these models, test different setups, and see what worksâall without the need for complex setups or additional tools.
What sets GitHub Models apart is its accessibility. Unlike platforms that cater to enterprise clients with more complicated workflows, GitHub Models is straightforward and available to everyone. Itâs good for quickly trying out ideas or just getting a feel for what these AI models can do.
This feature isn't just for the pros. GitHub Models is also finding its way into classrooms, with the company announcing that Harvard's Professor David J. Malan is planning to incorporate it into the CS50 course.Â
Currently, GitHub Models is in a limited public beta, so you'll need to sign up for the waitlist if you want to get early access. This release is part of Microsoft's larger goal to make AI more accessible and easy to use.Â
You prompt your LLMs, why not your speech-to-text?

AssemblyAIâs Universal-3 Pro introduces a new class of promptable speech modelsâbuilt for real-world Voice AI. It handles domain-specific language, multiple languages, accents, and noisy audio with ease.
Unlike traditional ASR, Universal-3 Pro lets developers guide accuracy with prompts, combining the reliability of speech recognition with the controllability of LLMsâso youâre not stuck fixing transcripts after the fact.
AssemblyAI is opening free access throughout February, and the Product Hunt community is among the first to try what promptable ASR can do.
đ Try Universal-3 Pro for free
Daily Top Products








DEVELOPER TOOLSÂ
Frontend AI generates your front-end UI code with the help of UI. Drop in a prompt or paste a design of what it should look like, and it will output usable code.Â
Shepherd Pro guides your users to the a-ha moment of your application with customizable in-app journeys that you can build in no time.
LIFE TOOLSÂ
flickd is an app for film and TV enthusiasts to come together to connect, discuss, track what they watch, and get recommendations from other.
Intimal is a platform for AI-mediated romantic relationships. It's like your relationship coach. You can get AI suggestions to improve your romantic life, analyze your current or past relationships and find out how to connect.
JOB HUNTING TOOLSÂ
Codei AI helps you land your dream coding job. You can track applications, generate role-specific coding questions for practice, and upload GitHub solutions for feedback.
Monday through Friday
Our ultra-fast Daily: Three takes on new products. Yesterdayâs top ten launches. Thatâs it.
