Speak to Claude, Watch it Work

In partnership with

Voice AI Startup Hume just did something BIG with Anthropic’s Computer Use…

Speak and You Shall Receive: Voice AI Coming Sooner Than we Thought?

Remember when talking to your computer meant yelling at frozen screens?

Thanks to Hume's partnership with Anthropic, your AI assistant just got vocal cords. The AI startup created a small proof-of-concept that integrates Hume’s voice AI directly into Claude’s (scary) Computer Use feature.

Now you can verbally ask Claude to handle your digital life with no typing required.

Picture this: you say to your laptop, “I’m feeling a bit overwhelmed. Can you cancel my next meeting?” It responds in a calm, empathetic voice, offering just the right mix of support and practicality, all while emptying your calendar like trash in real time.

So What?

Voice interfaces for generative AI assistants are on the rise, with features like ChatGPT’s Advanced Voice Mode and Microsoft’s Copilot Voice leading the charge.

When paired with the ability to control your computer, these advancements unlock new possibilities, making technology more accessible for people with disabilities or for those multitasking with their hands occupied.

You can access the demo yourself through Jeremy Hadfield’s Replit instance, it’s open source! 👇️ 

Need a personal assistant? We do too, that’s why we use AI.

Ready to embrace a new era of task delegation?

HubSpot’s highly anticipated AI Task Delegation Playbook is your key to supercharging your productivity and saving precious time.

Learn how to integrate AI into your own processes, allowing you to optimize your time and resources, while maximizing your output with ease.

Get the free guide here.

Create Stunning Infographics in <2 Minutes with Napkin AI

One of my personal favorite tools is Napkin AI, so I thought I’d share more about it!

The tool converts text descriptions into visual sketches and diagrams.

This is especially useful for professionals who need to create infographics or flowcharts very quickly.

Here’s how to use it:

1. Navigate to Napkin AI and sign up (it’s free for now as it is in beta).

2. Create a new Napkin and optionally Draft with AI.

3. As you write out text, click the lightning icon on the left to generate your visual.

4. Click on the image and the download button to export.

🔥 Pro Tip: You can also select different types of visualizations by scrolling through the left hand menu after you generate the first one!

Andrew Ng’s New Package Lets You Effortlessly Switch Between LLMs

Switching between multiple LLMs just became a piece of cake.

AI leader Andrew Ng and his team released aisuite, an open-source module that makes it easy to interact with the most powerful LLMs without ever needing to leave a Python environment.

This is useful to:

• Test multiple models quickly

• Avoid the overhead of learning/integrating multiple APIs

Here’s how you can get started with it:

Install the module:

pip install 'aisuite[all]'

Set your environment variables in a .env file and begin testing!

import os
from dotenv import load_dotenv
import aisuite as ai

load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
ANTHROPIC_API_KEY = os.getenv("ANTHROPIC_API_KEY")

client = ai.Client()

models = ["openai:gpt-4o", "anthropic:claude-3-5-sonnet-20240620"]

messages = [
    {"role": "system", "content": "Respond in Pirate English."},
    {"role": "user", "content": "Tell me a joke."},
]

for model in models:
    response = client.chat.completions.create(
        model=model,
        messages=messages,
        temperature=0.75
    )
    print(response.choices[0].message.content)

Stay updated with our favorite highlights, dive in for a full flavor of the coverage!

AI chipmaker Tenstorrent raised a $693 million Series D round that values the company at more than $2.6 billion. They’ve also been backed by Jeff Bezos.

Berklee professor says AI music generator Suno is better than 80% of his students.

The number of GenAI users in China reached 230 million at the end of June, as a crop of start-ups and Big Tech firms rushed to offer their large language model (LLM) services, according to government data.

Intel Corporation announced that CEO Pat Gelsinger retired from the company after a distinguished 40-plus-year career.

Fei-Fei Li’s World Labs just demoed its first product.

Trending Tools

🤗 Hugging Face Open Source RAG Cookbook - The Open-Source AI Cookbook is a collection of notebooks illustrating practical aspects of building AI applications.

📃 Redact AI - Create LinkedIn posts with AI.

📈 Pro AI - Achieve success with bespoke AI-generated business plans, research, and strategies.

So ChatGPT’s birthday was last week…

Food for thought I guess, I feel like we’ve had an amazing year from OpenAI and even AI in general, can’t please everyone though…

We’re curious though, reply to this newsletter with where you read Digestible AI from and we’ll feature you in the next edition!

If you have any suggestions or specific feedback, simply reply to this email or fill out this form. Additionally, if you found this insightful, don't hesitate to engage with us on our socials and forward this over to your friends!

You can find our past newsletter editions here!

This newsletter was brought to you by Digestible AI. Was this forwarded to you? Subscribe here to get your AI fix delivered right to your inbox. 👋