Happy Monday, wizards.
Here’s the most interesting things happening in AI today.
DARIO’S PICKS
source: github.com/openai/swarm
OpenAI has released Swarm, a framework that explores ergonomic, multi-agent orchestration. It showcases how developers can manage interactions and handoffs between multiple AI agents.
Imagine different AI assistants (e.g. “Customer service rep” and “Sales agent”), each with their own roles and instructions, working together smoothly. Swarm makes it easier to orchestrate the transfer of control from one such assistant to the other, all while giving fine-grained control and maintaining the necessary context for each assistant, in a workflow or product.
Swarm is currently available to developers on GitHub, ie. it requires coding knowledge and isn’t a product with a user interface that you can try out directly. It is primarily meant as an educational framework and not intended for production (also it does not use the Assistants API).
Why it matters We’re moving towards AI agents – systems that aren’t just intelligent but can interact with the “outside world” and perform tasks from start to finish. OpenAI is exploring more modular and collaborative ways to let developers build such systems – something which could make AI way more useful across various industries.
TOGETHER WITH TRUEMEDIA.ORG
Dario: I recently did an in-depth review of TrueMedia.org awesome free tool for detecting deepfakes. I found it easy to use, highly accurate in detecting deepfakes and it even gives you a detailed analysis of the results. It’s already being used by big companies like Thomson Reuters and NewsGuard.
Here’s how it works:
Test any social media post by copying and pasting the link into TrueMedia.org.
Get an instant analysis if the voice or face has been changed by AI – you can even find out what genAI tool may have been used.
TrueMedia.org is non-profit and non-partisan. The detector is being made available to the public in the run-up to the US election and others this fall.
It’s free for everyone. No account required.
👉 Try for free at TrueMedia.org
FEATURED GPT
The Wix AI website builder GPT helps you create a unique, business-ready site in no time; plus, get marketing tools, a custom domain & reliable hosting built right in.
Want your custom GPT featured? Apply here.
DARIO’S PICKS
2. Four real-world use cases of AI in legal services
I’m continuing my exploration of the world’s most impactful real-world use cases of AI.
Today, I’ve looked at AI in the realm of legal services. According to a recent report by Ironclad, over 70% of legal professionals trust AI and are already using it to enhance their work. AI in Legal is reducing tedious tasks, improving accuracy, and even helping to alleviate job dissatisfaction by allowing lawyers to focus on more strategic matters.
Here’s 4 companies I’ve identified that have found distinct, high-value use cases for their industry, by leveraging models from OpenAI, Anthropic and Google.
Harvey, an AI platform for law and professional services firms, partnered with OpenAI to build a custom-trained case law model. It has enabled its AI to assist with complex legal reasoning, contract review, drafting legal documents, and case law research. Their model has proven to be significantly more accurate and thorough than standard GPT for legal professionals, reducing errors like hallucinations and providing detailed, source-cited responses.
Ironclad uses OpenAI’s tech to power their AI assistant, a contract lifecycle management tool that identifies and redlines contract irregularities. The integration allows legal teams to reduce contract redlining time from 40 minutes to 2 minutes, improving efficiency without replacing human oversight.
Steno uses Anthropic’s Claude 3 Opus to power its Transcript Genius platform, enabling attorneys to quickly search, analyze, and extract insights from legal transcripts—word-for-word records of court hearings, depositions, and legal proceedings. Their solution centralizes transcript storage and, with a 200K context window, efficiently handles these lengthy, unstructured documents, saving attorneys a lot of time in preparing for depositions (formal witness questioning).
Justicia Lab uses Google’s AI technology to power an assistant that helps immigrants and asylum seekers by analyzing legal documents. Users can upload photos of important documents—such as immigration letters or notices—and the AI extracts key information (e.g. important deadlines, eligibility for immigration relief, etc) and provides personalized guidance on next steps.
Why it matters Rather than replacing jobs, it seems that—at least so far—AI's main contribution in Legal is making work more accurate, efficient and enjoyable.
FROM OUR PARTNERS
200+ hours of research on AI tools, prompting techniques & hacks packed in a solid 3 hour masterclass.
THAT’S ALL FOLKS!
Was this email forwarded to you? Sign up here.
Want to get in front of 13,000 AI enthusiasts? Work with me.
This newsletter is written & curated by Dario Chincha.
What's your verdict on today's email?
Affiliate disclosure: To cover the cost of my email software and the time I spend writing this newsletter, I sometimes link to products and other newsletters. Please assume these are affiliate links. If you choose to subscribe to a newsletter or buy a product through any of my links then THANK YOU – it will make it possible for me to continue to do this.