AI | Business | Startups
Biden’s Executive Order on AI is Signed. Now What?
Maybe that whole AI-Will-Destroy-The-World thing will be pushed off for a few more years.
If you think of AI as an out-of-control toddler, running around with a fork in it’s hand, stabbing right, stabbing left, until it finally stabs an electric socket and sets the whole house on fire, you’ll be happy to know that Grandpa Biden has come over and put the kid in the corner.
The new executive order is a thoughtful, well researched bill — well, not a bill just yet, an executive order — that took months to formulate. Biden and his team have met with multiple AI and tech industry leaders, from Bill Gates, Musk, Hinton to Sam Altman. After doing the research, hearing the concerns and optimism, a bill was crafted. It is as much a call for development and research as it it a set of bumper rails and speed bumps. Great to see a work-product of this quality produced by our government with everyone working together (sort of).
Not saying it’s perfect. There are concerns. And as always, the devil is in the implementation. But it’s a perfect start.
Here are the top 7 takeaways from the bill to be aware of:
- AI Safety and Security — No longer will the MVP (minimum viable product) philosophy of tech throwing out a product and letting the marketplace refine it be acceptable. Testing will be required. And the test results must be shared with the U.S. government. Testing protocols will be developed by the The National Institute of Standards and Technology and include ‘red team’ testing. Red team testing was developed and used in cyber security. It involves an independent team assigned to simulate real-world attack scenarios and exploit any weaknesses in the system’s design, implementation, or functionality. This testing must be completed, and shared, prior to release. In addition, the Department of Homeland Security will apply these same standards to critical infrastructure sectors.
- Privacy Protections — AI could put your privacy at risk. The bill urges Congress to pass bipartisan — any partisan really — data privacy legislation to safeguard privacy, especially that of children. It supports the development and use of privacy-preserving techniques. It’s AI to protect against AI. Also aims to strengthen privacy-protecting research, evaluate how agencies collect, and use, and train on commercially available information. AI systems can continue to be trained but should work to preserve the privacy and ownership(?) of the training data.
- Deep Fakes, Copyrights, and Bio-materials — The Department of Commerce will develop guidance for content authentication and watermarking to clearly label AI-generated content. This is aimed at ensuring that the communications received from the government are authentic. Hopefully, these guidelines will be viewed and used by the private sector and other governments as well. Bill also addresses using AI to develop biological materials and how to develop strong standards to prevent false and/or misleading information on materials that could harm individuals or our society.
- Equity and Civil Rights — The Executive Order addresses discrimination, bias, and other abuses in justice, healthcare, and housing due to malicious or irresponsible uses of AI. It provides clear guidance to prevent AI algorithms from increasing and continuing discrimination. It addresses biases through training, technical assistance, and coordination between the Department of Justice and Federal Civil Rights offices.
- Consumer Protection — As a consumer, AI can help protect you, help you find the deal of deals, protect your data, or it can screw you. The bill aims to advance the responsible use of AI in the consumer marketplace especially in healthcare. It places an emphasis on the development of affordable and safe drugs.
- Supporting Workers — When companies sprinted to China to get cheap labor, and cheap products, and bigger profits, the American worker was left behind. Instead of the increased profits going into education for displaced workers, it went into the pockets of executives. This bill attempts to correct this failure and ensure we don’t make the same mistake twice. AI is changing jobs. AI is changing offices. It’s changing the essences of the workplace. This is wonderful but also scary. The bill directs the development of principles, and best practices, to address job displacement, labor standards, workplace equity, health, and safety. It also calls for a report on AI’s potential labor-market impacts and options for strengthening federal support for workers that could lose their jobs. It offers help for teachers and educators by creating resources to deploy AI-enabled educational tools.
- Investment, Promotion, and Innovation — The bill wants to protect us but it also wants America to be the leader in research and development of AI technologies. It promotes a fair, open, and competitive AI marketplace. It provides small developers and entrepreneurs access to technical assistance and resources, and expands the ability of highly skilled immigrants and non-immigrants to study, stay, and work in the United States. It also grants $140 million to the National Science Foundation (NSF) to establish seven new AI research institutes. The NSF is the primary investor in non-defense AI research and plays a crucial role in advancing AI technologies.
That’s the down-n-dirty.
Sleep well tonight. The world will still be here tomorrow.
What does AI think about this new AI bill? Well, I asked it. Here’s the Q & A of it:
Q: What do you think about the new AI bill? Is it good? Or is it bad?
A: The new AI bill has generated mixed opinions and perspectives. Some argue that it is a positive step towards addressing the challenges posed by technology, data, and automated systems that threaten the rights of the American public [1]. These individuals believe that the bill will help prevent the misuse of AI tools and ensure that they are used responsibly and ethically. They highlight the need to address issues such as biased algorithms in hiring and credit decisions, unsafe patient care systems, and unchecked social media data collection [1]. On the other hand, there are concerns about the effectiveness and impact of the AI bill. Critics argue that regulating AI is a complex task due to its rapid development and evolving nature [4]. They question the feasibility of implementing regulations that can keep up with the pace of technological advancements. Additionally, there are concerns about the potential limitations on innovation and the unintended consequences of overregulation [4]. It is important to note that the AI bill is part of a broader effort to govern AI technology. The White House has recognized the potential of AI to solve urgent challenges and make the world more prosperous, productive, innovative, and secure [7]. However, they also acknowledge the need for responsible AI use and the potential societal harms that could arise from irresponsible use [7]. To address these concerns, the White House has been engaging with AI experts and major tech companies to strike a balance between promoting innovation and ensuring responsible AI development and use [3][5]. President Biden has emphasized the importance of governing AI technology to realize its promise and avoid risks [9]. He has signed an executive order to protect fundamental rights like privacy and called for new protections on personal data [10]. In conclusion, the new AI bill has sparked discussions and debates regarding its potential benefits and drawbacks. While some view it as a positive step towards safeguarding the rights of the American public and addressing the challenges posed by AI, others express concerns about its effectiveness and impact on innovation. The broader efforts to govern AI technology, engage with experts, and strike a balance between innovation and responsible use highlight the complexity of regulating AI.
Not bad. ALANI also gave me a list of sources for each response. You can see them numbered in the answer. I didn’t include them here but if you want to delve deeper, ask your own questions, and view the sources to double check the info, please proceed. It’s free.
To use our AI legislation chat bot built with ALANI follow the link below:
Need additional information? Visit AI.gov.
Want to keep up with cutting-edge AI news and bundleIQ development and breakthroughs? Join our free, weekly newsletter, read by thousands, here.
