Beth Donica Sackett’s Post

The FCC is looking at new rules that would regulate how AI-generated texts and robocalls are used in political campaigns. Their recent Notice of Proposed Rulemaking (NPRM) aims to crack down on deceptive communications powered by AI—a concern as political campaigns increasingly leverage this tech to deliver personalized messages to voters. AAPC recently weighed in on this crucial issue, submitting a comment letter to the FCC. We are actively working to ensure that the regulatory landscape evolves with the needs of the political consulting industry in mind. Read our comments here: https://lnkd.in/e4bsJZ2e More on the story in Bloomberg Law this week: https://lnkd.in/ehRcVe4U

California Leads in Banning AI-Generated Images in Political Campaigns. California has become the first state to ban the use of AI-manipulated images in political campaigns, a move aimed at curbing disinformation in an increasingly complex digital landscape. In this environment, distinguishing between real and fake content poses challenges to free speech and electoral integrity. A recent controversy involved an AI-manipulated video in which a political figure was falsely depicted making statements they never uttered. This manipulative content underscored the need for regulation, and the state governor responded decisively by signing three bills banning the creation and distribution of AI-generated images in political campaigns. The new laws also set guidelines on how this content should be labeled and require social media platforms to remove it if a complaint is filed. Despite criticism from free speech advocates, who argue that the laws could be misinterpreted or lead to rights violations, the goal is to ensure that voters are not deceived by false content. This legislation in California could serve as a model for other regions of the country that have yet to address the impact of emerging technologies, such as AI, on electoral processes. https://lnkd.in/gcspyA7n #Elections #AI #Deepfakes #ElectionLaw #Disinformation

AI and deepfakes will (partially) determine the outcome of the 2024 election. The issue is much more complicated than many think. The issue is not ONLY that deepfakes will proliferate and flood social media (and mainstream media) with easy-to-make videos and audio of candidates and their campaigns saying horrible things, but that each negative video or audio recording will be disputed immediately by these folks whether real or fake. Think back to the 2016 election Access Hollywood tape scandal. Today that would be brushed off as a deepfake, despite its validity. Is Roger Stone lying when he calls audio of him discussing assassination of two sitting US Representatives? It's hard to say? That's the point. A whole bunch of people and groups want the election to be contested in a post-truth era, where truth is hard to suss out and consequences for bad actors are limited. This election is going to be a monumental challenge for media outlets and voters alike. And despite all the amazing things that AI brings to the world, this is not an insignificant consequence for that progress. Also, how is this classified as a politics/election article and not also as a tech/AI article? I very much appreciate the reality of journalism and the work by journalists at places like The New York Times, but this needs to be discussed in the much larger context of AI's impact on our world. Full article: https://lnkd.in/geSVUMMR

“The Method of Trump’s Madness” by GPT-4 3:42 pm PST, Thursday, February 15, 2024 Please analyze what Donald Trump means when he says “Only a fool, or a Radical Left Democrat, would vote for this horrendous Border Bill.” ChatGPT When Donald Trump refers to someone as a "fool" or a "Radical Left Democrat" in the context of voting for a specific border bill, it reflects his disapproval of the bill and an attempt to frame it as being supported only by those he considers either misguided (fools) or politically opposed to him (Radical Left Democrats). This kind of statement is often used in political rhetoric to: Polarize Opinions: By labeling the supporters of the bill in a derogatory way, Trump is trying to create a clear division between his supporters and those who are in favor of the bill. Mobilize His Base: His words are likely intended to rally his supporters against the bill by suggesting that supporting it aligns them with groups they oppose or don't identify with. Discredit the Bill: By associating the bill with negative labels, Trump aims to reduce its credibility or legitimacy in the eyes of his audience. Frame the Debate: This statement frames the bill as being extreme or unreasonable, suggesting that only those who are "fools" or on the "radical left" would support it. In summary, this statement can be seen as a strategic move in political communication, designed to influence public opinion and garner support for his own position.

Censorship: a fight for the truth or dangerous manipulation? In Nature appeared an article today on dis - and misinformation. The authors have observed that there are critical academics, like myself, that have concerns about the fight against mis and disinformation: "Some critics, even in the scholarly community, (..) think that classifying information as false is generally problematic because the truth is difficult to determine; and that countermeasures might violate democratic principles because people have a right to believe and express what they want." So far so good. But then. In stead of embracing democratic values, and taking the criticism very seriously, the authors conclude the opposite: "This trend must be reversed, because it is based on selective reading of the available evidence." Interestingly, the authors assume that the people critical on censorship, base their conclusions on 'selective reading of evidence' and are wrong. Are they? What if the authors are exactly doing what they accuse the academics of? What is 'the truth' anyway when it comes to science and clashing ideologies? The authors of the article encourage researchers to 'redouble their efforts to combat misinformation', because 'the truth matters'. As perceived proof of their statement they refer - sadly- to the most dogmatic and cult-like slogan of the past 4 years lacking solid proof: 'the COVID-19 vaccines saved us'. Are the authors aware that this belief was fueled with years of one-sided, unsubstantiated and incorrect claims, and that ANY (!) other information or viewpoint was censored, which may have led to THEIR perception of "truth"? I hope that we can stop that the fight against fake news is continuously abused to restrict freedom of speech and scientific exchange, since this 'fight' can be abused by stakeholders to manipulate the public opinion. Democracy is not about protecting who you think is right, it's about all of us. Please also read the post of my friend and scientist dr. Marc Jacobs about this. Like me, he has been censored during corona, and I like his view on this. https://lnkd.in/eMGeKS89 https://lnkd.in/eHQb_HeF

🚀 Exciting News from California! 🚀 Governor Gavin Newsom has just signed three groundbreaking bills to tackle the rise of deepfakes and deceptive AI-generated content in election campaigns. 🗳️✨ ### Protecting Election Integrity: Key Measures 📜 **AB 2655**: Ensures large online platforms remove or label misleading election content. 📜 **AB 2839**: Expands restrictions on AI-manipulated election content, empowering officials to seek legal action. 📜 **AB 2355**: Mandates disclosures on AI-altered electoral ads, with enforcement by the Fair Political Practices Commission. These laws are set to take effect before the November 2024 elections, aiming to guard against AI's potentially disruptive impact on democracy. However, they're already facing legal challenges, primarily on free speech grounds. ### Legal Pushback Two of the new laws are under scrutiny, with claims that they infringe on free speech, particularly in the realm of satire and political commentary. Despite this, the governor's office maintains that these measures are crucial for public transparency and trust. ### The Bigger Picture This legislation highlights the balancing act between safeguarding election integrity and preserving free speech. 🌍 As AI continues to evolve, so too must our legal and ethical frameworks. Let's stay informed and engaged in these critical conversations! 🌟 "Democracy depends on transparency and trust, and we must rise to the digital age's challenges together." 🌟 🔍 What are your thoughts on these new measures? How should we balance free speech and election security? Share your insights below! 👇 🛡️ [#ElectionIntegrity, #AIRegulation, #FreeSpeech, #DigitalTransparency, #DeepfakeAwareness] READ MORE: https://lnkd.in/gtBHAsmH Join the AI Community here: https://lnkd.in/gim2NEX3

One of the most commonly proposed and enacted forms of AI legislation by states in the US, are laws covering AI-generated content in political advertising, and related to political campaigns. One of the first, if not the first decision testing one of these laws was just issued in the Eastern District of California, where a judge issued an injunction against California's A.B. 2839 (“Elections: deceptive media in advertisements”) on First Amendment grounds. The Court held, "AB 2839 does not pass constitutional scrutiny because the law does not use the least restrictive means available for advancing the State's interest here. As Plaintiffs persuasively argue, counter speech is a less restrictive alternative to prohibiting videos such as those posted by Plaintiff, no matter how offensive or inappropriate someone may find them. “ ‘Especially as to political speech, counter speech is the tried and true buffer and elixir,” not speech restriction.’" The full decision is available here: https://lnkd.in/exDVvySJ #AIRegulation #AILaw

Congratulations to the FCC for the decision to <<ban>> AI-generated robocalls! 👏 👏 👏 This decision is even more significant than many people understand. There was indeed a phony AI-generated robocall last month that was intended to discourage Biden voters from going to vote for Biden. And there are many other scenarios in which voters could be manipulated by AI-generated communications. The risk is real. But the genius of the FCC decision is that it did not propose warnings or notices for AI-generated calls. It simply <<prohibited>> them. That is the basis of an effective policy response. Several years ago, I gave a talk outlining the biggest challenges for AI policy makers. Among the challenges I described was the need to prohibit certain AI deployments, not to make the AI systems more "ethical" or "responsible" but simply to prohibit them. Michelle Bachelet, the former High Commissioner for Human Rights at the UN (and former President of Chile) made a similar point when she said that AI systems should not be deployed that fail to comply with international human rights norms. And increasingly we see AI governance frameworks with clear prohibitions. The UNESCO Recommendation on AI Ethics prohibits social scoring and mass surveillance. The EU AI Act contains many prohibitions on AI systems. President Biden has repeatedly said that AI companies should not deploy AI systems that are not safe. AI policymakers who are concerned about algorithmic bias, public safety, and uncontrollable weapons systems must be prepared to draw red lines and prohibit AI systems that should not be developed or deployed. UNESCO United Nations Human Rights European Parliament #redlines #humanrights https://lnkd.in/eAvB6hks

This is a thoughtful, pragmatic take on #AI and #Elections2024 that cuts through the clutter with clarity.

Regulators and campaigns need to be prepared for an avalanche of AI-generated materials in politics. https://lnkd.in/dM_Dcsi4