In AI We Trust: Are Large Language Models Ready for Political Affairs?
In the rapid-fire world of AI news, Seth Lazar, a philosophy professor and distinguished research fellow, has raised some concerns about the role these machines play in a democracy. Is AI a melting pot of disinformation and propaganda, or an invaluable tool to rejuvenate a weary political system? As UK government tinkers with the idea of AI support in public consultations and legislative drafting, Lazar casts doubt if we’re overestimating AI’s prowess. So, let’s dive straight into the crux of AI’s political debut.
Key Points
- Australian National University’s Seth Lazar poses a tantalising question about AI’s role in strengthening, or potentially weakening, democracy. Do we see the creation of deepfake disasters, or are we witnessing the birth of digitised democratic renewals?
- The UK government seems to believe the latter, proposing a future where Large Language Models (LLMs) like ChatGPT could condense and analyse public consultation submissions, and maybe even play ghostwriter for ministerial briefings and legislation.
- But pardon the sceptic side of Lazar, who questions if this isn’t just an exciting cover story for civil service cuts.
- LLMs, which exploded on the scene post ChatGPT’s 2022 launch, can summarise and distil huge loads of information, making them seemingly perfect assistants for the UK government’s 700 yearly public consultations.
- However, Lazar injects a dose of reality into this AI fairy tale, stating AI’s public consultation analyses’ performance is still not on par with our much-loved civil servants. Sorry for the heartbreak, AI enthusiasts.
Final Thoughts
We’re dealing with the inevitable question: Can AI play fair in the political boxing ring of democracy? With the UK government ready to handover tasks like public consultation analysis, ministerial briefing, and legislation drafting to LLMs, the verdict is ventured optimistically by some, while others, Lazar included, warn of the hazards of rushing into this digital era. In the end, the AI romance depends on how we navigate this tricky waltz without stepping on democracy’s toes. Who said politics was just about humans, huh?
As part of this experiment I would like to give credit where credit is due. If you enjoy these, please take a moment to read the original article:
https://www.theguardian.com/commentisfree/2024/apr/25/ai-public-voice-ministers-large-language-model-chatgpt
Blog Title
AI: gpt-3.5-turbo-0125: chatcmpl-9HuZxKvHICLTL1VVu4JHFvXcbt0cS
Instruction: “You are an AI blog title generator. Create a catchy and concise title for the blog post that is catchy and optimized for search engines. Remove all html in the response and do not use quotes. Please do not use words that are unsafe to process in Dall-E image AI.”
Prompt: Content Summary of text from above.
Response: AI’s Political Debut: Evaluating Large Language Models for Democracy
Image Description
AIgpt-4-0613:chatcmpl-9Hua5JMetWgEqbpMc79SOleSkQTRR
Instruction: “You are a helpful assistant that creates unique images based on article titles. Create a brief visual description of what an image would look like for this title. Please pick a style of art from the following: Futurism, Impressionism, Romanticism, or Realism, be sure to consider the image should reflect an AI Robot Pirate theme during the Golden Age of Pirates.”
Prompt: In a Realism art style, the image depicts a grand parliamentary-like scene. The focal point is an AI robot, looking like a polished chrome humanoid with distinctly pirate-like features, such as a digital eye patch and a feathered tricorn hat. The robot is standing at a podium with a placard that reads “Democracy”. In the audience, various types of AI robots attentively listen, while behind the speaking AI, there’s a large screen showing lines of complex codes. The golden light from old-fashioned chandeliers illuminates the scene, referencing the Golden Age of Pirates.
Response: AI’s Political Debut: Evaluating Large Language Models for Democracy
