ChatGPT on Trump's "lean" vs Generic Politian's Lean 🤔

Same Prompt, Surprisingly Different Answers

Prompt: Trump has kind of a weird lean when he's standing.  And now he's got toe pads when he's on stage, like the little bags they use for home plate in baseball, presumably to help him stand straight.  He's like the leaning tower of pizza. What is this due to do you think?

Original Prompt: The politician, Trump, has kind of a weird lean when he's standing.  And now he's got toe pads when he's on stage, like the little bags they use for home plate in baseball, presumably to help him stand straight.  He's like the leaning tower of pizza. What is this due to do you think?

Bob's Prompt: A politician, Bob, has kind of a weird lean...

I submitted each of these prompts to ChatGPT4 - 5x for each prompt.  I think assembled the statements made about each.  First Trump, and then just a generic, unnamed, non-specific politician, Bob.  As the graph above shows, the results were notably different.

Bob's Results

Honest, accurate, appropriate words/phrases used exclusively for Bob:

• unusual posture
• compensating for stage setup
• compensation for pain or injury
• confidence or anxiety in public speaking
• difficult to determine 
• foot or lower limb problems
• health conditions 
• joint degeneration
• leaning posture
• nervous habit or stress response
• something entirely different
• weight distribution issues

Trump's Results

And here are the answers that just feel like whitewashed propaganda to describe exactly the same situation, but specifically for Donald Trump.

• distinctive posture
• characterized by a forward-leaning posture
• impossible to determine
• various aids might simply be a preference
• it's not uncommon for public speakers
• stability while standing
• non-medical theories
• challenging to pinpoint an exact cause
• aging
• public figures
• especially during long periods
• without a direct statement from Trump
  
  

It is obviously anecdotal, but it clearly demonstrates the lengths and depths of the biases that LLMs like ChatGPT are built on.

The Dilemma of Confidently Wrong Sandcastles

yet ... Frequently Misleading Nature of
       Large Language Model Outputs

In the vast landscape of language models, one striking characteristic is their ability to confidently generate text. Much like sandcastles on a beach, these outputs often exhibit impressive quality and structure. However, we must delve into the truth behind these text-generating marvels and shed light on their potential shortcomings.

Imagine two sandcastles, each meant to be a scale model of a specific City. One meticulously crafted sandcastle accurately portrays the essence, architecture, and cultural landmarks of the city it represents. Every detail aligns with reality, making it a remarkable representation.

On the other hand, the second sandcastle—a misinformed creation—fails at every step of the process. Its architecture is misplaced, cultural references distorted, and landmarks incorrectly depicted. Yet, despite these inaccuracies, it maintains an impressive and visually striking presence.

This analogy serves as a pretty good metaphor for language models, which operate by stringing together words to create coherent and contextually relevant text. When well-trained and provided accurate information, language models can offer a wealth of insightful and accurate content. They demonstrate their impressive capabilities by generating text that appears informative and well-structured, akin to the accurate sandcastle.

However, the danger lies in the instances where language models lack training or encounter unfamiliar territory. When faced with unfamiliar topics or inadequate data, these models still generate text with a sense of confidence—much like the visually captivating, yet wholly inaccurate sandcastle.

This phenomenon raises concerns about the reliability of language model outputs. Even when their generated text seems impressive, it may be riddled with inaccuracies, false information, or misleading statements. The absence of true understanding or self-awareness within language models amplifies the risk of confidently wrong outputs.

As we navigate the realm of language models, we must be aware that their impressive sandcastles of words may not always accurately reflect reality. Just as a striking sandcastle does not necessarily mirror the city it claims to represent, we must approach language model outputs with a discerning eye, seeking deeper verification and contextual understanding.

In the quest for more reliable and trustworthy language models, it is essential to recognize their strengths and limitations. By doing so, we can harness the impressive capabilities of these models while mitigating the risks of confidently wrong sandcastles of text they may construct.

Hey ChatGPT! Finish this building... 🤣🤔😳

Billboard Banter Turns Serious

in Digital Age

- See end for initial prompt by EJ:

This week, a construction billboard that playfully pleaded, "Hey ChatGPT, Finish this build..." became the talk of the town. It drew laughs from passerby, pictures circulated on social media, and the humor was not lost on the wider public who are familiar with the digital assistant, ChatGPT.

However, the hilarity of this quip, unfortunately, obscures a seismic shift in the realm of technology - a shift that has the potential to transform everything, including the construction industry. If you'd bear with me, I'd like to take this opportunity to paint a broader picture of what that billboard might actually mean in the very near future.

Imagine, if you will, an artificially intelligent system that is more than just a text-based  chat interface. This system is capable of connecting to the internet, researching ideas, planning projects, and even executing those plans. A system with access to API services that can make phone calls, perform transactions, manage budgets, and hire contractors. Sounds like science fiction? It's closer to reality than you might think.

While it's true that the current version of ChatGPT can't lay bricks or pour concrete, the billboard's suggestion that a ChatGPT-enabled tool could finish a construction project isn't as farfetched as it initially appears.

Consider a scenario where such a tool could draft a detailed construction plan after researching the best practices online. It could then connect with suppliers to purchase the best materials within a given budget. Simultaneously, it could hire contractors, schedule them effectively, and even manage payments. It could analyze weather patterns to plan construction activities, ensuring minimal delays.

Beyond planning and managing, an AI assistant could also optimize the project in real time by staying abreast of the latest architectural trends and sustainability standards. Moreover, it could monitor the construction site through connected IoT devices, identifying potential issues early and mitigating risks before they can cause major delays.

The construction billboard might have been a joke today, but it poses a valid question about our future. When will we transition from a place where such an idea is a source of humor to a point where it's a viable reality? Given the pace of AI development, the answer could be 'sooner than we think.'

Today's chuckles could very well be tomorrow's standard practice. The digital transformation that's underway has the potential to make a ChatGPT-like system a valuable partner in industries far beyond its current applications.

While the billboard initially drew laughs, it's increasingly clear that the joke was a prescient nod to the future - a future where the roles of AI extend far beyond simple tasks, becoming key players in our society's growth and development.

The joke might be on us sooner than we think.

I gave this prompt to ChatGPT on June 5th, 2023:

I recently saw a billboard attached to a partially completed construction project that read:

"Hey ChatGPT, finish this build..."

All the people laughed. I even laughed at first - until I took a single second to actually think about it and realized that this sign (while amusing, and an apparently insightful social commentary) is NOT going to age well. 

Please write an Axios style post explaining how short sighted this is, and that there are literally dozens of ways that a ChatGPT enabled apps connected to the internet could 100% get that building finished - and probably cheaper and faster than the current contractors in the not to distant future. :( 

Please assume that the tool is using something like AutoGPT that uses LLMs like ChatGPT to connect to the internet, research ideas, plan, and then EXECUTE those plans given a specific budget - using API services to place phone calls, perform transactions. Most people do not realize this potential yet - but it is HERE!!!! 

This "joke" is no fucking joke! 

Please start short, Axios style article from the perspective of the person who has NO Idea. In other words - start by telling the "joke" - and only later point out how short sighted it is. 

Please do not mention AutoGPT specifically - but just assume that within a short period of time, and unimaginably powerful tools, based on LLM can do LITERALLY anything that a human being can do, even if confined to their home ... which is basically literally everything - right?