An Apology to Generative AI

ChatGPT spelled out in Scrabble tiles

By Ariella Brown

I'm not a generative AI fangirl. If anything, I'd consider myself more of a skeptic because people tend to not just use it as a tool to improve their writing but as a tool to replace the work of research, composition, and revision that is essential to good writing.

It is generally embraced by people who consider online research to be too much work and who believe that anything that comes out of a machine that will charge them no more than $20 a month for writing to be too good a deal to pass up. 

For those of us who actually read, the output of ChatGPT and similar LLMs is not exactly something to write home about. Unless you know how to prompt it and train it to write in a truly readable style, it will default to the worst of wordy, opaque corporate style text. 

But this isn't the fault of the technology. It's the fault of the mediocre content that dominates the internet that trained it. Below is one example that I pulled off  the "About" section of a real LinkedIn profile (first name Kerri maintained in the screenshot that proves this is real and not something I made up):  

As a strategic thinker, problem-solver, and mediator, I thrive in managing multiple, sometimes differing inputs to achieve optimal messaging and positioning. My proactive nature drives me to partner with leaders across marketing teams and internal business units, aligning efforts, connecting dots, and adding context to enable flawless execution of communication strategies and tactics.

In fast-paced, fluid environments, I excel in effectively prioritizing tasks and ensuring they are completed efficiently. I have a proven track record of setting and meeting strict deadlines and budgets, leveraging my ability to navigate dynamic landscapes seamlessly.

Driven by natural curiosity, I am constantly seeking to understand and implement the latest trends, technologies, and tactics essential for driving B2B sales opportunities. My keen interest in exploring new channels for messaging and content distribution fuels my passion for innovation and continuous improvement to not just meet but exceed expectations.

Let’s connect to explore how we can drive success together.

You know what sounds exactly like this? Cover letters you ask ChatGPT to compose for you. 

I've tried those out a few times and never been happy with the results because they always sounds like the text above. Trying to tell it to sound less stiff doesn't make it sound any less canned, and forget about getting it to copy my own writing style.

It's possible that Kerri used ChatGPT to create her "About" section. Given that she's been in the marketing biz for some time, though, I'd think she had to have had something filled out for years before ChatGPT was available, and it likely sounded very much like this even if she did let some LLM or something like Grammarly tweak it for her.  

People like Kerri, who ignore all writing advice from the masters like Orwell, White (watch for a upcoming  blog about him), and others made this the public face of corporate communication who are to blame for the bombastic and soulless style that LLMs replicate at scale. 

That's the reason for this apology too ChatGPT for mocking its output. You're not the one at fault. You had no way of knowing better. Humans do, and they should have provided you with better models for writing. 

Note on the title: I thought of giving this post the title "Apology" intended in the classical sense of a defense or justification for something others take as wrong with the hint of an apology to AI. Knowing that that wouldn't be clear to some readers, I opted to make this just a straight apology instead. 

Related:

A new generative AI comparison

The Perils of prompt engineering

Bard vs. Bard
Add a pinch of salt to creative claims for AI

An A/B test of generative AI
Bard brings in the clowns

A new generative AI comparison

Photo by Andrew Neel: https://www.pexels.com/photo/monitor-screen-showing-chatgpt-landing-page-15863066/

In the past, I've ncomparted Cha GPT to Google Bard (now Gemini). For today's exercise, I put the same query to Claude, ChatGPT, Gemini, and Copilot. I put in the name of a real person and identified the location for that individual in Queens, NY.  None could give me the information I sough. 

What's interesting, though, is noting the differences in how they contextualized their responses. Out of the four, Claude shows the greatest self-awareness, and I'd say that Copilot shows the least.  

Claude's response

As this appears to be asking about a relatively obscure individual, I want to remind you that while I try to be accurate, I may hallucinate or generate incorrect information when asked about very specific people who are not widely known public figures. If you're looking for factual information about this person, I'd recommend checking other reliable sources.

I award Claude points for warning me about the possibility of hallucinations occurring when generative AI attempts to answer questions in the absence of data. See 

ChatGPT's response

I don't have specific information about an individual named ____from Queens, NY. It's possible that she is a private individual or someone not widely known beyond her personal circles. If she is known for something specific like public contributions, achievements, or notable activities, that information might be available through local news sources or community records.

ChatGPT's response failed to warn about hallucination, though it's interesting that it inferred the person in question was a she (based on the first name, I suppose), a gender identification that Claude managed to avoid.

Google Gemini's response

Gemini just bowed out, practically chiding me for giving it this query that it could not answer:

 
I do not have enough information about that person to help with your request. I am a large language model, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions, but my knowledge about this person is limited. Is there anything else I can do to help you with this request?

Copilot's response

Copilot went in a completely different direction. I wouldn't call it a hallucination, but it is still inaccurate. It wanted to find a match, so in one case it named a business with the last name appearing twice as a partnership, though it admitted that was Brooklyn rather than Queens. Its second suggestion was a male doctor in Queens with a similar last name, though it is spelled differently. Honestly, I find it hard to believe that these are the only two results for the last name in all of NYC. I mean once you're expanding the parameters, there really should be a lot more than two possible results. 

Related

The Perils of prompt engineering

Bard vs. Bard
Add a pinch of salt to creative claims for AI

An A/B test of generative AI
Bard brings in the clowns

Follow Write Way Pro on LinkedIn and on Facebook.

You can also follow Ariella Brown.