
Seems only right to ask ChatGPT about this first…
“Nobody is born with a style or a voice. We don't come out of the womb knowing who we are. In the beginning, we learn by pretending to be our heroes. We learn by copying.”
~ Austin Kleon
For this post, if I’m sharing my unadulterated organic writing, it will look like it does normally. Like this. Normal font etc.
If I’m sharing something written by a someone else or a machine learning chatbot like the following section where I asked ChatGPT how to look for AI written content, I’ll drop it in a quote and attribute it to the chatbot used. Like so…
Spotting if someone is using AI to write content can sometimes be challenging, as AI-generated content is becoming increasingly sophisticated. However, there are a few indicators you can look for:
Unusual Language Patterns: AI-generated content might exhibit unusual or unnatural language patterns, phrasing, or word choices. Look for sentences that seem overly formal, overly technical, or lack a human touch.
Consistency and Repetition: AI tends to produce consistent and repetitive content. If you notice the same phrases, ideas, or structures repeated throughout the text, it could be a sign of AI-generated content.
Lack of Personal Experience or Emotion: AI-generated content often lacks personal anecdotes, emotions, or experiences. If the content seems devoid of genuine human experiences, it might be generated by AI.
High Volume and Speed: If someone is producing a very large volume of content in an unusually short amount of time, it could be an indication that AI is involved. AI can generate content at a rapid pace.
Inaccurate or Incoherent Information: AI-generated content might occasionally produce inaccurate or incoherent information, especially when dealing with complex or nuanced topics. If you spot inconsistencies or errors that a human writer would likely catch, it could be a clue.
Generic or Template-Like Content: AI-generated content might lean towards generic or template-like language, as it often relies on patterns learned from training data. If the content feels generic and lacks a unique voice, it might be AI-generated.
Sudden Shifts in Style or Tone: If you notice abrupt changes in writing style, tone, or focus within a piece of content, it could be a result of different AI models being used or a human editor making adjustments.
Use of Advanced Technical Concepts: AI-generated content might include highly technical terms or concepts without proper context or explanation. If the content jumps into complex topics without adequate introduction, it could be a sign of AI involvement.
Unusual Sources or References: If the content cites obscure or unusual sources, especially those that are not commonly referenced by human writers, it could be an indication of AI-generated content.
Testing with Specific Prompts: You can test whether someone is using AI by providing them with a specific prompt or question and observing how well they respond. If their response seems too polished, too quick, or lacks a human touch, it might be generated by AI.
Remember that these indicators are not foolproof, and some skilled human writers might mimic AI-generated patterns intentionally. Additionally, AI technology is constantly evolving, so its output may become even harder to distinguish from human writing over time. ~ChatGPT 3.5
On the whole I feel (and I do actually feel. Unlike the bot above) the above points made are worth heeding. The key for me is the first point though. The ‘lack of a human touch’. It’s hard to express yourself in your work when you are asking a machine to do the expressing.
By all means work with these incredible tools, just remember to add those genuine emotions, anecdotes and insights. For now people relate to people better than they relate to machines.
“There must be a certain amount of imitation, copying, in outward technique, but when there is inward, psychological imitation surely we cease to be creative.”
~ Jiddu Krishnamurti
Keep reading with a 7-day free trial
Subscribe to