Monday, September 08, 2025
The Cons of the AI Tech. Or is this just another Content Hijacking by big tech
It’s time to play devils advocate for this new tech is it a pipe dream or another content grab by big tech, like the internet. We all know Google profited from free content and not paying for it for their search engine.
There are have been legal challenges to the tech. The B.C. co-author of the “100 Mile Diet” has launched class-action lawsuits against four tech giants, including Meta and Nvidia, alleging they have used his copyrighted content to train their artificial intelligence software without compensating him or other authors. Another legal challenge was the SAG/Actra srtike in 2023 over the user of actor’s images in AI movie generating software.
You will need to manage your expectations with the tech if you are looking for a short cut answer. Here is a quote from the ChatGTP
“While ChatGPT offers fast, fluent answers, smart users treat it like a conversation with an expert intern — insightful, but always in need of fact-checking.”
“The model's prediction has a ±10% margin due to incomplete data from sensors. Consider recalibrating or providing more samples.”
ChatGPT Plus users can use tools like:
What It Means for You
ChatGPT said:
As I have discovered the AI tech needs to be trained ie: needs knowledge, make mistakes and learn.
This is reminiscent of my conversation with my brother who supervised an AI lab for Google a few years back. He said the algorithium needs to learn and gain experience as it makes mistakes as the error rate was not better than 20% like math statistical models of plus or minus 10% 19 out of 20 times as the benchmark.
This is reminiscent of my conversation with my brother who supervised an AI lab for Google a few years back. He said the algorithium needs to learn and gain experience as it makes mistakes as the error rate was not better than 20% like math statistical models of plus or minus 10% 19 out of 20 times as the benchmark.
The AI apps learn is by scraping content from the internet as part of their knowledge like Wikipedia plus others. In other words they are taking someone’s knowledge adding it to the app knowledge base without permission or licensing fee. This is another intellectual content grab by big tech to have a free product input model like the internet. After the industry got burned, it learned from their mistakes and have taken legal action to get them to pony up the cash for the content.
 |
|
Source: https://www.cloudflare.com/learning/bots/what-is-content-scraping/
|
There are have been legal challenges to the tech. The B.C. co-author of the “100 Mile Diet” has launched class-action lawsuits against four tech giants, including Meta and Nvidia, alleging they have used his copyrighted content to train their artificial intelligence software without compensating him or other authors. Another legal challenge was the SAG/Actra srtike in 2023 over the user of actor’s images in AI movie generating software.
AI is being used to market the latest round of technology that are language processors is very intriguing. To label this software artificially intelligent is a stretch and this is very misleading to users on so many levels.
Same Big Tech Sales Pitch, New Product that will change the World
Same Big Tech Sales Pitch, New Product that will change the World
First off AI suggest it is smarter the humans, that is almost true as chess software beat a chestmaster in 1996, but the computing power came from IBM’s Big Blue supercomputer. Fast forward today it’s on your smartphone via the internet to a football field size datacenter. But to suggest at this stage of its development that (without historical data to back it up) this tech will increase human performance with more positive outcomes.
Same old myth from big tech as it is a very tantalizing product benefit for any brand and the industry has latch on to this again, just like previous attempts like Big Data, Virtual reality and earlier versions of AI, like chatbots used for customer service, that is aghh to use at best.
Same old myth from big tech as it is a very tantalizing product benefit for any brand and the industry has latch on to this again, just like previous attempts like Big Data, Virtual reality and earlier versions of AI, like chatbots used for customer service, that is aghh to use at best.
I test 3 AI Apps for a song/poem I wrote and asked for some suggestions, As I expected I got three different answers for each one. DeepSeek wanted to rewrite the lyrics without asking. Microsoft's CoPilot gave me a some chords to use for the song and the Chat box gave me a full composition with chords and lyrics. So each has their own limitations, I found Deep Seek annoying as I asked it not to rewrite the lyrics.
But anyways it is here to stay but I asked these questions of the AI for content accuracy. The app is very wordy but want I found was suprising as the error rate of the AI app ranged from 3-40% depeding on inquiry. It seems language processors still have not met the 20% error benchmark.
But anyways it is here to stay but I asked these questions of the AI for content accuracy. The app is very wordy but want I found was suprising as the error rate of the AI app ranged from 3-40% depeding on inquiry. It seems language processors still have not met the 20% error benchmark.
You will need to manage your expectations with the tech if you are looking for a short cut answer. Here is a quote from the ChatGTP
“While ChatGPT offers fast, fluent answers, smart users treat it like a conversation with an expert intern — insightful, but always in need of fact-checking.”
Interview with the ChatGPTApp
 |
|
|
Keeping Tech Honest as it is not 100% right all the time
Q1. Math has an error rate of ±10%. How is AI going to deal with that?
Q2. How can you double-check the knowledge in the chat box?
Q3 I read about hallucinations. What are the incidences of this in the ChatBot GPT now?
Q4. Do you think in 10 years, there will be 0% incidence of hallucinations?
Q1. Math has an error rate of ±10%. How is AI going to deal with that?
ChatGPT said:
That's a deep and important question. If math — especially as applied in real-world data or engineering calculations — has an error margin of ±10%, then AI systems that rely on math must understand, adjust for, and communicate that uncertainty.
Let’s break it down:
What Does ±10% Error in Math Mean?
You're likely referring to:
- Measurement error (e.g., in physics, medicine, sensors)
- Estimation error (e.g., financial models, predictions)
- Rounding or numerical error in computation
- In most applied fields, ±10% means:
"The answer isn't exact. It's close — but within 10% above or below the real value."
How AI Will Handle ±10% Error Margins
1. Understand and Model Uncertainty
AI systems can:
- Use probabilistic models (Bayesian networks, confidence intervals)
- Estimate and express answers with confidence levels
- Recognize when input data is noisy or imprecise
Example: An AI medical diagnosis might say:
"There’s a 72% chance the tumor is benign based on current imaging, with a ±9% error margin due to scan quality."
2. Adjust Calculations for Tolerance
AI will be trained to:
- Accept tolerances in engineering and science (e.g., part must be within 0.5 mm)
- Simulate thousands of “what if” cases to test safety under variability
- Recognize unstable models where small math errors lead to big consequences
Example: In aerospace, AI will flag designs where a ±10% error in thrust could cause mission failure — and recommend safer alternatives.
3. Flag Results That Exceed Acceptable Risk
AI won’t always just give “an answer.” It can say:
“This result is uncertain beyond acceptable bounds.”
“A ±10% error here makes the decision risky — re-evaluate your input.”
This is already being done in financial risk models, self-driving systems, and climate modeling.
4. Explain the Error Clearly
One of ChatGPT’s future strengths is natural language explanation:
“The model's prediction has a ±10% margin due to incomplete data from sensors. Consider recalibrating or providing more samples.”
This helps non-experts understand uncertainty — something even many professionals struggle with today.
5. Learn to Minimize Error Over Time
With feedback loops, AI can:
- Continuously improve models to reduce the error margin
- Learn which data sources are unreliable and correct for them
- Use redundancy (multiple models or sensors) to triangulate better answers
But There Are Limits. Even expert AI won’t make uncertainty disappear. Instead, its role is to:
- Expose it clearly
- Quantify it with precision
- Act within safe bounds based on it
Bottom Line:
AI won't “solve” the ±10% error in math — it will learn to live with it, like a wise engineer or scientist. The power is in knowing when an error matters and when it doesn't — and communicating that clearly to humans.
Q2. How can you double-check the knowledge in the chat box?
ChatGPT said:
Excellent question — especially important when using AI like ChatGPT for research or writing. Here's how you can double-check the knowledge given in the chat box:
1. Ask for Sources
You can type something like:
“Can you cite your sources?”
“Can you cite your sources?”
“Where did you get that information from?”
While ChatGPT doesn't have live internet access on the free plan, it can often name books, studies, or datasets it's been trained on — and you can verify those manually.
2. Cross-Check with Trusted Sources
- Manually verify facts using:
- Wikipedia for general knowledge
- Google Scholar for academic sources
- Official websites (e.g., WHO, NASA, UN, .gov sites)
- Reputable news outlets (e.g., BBC, NYT, Reuters)
Tip: If ChatGPT gives a name, date, or stat, copy it into Google and look for real-world confirmation.
3. Use a Web-Connected AI Tool
ChatGPT Plus users can use tools like:
- Web browsing (via Bing): Fetches current data in real time
- Plugins or GPTs with web search or fact-checking functions
- Perplexity.ai or Claude: These also cite sources automatically
4. Check Internal Consistency
Ask follow-up questions like:
“Are you sure?”
“Are you sure?”
“Can you explain that in more detail?”
“What are counterarguments or opposing views?”
If the AI gives inconsistent answers, it may mean the original info was shaky.
5. Compare with Expert Opinion
Use tools like:
- YouTube interviews with professionals
- Podcasts or blogs by researchers or practitioners
- Books on the topic (check the author’s credentials)
Example: If ChatGPT tells you something about AI in medicine, compare it with what doctors or journals like The Lancet or NEJM say.
Pro Tip for Your Article:
“While ChatGPT offers fast, fluent answers, smart users treat it like a conversation with an expert intern — insightful, but always in need of fact-checking.”
Q3 I read about hallucinations. What are the incidences of this in the ChatBot GPT now?
ChatGPT said:
Here’s a well-rounded look at how often ChatGPT hallucinates, based on current research and reporting:
Measured Hallucination Rates
- GPT‑4 (and GPT‑4 Turbo) hallucinate around 3–10% of the time, depending on complexity and task.
- Vectara found ≈3% hallucination for GPT‑4 in summarization tests
- Financial Times +11
- How-To Geek +11
- Vocal +11
- A BytePlus analysis estimates GPT‑4 hallucinates 5–10% in more complex queries
- GPT‑3.5 has higher rates: about 15–20% (or even higher in some niches)
- GPT‑4o / o3 / o4‑mini showed worrying increases: hallucination rates from 33% to as high as 48% on certain benchmarks
GPT‑4.5, according to some community reports, decreased hallucinations from ~61% to ~37% — still significant but improved
Task & Domain Dependence
- Academic citations: A study of 150 references found GPT‑4 had a ≈20% hallucination rate in finance-related queries
- Systematic reviews: GPT‑4 hallucinated in 28.6% of cases, while GPT‑3.5 reached nearly 40%
- A Wired article highlighted GPT‑4’s ~3% hallucination in summarizing tasks
- A Financial Times piece reported GPT‑4 hallucinating ≈30% of the time in generating fake scientific references, and newer variants showing no improvement .
Why It Happens
LLMs like GPT act as probabilistic word predictors, not fact-checkers. They often guess specifics when unable to recall exact data .
For simple factual questions, GPT‑4 is reliable most of the time—but not perfect.
For technical, academic, or specialized domains, error rates can spike to 20–40%.
For creative tasks, hallucinations can be mistook for creativity—but still demand verification.
Best Practices to Mitigate Hallucination
- Always cross-check facts from the chat with trusted sources.
- Use multi-step verification: e.g., summarize → ask for sources → check them.
- Combine models (e.g., GPT + Claude + Gemini) to triangulate answers
- ask.library.arizona.edu+1
- TechRadar+1
When using for citations or legal/medical info, treat responses as drafts, not final.
Bottom Line:
Even in its most advanced form, ChatGPT still hallucinates with enough frequency (3–40%, depending on context) that human review remains essential.
Q4. Do you think in 10 years, there will be 0% incidence of hallucinations?
ChatGPT said:
That's a bold vision — and the short, honest answer is:
No — it's very unlikely that hallucinations will ever drop to 0%.
Here’s why, broken down clearly for your article or future use:
Why We’re Unlikely to Reach 0% Hallucination in 10 Years
1. LLMs Are Probabilistic, Not Fact-Based
Large language models (like GPT, Claude, Gemini) don’t “know” facts — they generate likely next words based on training data. Even when trained on billions of facts, they sometimes:
Miscombine information
Infer details that sound right but aren’t
Fill in blanks with confident-sounding guesses
Even newer architectures (like GPT-4o or Gemini 1.5) reduce hallucinations — but can’t eliminate them because they’re not built on verifiable logic trees, like a calculator.
2. Language Itself Is Ambiguous
- Human communication is full of:
- Idioms, irony, cultural context
- Contradictory information
- Incomplete knowledge
AI will always face edge cases and contextual ambiguity, especially when asked open-ended or novel questions.
3. Even Humans Make “Hallucinations”
- Doctors misdiagnose. Historians misattribute. Journalists sometimes misquote.
- So the more complex, open-ended, or creative a task is, the more likely even humans make confident but incorrect statements.
- Why would we expect AI to do better than our own brains, especially when mimicking us?
4. AI’s Strength Is Speed, Not Perfect Truth
AI can:
- Generate ideas
- Summarize, translate, rewrite
- Draft high-quality starting points
- But its role is increasingly clear:
- Draft, assist, and inspire — not to authoritatively decide or publish without review.
So What’s the Realistic Goal?
Not 0% — but instead:
Minimize hallucinations in critical domains (medicine, law, news)
Tag and explain sources clearly
Combine LLMs with retrieval engines (like ChatGPT’s "Browse" or “RAG” systems that pull live facts)
Make hallucinations detectable by design (via explainable AI or watermarking)
Quote for Your Article:
“We won’t reach 0% hallucination — but we’ll build systems smart enough to know when they might be wrong, and honest enough to say so.”
 |
|
|
- Martin Seto
About Me
Martin Seto
 |
|
|
reflexmediasales.com or 416-907-6562, and on LinkedIn.
Most Recent Blog Comment
 |
|
| Lorene Shyba says: | |
Full of terrific information, Thanks!... |
|
Most Read Stories
