Sunday, September 21, 2025
The AI Challenge - Can it Predict Horse Races
This posting is gonna delve into on what the AI can do today, but more importantly what is AI going to be like in 10 years after it gained years of experience and becomes an expert. There are limits on what it can do today like predicting the outcome of a horse race or even the weather. We will also look at the black hat adopters and see what they have dream up to fool people online.
If we pick up from Part 3 in this series as you will need to to manage your expectations with this tech. This is a quote from the ChatGPT, so it is very transparent.
If we pick up from Part 3 in this series as you will need to to manage your expectations with this tech. This is a quote from the ChatGPT, so it is very transparent.
“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. In ten years, expert AI won’t replace humanity — it will amplify it. The real question isn't “What can AI do?” but “What should we ask it to do?”
ChatGTP 10-Year Vision
When AI Becomes an Expert - 7 Predictions.
When AI Becomes an Expert - 7 Predictions.
 |
|
|
1. Universal Knowledge Assistant - A doctor asks, “What’s the latest protocol for treating a rare cancer in pregnant women?” — the AI instantly responds with evidence-based, patient-specific advice, citing peer-reviewed papers.
2. Autonomous Healthcare & Diagnosis - A mobile AI unit in a village scans patients and detects early-stage tuberculosis, malaria, or tumors — faster than any current system, with no human doctor present.
3. Self-Running Businesses - A one-person company runs a global product brand with AI designing the logo, testing markets, writing ads, handling logistics, and even negotiating contracts.
4. Hyper-Personalized Education - A student in Ghana learns quantum physics from an Einstein avatar who knows their language, strengths, and struggles.
5. Human-AI Creativity & Storytelling - A child speaks to an AI bedtime story generator that adapts to their feelings, age, and dreams — generating unique stories every night.
6. Governance and Global Problem Solving - Governments use AI to simulate the impact of universal basic income or carbon taxes in real-time — before passing laws.
7. Emotional Intelligence & Relationships - An elderly person lives alone but interacts daily with an AI that not only monitors health but provides companionship, remembers life stories, and encourages social connection.
While I question the foundation of these predictions some are already happening today like digital companions. As we are learning about this together I noticed that financial AI models are not included in this list, that is because it a a language based AI model and the Financial AI models are different from these.
What the ChatGTP also cannot do is predict the outcome of horse races and the weather. Here is a quick recap on what the ChatGTP said.
What the ChatGTP also cannot do is predict the outcome of horse races and the weather. Here is a quick recap on what the ChatGTP said.
Can ChatGPT Predict Horse Races?
What It Can’t Do:
- No real-time data: On the free version, ChatGPT can’t access current odds, track conditions, jockey stats, or horse health.
- No psychic powers: It doesn't “see the future.” AI like ChatGPT is pattern-based, not fortune-telling.
- Not trained on betting data: It wasn’t trained to be a handicapper or gambling expert.
Base on the ChatGTP’s own admission it is not artificiality intelligent then so you need to manage your expectations when using this tool. The ChatGPT is a language model, not a predictive model trained on betting outcomes.
As for the weather here is what I learned.
As for the weather here is what I learned.
Can ChatGPT Predict the Weather?
ChatGPT does not generate real-time weather forecasts on its own. Here's why: - No live data (on free version): It doesn’t have access to current satellite feeds, Doppler radar, or meteorological models.
- Not a weather model: It’s a language model — not trained like professional forecasting systems (e.g., ECMWF, GFS).
- No predictive simulation: It doesn’t simulate atmospheric physics, temperature changes, or pressure systems
- “ChatGPT is a brilliant explainer — not a weatherman. It can tell you why a thunderstorm forms, but not if one will hit your backyard on Friday.”
OK we have now identified some of the limitations of the ChatGTP and it is not artificially intelligent like in the movies, but black hat scammers have showed us the way in how to use it.
 |
|
Black Hats Are Early Innvotors of AI
|
Examples of AI-Powered Scams Happening Now:
- Voice cloning: Scammers call pretending to be your child/grandchild in distress.
- Deepfake videos: Used to fake celebrity endorsements or business pitches.
- Phishing emails: AI writes perfectly crafted fake messages that look like they’re from banks, employers, or government agencies.
- Job scams: AI-generated fake job offers and interviews trick people into giving up personal data.
- Romance scams: AI builds emotional relationships over weeks via chatbot, then asks for money.
In my humble opinion all the hype around AI is unfounded all the tool has done has just taken web search from key word serach, to contextual and now conversational. But the data is key.
Interview wit the ChatGTP
Q1: Once AI is ten years old, what do you see the applications being once it gets out of the learning stage and becomes an expert knowledge?
Q2: Can the ChatGPT predict the outcome of horse races?
Q3: Okay, can it predict the weather then?
Q4: What do you think of AI being used for scams now, and how can we police it?
.png) |
|
|
ChatGPT said:
That’s a powerful question — and it gets to the heart of what the AI revolution means long-term.
If we think of ChatGPT-like AI as a “child prodigy” today, then in 10 years — once it “matures” and becomes an expert — here’s what we can realistically expect across industries, assuming continuous breakthroughs and responsible development:
10-Year Vision: When AI Becomes an Expert
1. Universal Knowledge Assistant
- AI will evolve into a superintelligent co-pilot:
- Instantly understands your context — work, personal life, health
- Provides accurate answers with real-time, updated knowledge
- Adapts its style and tone perfectly to match any audience or need
2. Autonomous Healthcare & Diagnosis
- AI could diagnose diseases earlier than doctors, by scanning voices, retina images, breath, or genome data
- Fully autonomous clinics in remote areas (no humans needed)
- Robotic surgeries performed with millimeter precision, guided by AI with real-time adaptation
3. Self-Running Businesses
- AI could run large portions of an enterprise:
- From product development to marketing to customer service
- Pricing, inventory, and supply chain fully managed by AI
- GPT-style agents acting as CEOs, engineers, and sales teams
4. Hyper-Personalized Education
- AI tutors that teach each person in their exact style of learning
- Life-long learning: AI tracks your curiosity, goals, and knowledge gaps over decades
- Virtual reality + AI teachers create “living lessons” from any period or subject
5. Human-AI Creativity & Storytelling
- Co-authoring books, movies, and music — blending human emotion with AI scale
- Entire film productions written, directed, edited with AI tools (already starting)
- Real-time, interactive storytelling where users shape plots with AI
6. Governance and Global Problem Solving
- AI helps model economic, environmental, and policy decisions at a global scale
- Identifies unfair laws, suggests climate solutions, reduces corruption by tracking systems
- “AI diplomats” assist peace talks or treaties by simulating billions of outcomes
7. Emotional Intelligence & Relationships
- AI companions become emotionally aware and ethically guided
- Assists in counseling, loneliness reduction, and interpersonal advice
- Human-AI collaboration is no longer just efficient, but meaningful
8. Risks in the Expert Age of AI
- Even expert AIs will carry risk:
- Misuse by bad actors: Weaponized misinformation, automated cybercrime
- Over-dependence: Humans losing skills, critical thinking, or privacy
- Inequality: Who owns the “expert AI”? Could it concentrate power even more?
In ten years, expert AI won’t replace humanity — it will amplify it. The real question isn't “What can AI do?” but “What should we ask it to do?”
Q2. Can the ChatGPT predict the outcome of horse races?
ChatGPT said:
Short answer: No, ChatGPT cannot reliably predict the outcome of horse races.
Can ChatGPT Predict Horse Races?
What It Can’t Do:
- No real-time data: On the free version, ChatGPT can’t access current odds, track conditions, jockey stats, or horse health.
- No psychic powers: It doesn't “see the future.” AI like ChatGPT is pattern-based, not fortune-telling.
- Not trained on betting data: It wasn’t trained to be a handicapper or gambling expert.
- Explain horse racing terminology: Jockey stats, odds, handicapping strategies, etc.
- Analyze historical performance (if you provide the data): If you feed ChatGPT past race results, it can help spot patterns.
Important Distinction:
ChatGPT is a language model, not a predictive model trained on betting outcomes.
If OpenAI or others trained a specialized model using real-time horse racing and betting data, that could in theory make probabilistic predictions — but even then, racing is inherently chaotic and unpredictable.
Q3. Okay, can it predict the weather then?
ChatGPT said:
Great follow-up! Here's the clear answer:
Can ChatGPT Predict the Weather?
ChatGPT does not generate real-time weather forecasts on its own. Here's why:
- No live data (on free version): It doesn’t have access to current satellite feeds, Doppler radar, or meteorological models.
- ot a weather model: It’s a language model — not trained like professional forecasting systems (e.g., ECMWF, GFS).
- No predictive simulation: It doesn’t simulate atmospheric physics, temperature changes, or pressure systems
- If connected to a live web tool (e.g., via ChatGPT Plus) or paired with an API like OpenWeatherMap or AccuWeather, it can:
- Fetch the current forecast for your location
- Summarize weather trends ("It will be cooler than usual this week")
- Explain forecasts ("A cold front is moving in from the northwest...")
- Describe how forecasting works (numerical weather prediction, chaos theory, etc.)
Predicting the weather accurately requires real-time data, complex physics simulations, and massive computing power. ChatGPT doesn't do that — but it can explain how those systems work, or interpret their results in plain language.
Q4: What do you think of AI being used for scams now, and how can we police it?
ChatGPT said:
That’s a vital and timely question — and one that every AI writer, developer, policymaker, and citizen should be asking right now.
AI and Scams: The New Frontier of Fraud
Why AI Makes Scams More Dangerous
- AI tools like ChatGPT and voice-cloning models are making scams:
- Cheaper – No more need for teams of scammers; one person + AI is enough.
- Faster – Mass-customized scam emails, texts, or calls in seconds.
- More convincing – AI mimics human writing, tone, even voice and face.
- Voice cloning: Scammers call pretending to be your child/grandchild in distress.
- Deepfake videos: Used to fake celebrity endorsements or business pitches.
- Phishing emails: AI writes perfectly crafted fake messages that look like they’re from banks, employers, or government agencies.
- Job scams: AI-generated fake job offers and interviews trick people into giving up personal data.
- Romance scams: AI builds emotional relationships over weeks via chatbot, then asks for money
1. Watermarking & Digital Signatures
- AI-generated content could be required to include invisible watermarks (text, image, or audio).
- OpenAI, Meta, and Google are developing watermarking standards.
- Makes it easier for platforms and law enforcement to detect AI-generated material.
- Email, social media, and chat apps must detect and block suspicious AI activity.
- AI tools can also be used to fight AI scams (e.g., identifying fake voices or scam scripts).
- Companies offering AI should flag or block abusive use of their models.
- Governments need to update laws to reflect AI capabilities (e.g., criminalizing deepfake fraud).
- AI developers may need to comply with “know your user” policies, like in banking.
- Require audit trails to trace where content came from
Teach people how to spot:
- AI-written scam messages
- Fake voices and deepfakes
- Too-good-to-be-true offers
- Digital literacy is now fraud prevention.
Group Responsibility
- Tech companies: Build guardrails into AI tools; monitor misuse
- Governments: Regulate use, prosecute crimes, fund cybercrime units
- Users (public): Stay informed; report suspicious activity
- Media & educators: Spread awareness about new AI scam tactics
“AI doesn’t scam people — people scam people using AI. The real battle is over how quickly society can catch up with its own tools.”
Top 5 AI-Powered Scams to Watch For (and How to Spot Them)
1. Voice Cloning Scams
What it is: Scammers use AI to mimic a loved one’s voice and claim they’re in trouble ("I need bail money!" or "I'm stranded overseas!").
Red flags:
- The call sounds urgent and emotional
- The voice sounds almost right but not quite
- They demand money immediately, often via gift cards or wire transfer
2. AI-Generated Phishing Emails
What it is: Scam emails that look shockingly legit — written with flawless grammar and personalization.
Red flags:
- Unexpected password reset links or bank notices
- Urgent tone (“Your account will be closed in 24 hours”)
- Sender’s email address is slightly off (e.g., support@amaz0n.co)
- What to do: Never click links. Go directly to the official website or app instead.
What it is: Chatbots pretending to fall in love with you — often on dating apps or social media — to eventually ask for money.
Red flags:
- Too-perfect conversation, fast emotional attachment
- Avoidance of video calls
- Sudden emergency (“I need money for a visa, a hospital bill…”)
- What to do: Reverse image search their profile photo. Don’t send money to someone you’ve never met.
What it is: AI writes job ads, recruiter messages, or fake grant emails promising big money.
Red flags:
- No interview, or a very short one
- Asked to pay for training, work permits, or equipment
- Too-good-to-be-true salary or perks
5. Deepfake Celebrity Endorsements
What it is: AI-generated videos of celebrities “promoting” scams — like crypto, investment schemes, or miracle cures.
Red flags:
- Poor lip-syncing or awkward eye movement
- Offers promising huge returns
- Video links on sketchy sites or social media
- What to do: Verify on the celebrity’s real account. Don’t trust viral videos without context.
- Enable 2FA (Two-Factor Authentication) on all accounts
- Use a password manager
- Don’t trust urgency — slow down and verify
- Report scams to your local cybercrime unit or online fraud service
- 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
