Next Generation Orb
Next Generation Orb in Use
The 2 minute video in Video Source 22 below is truly worth watching. Project Astra by Gemini (located in a cell phone) is very observant and helpful. This video starts with the image shown below.
Where should I start? What should my first steps be? What goals should I set for myself? How much time do I need to devote to this study? Where will I see the most immediate benefits? What are some pitfalls to avoid? From whom or where can I get advice about this journey? Should I consider AI a philosophy, a skill set, an adventure, an academic endeavour, a process, a way of thinking, a tool-box, a release, an abyss, a new language, a new sport, a new paint set to color the world, a group effort, a private study, a way of life, a religion, a new beginning, a way to dig deeper into my current interests? Is AI scary? Is AI applicable to everything I do? What equipment helps me use AI? What tools are available? Should I start now or wait a year? Do I need special new AI friends or will the whole world be moving in this same AI direction? Are there knaves ready to lead me astray in AI?or Is AI so valuable that it needs to be fully applied in every aspect of my life. Will AI cause me to add new associates to my life? Is there a danger of AI becoming addictive? Will AI make me a better person? Today's young people are said to spend too much time with their devices, their cell phones; is AI as addictive, is it hugely time-consuming? Are there many traps within the AI spectrum?
Who should I discuss AI with? my family my lawyer my doctor my friends my best friend my political associates my psychiatrist everyone, everywhere no-one facebook groupsOr. . . is it all of the above?
Which AI websites should I try first? ChatGPT CoPilot (Microsoft) TED This is my first choice. See Video Source 02 Max Sills (Video Source 02)Artificial intelligence is shattering expectations of human predictability, motivation and speed in every part of society - including law. Lawyer Max Sills explores the practical challenges of negotiating with AI-powered systems as they become integrated into the world around us, offering a hopeful path to navigate these soon-to-be transformed institutions.
Companies
---------
Accenture - provides AI expertise (assistance) to European companies
Anthropic - Dario Amodei
Bard - Timothy Ring
BxAI - Elon Musk
Claude AI - by Anthropic (free). Pay for Claude Pro (data up to 2022)
Claude 3 - Haiku, Opus and Opus
Conjecture - Connor Leahy CEO
Crusoe Energy - with Oracle and OpenAI to provide (Source 39) servers using Nvidia's AI chips
DeepMinds - Sir Demis Hassabis teamleader creating AlphaGo
Google - DeepMind (Mustafa Suleyman)
Inflection - owned by MicroSoft
Nvidia - CEO Jensen Huang
OpenAI - began before 2018, current CEO Sam Altman
- GPT-2 Connor Leahy reverse engineered in 2010?
- GPT-3 (June 2020) - Large Language Model (LLM)
- ChatGPT (2024) - polished version of GPT-3
- GDPR (General Data Protection Regulator)
- Gemini (with verbal interactions - by Google)
- GPT-4 (future)
- GPT-4o (Canvas)
- GPT-5s (2023 or 2024?)
- Q* 2.5 (2024) OpenIA Alignment (Sebastian Moss)
Shadow Phoenix (Russia attack)
- Q* [say Q-STaR] Mira Murati got Sam Altman oustered (but he was rehired)
- OpenAI O1 announced in October 2024 (based on GPT-4o?)
StabilityAI - Emad Mostaque CEO (has a kid who "had" autism.)
Waymark - an AI video tech company: makes movies eg "The Frost"
Source 18 is a prediction of the AI Future.
What if an AI system could produce its own "data sets"?
Mike Wooldridge (Video Source 06)
Artificial Intelligence is different from Human Intelligence.
Very Important Paper: "Attention is all you need" by Ashish Vaswani Transformer Architecture Rich Sutton - Canadian AI Expert at University of Alberta (invented Reinforcement Learning) Big AI Emergent Capabilities from GPT-3 multimodal: text, images, sounds "Augmented Large Language Models" "Machine Conciousness" Blake Lemoine says "Our machines are sentient!" The hard problem (David Chalmers) Patrick Nagel (1970) "Some is conscious if it it like something" Nagel: AI and art Safe GuardRails are needed.
From Video Source 04 -------------------- 1 Learn AI Limitations ethical, bias 2 Curiosity & Continuous Learning keep-UpToDate Tools 3 Natural Language Processing learn the principles 4 AI Project Management 5 Business Strategy & Implementation identify opportunities 6 Creative AI Thinking use our imagination 7 Data StoryTelling/Visualization 8 Personal Branding create a picture of one's self 9 Prompt Engineering ask pertinent questions
You need to "fact-check" everything that ChatGPT produces. Guard-Rails are being implemented. Does this herald "General AI"? Is this technology the key to "General Artificial Intelligence?" or "Artificial General Intelligence" Video Source 08 History of AI over the years Must-reads by Greene: 1. Fabric of the cosmos, 2. Hidden reality, 3. Until the end of time Post Labor Economics Universal Basic Income (UBI) StabilityAI CEO: Emad Mostaque (has a kid who "had" autism.) 2017 Big Data
----------------------------------- The "AGI Deadline" (Artificial General Intelligence) ASI (Artificial Super Intellignece) "AI or Super-Intelligent Alignment" (i.e aligned with human values) "Generative Pre-trained Transformer" (GPT) QUALIA Deep-Q Project TUNDRA Yann LeCun Auto-Regressive Noam Brown Game-Playing Systems AlphaGo by Habbassis AlphaZero "System 2" thinking Libratus Cicero (Diplomacy) Andre Carpathay? re using Game Theory in AI
36 ChatGPT Tips (Video 14) (2024) by Drake Suratch 1 Prompt - follow-up questions analyzing, understand and expand 2 Assign a role 3 use sloppy 4 set your context within the prompt 5 rename your chat logs within ChatGPT 6 utilize prompt sequences [Goal], [Context], [Action] 7 Archive Chat for later use 8 Use Custom Instructions (for 3N+ customers) 9 Speak with ChatGPT 10 Utilize Output Formating 11 Identify Objects using GPT-4 (w vision :images) 12 Use ChatGPT for research assistance (up to 2023 D April) 13 Use it for knowledge retention explain it like I were 5 give me an analogy to better understand its function 14 Use ChatGPT in order to plan 15 Utilize the "plug-in" store (130 pages of stores eg Wolfram 16 Generate Check-lists 17 Share chats within ChatGPT 18 Create a GPT GPT is like a partner, employee or staff 19 Use ChatGPT to brainstorm 20 Use it to enhance your stories or writings 21 Understand its limitations always double-check the results (biases errors) 22 Generate images using ChatGPT create a picture of .... 23 Summarize long text within long text eg summarize a book 24 Use analogies to understand complex topics 25 Use it for language translation 26 Use it to analyze documents (use GPT+) 27 Create Mind Maps 28 Use web browsing for data input ask it to create video ideas and scripts 29 Create Descriptions or Slogans 30 Use it for interior styling (for rooms) 31 Use for SEO (Search Engine Optimization) https://aifoundations.io 32 Change your theme within ChatGPT 33 Use ChatGPT for problem solving 34 Use 3rd party applications (change UI user intefface) 35 Purchase his ChatGPT Mastery Course (Cost: $ ?) "Engineer Your Life" The group is super-early 36 Subscribe to "AI Foundations" Become a Pro Rated (9) by the author Video Source 15 has not yet been viewed nor rated. Also watch Video Source 32: 12 Use Cases of the NEW ChatGPT Canvas (Future of Writing)Video Source 16 is by Connor Leahy, CEO of Conjecture, an expert in AI. He was recently recommended to the author by Christine Ward.
1 Reasoning, Logic eg Math Proofs 2 might create its own data sets
Copilot's immediate reply can be seen in Web Source 04.In 2025, which university courses are essential given the future impact of AI on people in their twenties?
The author asked another question of Copilot: Should I consider AI a philosophy, a skill set, an adventure, an academic endeavour, a process, a way of thinking, a tool-box, a release, an abyss, a new language, a new sport, a new paint set to color the world, a group effort, a private study, a way of life, a religion, a new beginning, a way to dig deeper into my current interests? Copilot responded: AI, like a multifaceted gem, reflects myriad facets. Let's explore its shimmering dimensions: Philosophy: AI invites contemplation. It poses questions about consciousness, ethics, and the boundaries of intelligence. Dive into the philosophical depths where AI meets metaphysics. Skill Set: Sharpen your digital chisel. Learn algorithms, programming languages, and data manipulation. Craft AI models like an artisan shaping clay. Adventure: Embark on a quest through neural networks and algorithmic jungles. Uncharted territories await - discover, iterate, and innovate. Academic Endeavor: Enroll in the halls of AI academia. Decode research papers, attend lectures, and unravel the mysteries of AI's inner workings. Process: AI dances to an algorithmic rhythm. It's the choreography of data preprocessing, model training, and validation. A symphony of 0s and 1s. Way of Thinking: AI rewires cognition. It's not just code; it's a mindset. Think probabilistically, embrace uncertainty, and let neural pathways spark. Toolbox: AI, your digital Swiss Army knife. Extract insights, automate tasks, and predict outcomes. Each algorithm - a tool for a specific job. Release: Unshackle creativity. AI generates art, music, and poetry. It's the muse that whispers in binary. Abyss: Peer into the void of AI's limitations. Bias, black boxes, unintended consequences. The abyss gazes back. New Language: Speak Python, TensorFlow, and PyTorch. Decode neural hieroglyphs. Conversations with machines. New Sport: Compete in Kaggle arenas. Score touchdowns with neural nets. The adrenaline rush of accuracy metrics. Paint Set: AI wields brushes of pixels. Colorize old photos, compose symphonies, and dream in RGB. Group Effort: Collaborate in open-source communities. Code together, debug together. AI, a collective masterpiece. Private Study: Solitude and algorithms. Late nights deciphering code. The quiet hum of GPUs. Way of Life: AI permeates existence. From chatbots to recommendation engines, it's woven into our digital fabric. Religion: Worship at the altar of neural activations. Seek enlightenment in backpropagation. The church of Turing. New Beginning: Reset weights, initialize hope. AI, the phoenix rising from data's ashes. Deeper Dive: Plunge into your passions. AI augments astronomy, music theory, ecology. Illuminate your interests. Choose your prism. AI awaits - a canvas, a labyrinth, a quantum leap. WHAT AN ENRICHED RESPONSE !!!!
My response to Copilot: ---------------------------- Reply in words that a five year old would understand Copilot -------- Sure! Imagine AI as a magical toolbox. ??? Magic Tools: Inside this toolbox, there are special tools that can think and learn like wizards. They're called algorithms. ??????? Talking Robots: These tools help us create talking robots. You know, like when you talk to Siri or ask questions on the computer. ???? Picture Painters: AI can also paint pictures! It uses colors and shapes to make beautiful art. ???? Brain Helpers: Just like how our brains remember things, AI can remember too! It helps us find answers and solve puzzles. ???? New Languages: AI speaks its own language. It's like learning a secret code to talk to computers. ????? So, AI is like a magical friend that helps us do cool things with computers NOTE: the ??????? were all emoticons that would appeal to a 5 year old !!!
I googled: Did Nagel say "Someone is conscious if it is like something" ' Google said: Your search - Nagel said "Someone is conscious if it is like something" - did not match any documents. But I asked Copilot: Did Nagel say "Someone is conscious if it is like something" Copilot Yes, Thomas Nagel, a philosopher, famously expressed the idea that consciousness is characterized by what it is like to experience something. He coined the phrase: "Someone is conscious if it is like something" . In other words, when we are conscious, there is a subjective experience - an inner "what it feels like" to be us. Nagel's exploration of this concept has influenced discussions on the nature of consciousness and the mind. But if I removed the quotation marks, Google said: Perhaps the most fundamental and commonly used notion of "conscious" is captured by Thomas Nagel's famous "what it is like" sense (Nagel 1974). When I am in a conscious mental state, there is "something it is like" for me to be in that state from the subjective or first-person point of view.People using Google on iPhones get inferior results. People using MicroSoft laptops, can use "Copilot" (an icon in the bottom right-hand corner) to get superior results.
To get a better response, I had to rephrase my question to Google. And the answer was not as well presented WHAT MORE NEEDS TO BE SAID? Copilot is somewhat better than Google !!!
This comparison is as of 2024DApr25. See Source 07 for more information. 1. No Knowledge cutoff 2. Footnotes 3. A more advanced model 4. Voice inputs 5. Image inputs 6. Image generation 7. Shopping assistance
This is perhaps the breakthrough that openAI was hesitant to release when it briefly fired its president, Sam Altman. Apparently the board of openAI thought that stronger safeguards were needed before releasing the breakthrough to the public.We are launching our newest flagship model and making more capabilities available for free in ChatGPT.
(*) chatbot description by company
- ----------- -------------------------------------------------
(7) ChatGPT (version 3.5 use data up to 2021) by OpenAI
(8) ChatGPT Plus (version 4 uses data up to December 2023)
(9) ChatGPT 4o (oral interface released 2024 E May 14) by OpenAI
( ) Gemini (formerly Bard) by Google
( ) Socratic (for kids and students) by Google
( ) Code Assist (programming tool) by Google
(5) Copilot (formerly Bing Chat)by MicroSoft uses GPT-4 Turbo
( ) Image Creator from Microsoft Designer
( ) WolframAlpha (math & Science from Mathematica) at WolframAlpha.com
( ) Jasper (not free, for businesses and marketers) with plagiarism checker
( ) Claude (for summarizing documents) by Anthrophic
( ) Perplexity (links to internet and sources) at perplexity.ai
( ) chatsonic (not free, is uptodate regarding current events)
( ) Azure (not free) by Microsoft
( ) Canvas (not free) in 2024 by OpenAI
( ) Artifacts (not free) in 2024 by Anthropics
* rating by David COLE
1. Go to Click Here
moderated by Mira Murati
2. Do NOT click on "Try ChatGPT"
3 Click on
"Rewatch the live stream" that is to its right
You should then see a picture of 2 guys
4. Click on the triangle in the circle
(in the bottom left corner of the video screen.)
5. The video should start immediately.
It is a 26 minute video. The first 10 minutes talks about their
new product called "GPT-4o". The remainder is an impressive
video demonstrating its capabilities such as translating and teaching.
dangers and limitations of generative AI Diffusion Models Ethical and social concerns Generative AI generative AI: How it functions Generative AI's influence on visual creativity Generative AI in audio production Generative Adversarial Networks generative AI: Model drift and data poisoning Large Language Model large-scale generative AI models Legal risks Linguistic transformation: Multimodal models Operational risks The two sides of generative AI Transformer models Using synthetic data to solve data scarcity challenges Utility of generative AI Variational Autoencoders
1. Custom Instructions 2. Memory 3. Temporary Chat 4. Improve the model for everyone 5. Theme
Please note that we currently do not provide the Hailo Dataflow Compiler (DFC) for the general public. [Ed Note: DFC is available as of 2024 G Jul 01] A user had complained: I wish this was communicated before I bought the AI kit. It should be stated somewhere obvious, like the Raspberry Pi AI Kit product page. [Ed Note: various users have mixed success when downloading the DFC]
He mentions future "autonomous personal assistants". Altman also wrote:"Deep learning worked!" In 15 words, he says: "deep learning worked, got predictably better with scale, and we dedicated increasing resources to it.".
Source 24 describes Sam Altman's recent (2024ISep27) talk and his comments about the departure (see Source 25) of 3 top members of OpenAI team:"I believe the future is going to be so bright that no one can do it justice by trying to write about it now; a defining characteristic of the Intelligence Age will be massive prosperity," he wrote. "Although it will happen incrementally, astounding triumphs - fixing the climate, establishing a space colony, and the discovery of all of physics - will eventually become commonplace. With nearly-limitless intelligence and abundant energy - the ability to generate great ideas, and the ability to make them happen - we can do quite a lot."
Sam Altman seems to still be revered as a (or perhaps the) leading expert in Artificial Intelligence today. For a Sam Altman interview in May 2024 see Video Source V218:26 below.He began by thanking [Chief Technical Officer Mira] Murati and the other two outgoing executives, VP of research Barret Zoph and chief research officer Bob McGrew, for their contributions.
Perplexity AI is an AI-powered research and conversational search engine that answers queries using natural language predictive text. It is based in San Francisco, California.
Founded in 2022, Perplexity generates answers using sources from the web and cites links within the text response.[2] Perplexity works on a freemium model; the free product uses the company's standalone large language model (LLM) that incorporates natural language processing (NLP) capabilities, while the paid version Perplexity Pro has access to GPT-4, Claude 3.5, Mistral Large, Llama 3 and an Experimental Perplexity Model.[3][2][1] In Q1 2024, it had reached 15 million monthly users.[4]
History
Perplexity was founded in 2022 by Aravind Srinivas, Denis Yarats, Johnny Ho and Andy Konwinski, engineers with backgrounds in back-end systems, AI and machine learning. Yarats, the CTO, was an AI research scientist at Meta, while Srinivas, the CEO, worked at OpenAI as an AI researcher. Ho, the Chief Strategy Officer, worked as an engineer at Quora, then as a quantitative trader on Wall Street, and Konwinski was among the founding team at Databricks.[5]
See the full wikipedia article for links to the footnotes appearing in square braces (in the above).
The First Law: A robot may not injure a human being or, through inaction, allow a human being to come to harm.
The Second Law: A robot must obey the orders given it by human beings except where such orders would conflict with the First Law.
The Third Law: A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.
Accenture runs GenWizard (Julia Sweet, CEO)
Alphabet owns Google
Apple sells iPhones
Google runs Gemini (an AI chatbot)
Horizon3 run by Accenture
MediaTek with NVIDIA have a 3nm AI PC CPU
Meta owns Facebook
Micron Tech. sells HBM memory chips
Microsoft sells Windows
Microsoft runs Bing (an AI chatbot)
Microsoft runs Copilot (an AI chatbot)
NVIDIA sales Blackwell Chips to be worth $10B
single chip price: US$22,000.
OpenAI runs ChatGPT series (an AI chatbot)
OpenAI runs GPT-4o (a superior AI chatbot)
OpenAI runs Strawberry
Palantir T. has data analytics software platforms
Perplexity runs Perplexity AI (an AI chatbot)
Qualcomm has Snapdragon X Elite chip
ServiceNow helps to streamline inefficiencies
teams up with NVIDIA
Snowflake runs custom chatbots on rented GPUs
Unilever with Accenture: Generative AI-Powered
Analysis of All Internet Information
Application of Extensive Corporate Resources
Creation of AI Corporations
Development of AI Software
Development of LLMs (Large Language Models)
Development of OpenAI O1 that reportedly THINKS
using "system two thinking"
Evolution of Computer Processors
Evolution of GPUs (Graphic Processor Modules)
eg NVIDIA's Blackwell GPU (Source 34)
Expanding Corporate Use of AI
Robots Equipped with AI
Source 34 (Tom's Hardware) announces that NVIDIA's Blackwell GPU (US$22,000) is sold out for the next 12 months (as of 2024JOct11).
Table of Contents What is Microsoft Copilot? What are the versions of Microsoft Copilot? When will Microsoft Copilot be available? How much does Microsoft Copilot cost? Copilot in Windows 11 What are business benefits to using Microsoft Copilot? How does Microsoft plan to integrate Copilot into its applications?
On 2024JOct04, Source 31 states:In Source 32, the webmaster has created a short text file listing recent news about various AI and related technology companies.
Sam Altman admits ChatGPT's Advanced Voice Mode tricked him into thinking AI was a real person: "I kind of still say 'please' to ChatGPT, but in Voice Mode, I couldn't use the normal niceties.
Speaking of ChatGPT, OpenAI recently shipped its long-awaited Advanced Voice Mode feature to ChatGPT Plus and Teams users. For context, the feature ships with five new voices, custom instructions, improved conversational speed, smoothness, and accents in select foreign languages.
It's worth noting that the feature isn't yet available in the EU, the UK, Switzerland, Iceland, Norway, and Liechtenstein. You'll also need a $20 monthly subscription to access the feature. While it remains unclear whether the feature will ship to broad availability, OpenAI may be reluctant to ship it because of the EU AI Act's stringent policies, prohibiting AI systems that can recognize a user's emotions.
For the full article, read Source 35 which predicts trillion dollar companies. It compares the Average IQ's of many recent (as of 2024JOct12) AI chatbots. It includes a link to a 32 second video.Wow. . . it says "But ChatGPT o1 reportedly THINKS!" . . . [with an IQ of 128! See the image below]
Large language models (LLMs) are incredibly good at stating things confidently, even if they aren't always correct. The OpenAI o1 model family from OpenAI is the latest attempt to fix that - by getting the AI to slow down and work through complex problems, rather than just running with the first idea it has.Later, it says:
It's a really interesting approach, and if o1 lives up to OpenAI's claims, it could be the start of another leap in just how useful LLMs can be.
What is OpenAI o1? OpenAI o1 is a new series of models from OpenAI. While they're similar to other OpenAI models, like GPT-4o, in many respects - and still use the major underlying technologies like transformers and a neural network - the o1 models are significantly better at working through complex tasks and harder problems that require logical reasoning.
Add the power of ChatGPT to your workflows Automate ChatGPT That's why Open AI is "resetting the counter back to 1" rather than releasing them as GPT-5. (And yes, the weird letter casing and hyphenation of all this drives me mad, too.)
Right now, there are three o1 models:
OpenAI o1: The most capable o1 model, it's currently unavailable, though OpenAI has released information about its performance.
OpenAI o1-preview: A preview version of the full o1 model, though it's not as powerful as the full model. It's available to ChatGPT Plus subscribers and through the OpenAI API.
OpenAI o1-mini: A version of o1 optimized for speed.
The o1 models aren't meant as a replacement for GPT-4o and GPT-4o mini: they offer a different price-to-performance tradeoff that makes sense for more advanced tasks. Let's dig into what that looks like.
How does OpenAI o1 work? According to OpenAI, the o1 models were trained to "think" through problems before responding. In effect, this means they integrate a prompt engineering technique called Chain of Thought reasoning (CoT) directly into the model.
When you give an o1 model a complex prompt, rather than immediately trying to generate a response, it breaks down what you've asked it to do into multiple simpler steps. It then works through this chain of thought step by step before creating its output.
In the introduction post on OpenAI's blog, you can see a few examples of how the o1-preview model uses CoT reasoning to analyze complex problems like decoding a cipher text, solving a crossword, and correctly answering math, chemistry, and English questions. They're worth looking through - they'll give you a much better idea of how the o1 models work.
[Chat] GPT-4o vs. OpenAI o1[ChatGPT-4o is the same as ChatGPT-4 Omni (where the "o" means "Omni".]
When it comes to tasks that require logical reasoning, OpenAI o1 and OpenAI o1-mini are significantly better than GPT-4o (and by extension, almost all other AI models). On typical AI benchmarks that require some logic where GPT-4o performs really well, like MMLU, OpenAI o1 still scores higher.
More interestingly, on tasks that require high levels of logical reasoning, GPT-4o tends to do pretty poorly. One example that OpenAI uses is the 2024 USA Math Olympiad (AIME) paper. Out of 15 hard math questions, GPT-4o was only able to answer two correctly. o1, however, was able to get 13 correct, which would place it among the top 500 students taking the paper in the U.S. The situation is similar on the competitive coding platform Codeforces. GPT-4o only scores in the 11th percentile, while the full o1 model scores in the 89th percentile.
by @labsanta 00:04 Generative AI is transforming how we work, learn, and teach. 03:15 Sam Altman discusses how AI and machine learning can personalize learning and broaden access to knowledge. 08:19 Discussion on progress towards generalized intelligence 10:37 GPT-4's launch was perceived differently due to internal familiarity, leading to surprise at public reaction 15:02 Definition of AGI is becoming meaningless 17:15 AGI may not require abstraction for functionality 21:51 Young people may have a relative edge in the tech industry. 23:58 Encouraging ambitious and long-term projects 28:02 The evolving shape of safety in AI technology 30:10 Regulation and trust are crucial for the future of AI. 34:05 Importance of accessibility and curiosity in AI 36:25 Importance of investing in cheap, clean, safe, reliable energy for business and security 40:43 AI will revolutionize education in the next two decades. 42:57 Rapid growth of OpenAI in a year 47:10 Future programmers will require higher programming skills 49:15 Society's challenge in adapting to rapid AI changes
Claude Elwood Shannon (April 30, 1916 - February 24, 2001) was an American mathematician, electrical engineer, computer scientist and cryptographer known as the "father of information theory" and as the "father of the Information Age".[1][2] Shannon was the first to describe the Boolean gates (electronic circuits) that are essential to all digital electronic circuits, and was one of the founding fathers of artificial intelligence.[3][4][5][1][6] He is credited alongside George Boole for laying the foundations of the Information Age.[7][8][9][6] Links to the footnotes can be found in the original article.Wikipedia also states Shannon's Equation (also called the Shannon - Hartley theorem) which is:
During the oral questioning concerning the WebMaster's Master's Thesis, one of the questions posed was "Can you prove (or derive) Shannon's Equation?" The WebMaster replied "No", but his Master's Thesis was none-the-less approved. It was probably Dean Andrew Booth PhD who posed the question. Dean Booth's wife, Kathleen nee Britton Booth PhD, was another of the WebMaster's professors at the University of Saskatchewan (Source 41). More is said of Kathleen Booth PhD in Article 220. The surname BOOTH appears in the WebMaster's list of known ancestors [his great grandmother Sarah Ann BOOTH (1855-1939)], but the relationship, if any, with Andrew BOOTH is unknown.C = B x log2(1 + S/N) C is channel capacity in bits/sec B is the channel bandwidth in Hz log2(k) is the function: logarithm to the base 2 of a number k S is the average received signal power in watts N is the average power of the noise and interference over the channel Note that S/N is NOT measured in decibels.
|
(To enlarge .....Click it)
Next Generation Orb |
(To enlarge .....Click it)
Next Generation Orb in Use |
@MrFlexNCAs of 2024 J Oct 20, this WebMaster does NOT yet buy it! If you haven't yet seen the "orb" video, here is the "Proof of Human" plan that resulted in the development of this orb:
1 day ago
To answer the question of what problem this solves: As the world becomes increasingly digital and AI becomes sophisticated enough to convincingly mimic humans (even in speech and video), the need for reliable human verification will become critical. Social media platforms and other online services may soon require this verification to ensure users are genuine before allowing account creation. If we don't establish a robust way to verify humanity, the internet could be overrun with fake accounts, an issue many already believe is happening now.
Inside OpenAI's O1: The revolutionary model that takes time to think.
The O1 models have already demonstrated strong performance in various benchmarks. For instance, in a qualifying exam for the International Mathematics Olympiad, the O1 model achieved an 83% accuracy rate - a significant leap from the 13% scored by OpenAI's GPT-4o. Brown noted that the ability to reason through complex mathematical formulas and scientific data makes the O1 model especially valuable for industries that rely on data-driven decision-making. . . .
As Brown concluded his talk, he emphasized that AI development is at a critical juncture: "Now we have a new parameter, one where we can scale up system two thinking as well - and we are just at the very beginning of scaling up in this direction."
by TED on 2024 D Apr 10 by Max Sills on 2023 J Oct 01 by NOVA PBS Official on 2024 C Mar 27 by AI Uncovered c2023 F Jun 01 by Scott Pelley c2019 F Jun 01 by Mike Wooldridge of The Turing Institute at The Royal Institution c2024 A Jan 01 by David Bombal w Mike Pound c2024 A Jan 10 by Turing Inst.Brian ? World Science Festival c2023 Dec 10 by World Science Festival Brian Greene w Jaron Lanier of Microsoft c2024 Feb 10 by Stephen Wolfram of Wolfram c2024 C Mar 10 by Global Education c2024 D Apr 11 TheAIGrid Fhilcar Faunillan Demmis Hassabis Google (or Deepmind?) CEO c2017 C Mar 10 Impact Theory Tom Bilyeu w Emad Mostaque c2023GJul18 by Drake Suratch of AI Foundations c2024AJan10 by Drake Suratch of AI Foundations c2024BFeb10 by Data Slayer c2024AJan10 by Connor Leahy at EISM (intro by Luis Razo) c2024CMar10 by the Inside View c2024CMar11 by Futurepedia c2023LDec10 by Mattew Berman c2023LDec10 by the AIGRID c2023KNov24 by Project Astra c2024EMay14 by Hailo c2024FJun10 by AI Uncovered c2024HAug11 by AI Foundations c2024ISep10 by Stanford eComer c2024EMay00 by AI Revolution c2024JOct07 by Meric Gertler of CBS c2024JOct07 by Linus Tech Tips c2024FJun00 Michigan Engineering c2024ISep12 CNET c2024JOct18 by Drake Suratch of AI Foundations c2024JOct25
The 10 Best AI Courses in 2024 by Megan Crouse on 2024DApr08
Aristotle's Categories by Zalta and Nodelman on 2024DApr19
Chronological List of Inventors / Thinkers by D@CC on 2024DApr19
Impact Of AI On University Graduates by Copilot on 2024DApr21
AI . . Smarter than any human. . . by 2025 by Bob Waugh on 2024DApr22
Google releases . . .new free resources to help you . . . . AI prompts by Sabrina Ortiz on 2024DApr22
7 Reasons why ... Copilot instead of ChatGPT by Sabrina Ortiz on 2024DApr25
The best AI chatbots: ChatGPT . . . [copilot etc] by Sabrina Ortiz on 2024DApr12
Introducing GPT-4o . . . . by openAI on 2024EMay13
How to write better ChatGPT prompts in 5 steps by David Gewirtz on 2024EMay01
AI Glossary (from CNET) transcribed by D@CC on 2024EMay26
Google Gemini Cheat Sheet (formerly Bard) from TechRepublic by Andy Wolber on 2024FJun 27
Generative AI: Everything you need to know from Android Police by Ben Khalesi on 2024GJul09
I tweaked 5 ChatGPT settings from ZDNet Police by Sabrina Ortiz on 2024GJul02
Raspberry Pi AI kit (with PCIe connector) from Seeed Studio on 2024GJul11
Dataflow Compiler (DFC) is now available! from Hailo on 2024GJul01
Search PineBerry (Pineboards) in Article 210. by D@CC on 2024DApr05
How to use ChatGPT: A step-by-step guide by Laura Pajuelo on 2024GJul15
Fei-Fei Li's World Labs by Marina Tempkin on 2024ISep13
With spatial intelligence, AI will understand the real world (a TED talk) by Fei-Fei Li on 2024DApr01
ChatGPT Cheat Sheet: ... Guide for 2024 by Megan Course on 2024ISep16
Sam Altman: AI superintelligence. . . soon... by Chris Morris on 2024ISep24
The Intelligence Age by Sam Altman on 2024ISep23
The Future of AI by Riddhi Kanetkar at Italian Tech Week on 2024ISep26
Mira Murati's exit ... [leaving OpenAI which is becoming] a profit-first corporation by David Meyer,Sharon Goldman in yahoo!finance on 2024ISep24
OpenAI to . . . . give Sam Altman equity by Krystal Hu,Kenrick Cai for Reuters on 2024ISep26
Sam Altman: Biography by Erik Gregersen for Britannica on 2024ISep26
ChatGPT Glossary: 47 AI Terms That Everyone Should Know by Imad Khan on 2024ISep29
OpenAI's bankruptcy flames linger on as Apple stops funding by Kevin Okemwa for Microsoft Start on 2024JOct01
Microsoft Copilot Cheat Sheet by Mark W. Kaelin on 2024JOct01
ChatGPT's Advanced Voice Mode by Kevin Okemwa at Windows Central on 2024JOct04
AI Companies by D@CC on 2024JOct07
Hinton isn't a fan of Sam Altman's Leadership by Kwan Wei Kevin Tan at businessinsider on 2024JOct09
Blackwell .. sold out.. next 12 months by Anton Shilov for Tom's Hardware on 2024JOct11
OpenAI Races Toward AGI with its New Breakthrough Model by Luke Lango on 2024JOct12
AI steps into science limelight with Nobel wins by ETX Studio on 2024JOct12
NVIDIA's most powerful chip: GH100 by Wayne Williams TechRadar on 2024JOct08
Accenture's Deal With Nvidia by Adam Spatacco on 2024JOct13
Crusoe . . .with VAST Data .. on Crusoe Cloud by Crusoe AI on 2024ISep26
. . . OpenAI o1? And how does it compare to GPT-4o? by Harry Guinness on 2024ISep17
Remembering a USask computing pioneer by Chris Putnam on 2022LDec06
. . . Murati . . . new AI startup . . by Anna Tong and Krystal Hu on 2024JOct18
AIHUB & FINDER site on 2024JOct24
OpenAI O1 by Noam Brown at TED at VentureBeat on 2024JOct24
One-Minute Daily AI News @ DATE (buggy) at reddit on 2024JOct25
One-Minute Daily AI News @ DATE (try this) at reddit on 2024JOct25