May 1, 2025: Top Websites Ranking

• chatgpt.com ranked fifth with 07:15 avg. visit duration

May 21, 2025: Sam & Jony introduce io

• “[S]hared values”

Apply

Please feel free to apply for funding via the following link.

Apply

Feedback

Please feel free to give feedback via the following link.

Feedback

Subscribe

Please feel free to subscribe via the following link.

Subscribe

Timeline

---

Explore OpenAI's groundbreaking journey in artificial intelligence. This timeline tracks the evolution of its key language models, from the initial Generative Pre-trained Transformer (GPT) to the advanced GPT-4, detailing each milestone in AI development. Discover the story behind these influential technologies.

OpenAI's Language Model Development: A Chronological Journey

Here's a summary of the motive, story, and source behind several of OpenAI's key language model advancements, presented in chronological order with their announcement/publication dates:

1. Language Unsupervised (GPT) - June 11, 2018

• Motive: The research aimed to overcome the limitations of supervised learning, which demands large, meticulously curated and costly datasets. Unsupervised learning presented a scalable solution by leveraging increasing computational power and the vast availability of raw data, thereby removing the dependency on explicit human labeling.

• Story: This work showcased a system that combined transformers with unsupervised pre-training, achieving state-of-the-art results across diverse language tasks. The methodology involved training a transformer model on extensive unsupervised data, followed by fine-tuning on smaller supervised datasets. This approach demonstrated improvements in areas like commonsense reasoning, semantic similarity and reading comprehension. The underlying language model also exhibited capabilities in tasks like sentiment analysis and answering multiple-choice questions without specific training.

• Source: OpenAI - Improving language understanding with unsupervised learning

2. Better Language Models (GPT-2) - Feb. 14, 2019

• Motive: The primary goal in developing GPT-2 was to create a language model capable of generating coherent text paragraphs and achieving top-tier performance on various language modeling benchmarks without task-specific training. The model was trained to predict the next word in a massive 40GB internet text dataset.

• Story: GPT-2 demonstrated impressive capabilities in generating synthetic text, performing basic reading comprehension, machine translation, question answering and summarization. It showcased a unique ability to adapt its style and content based on the provided conditioning text. The article also acknowledged the potential for malicious uses, such as creating misleading news or impersonating individuals online, which led to a staged release of the model.

• Source: OpenAI - Better language models and their implications. GPT-2 was trained on a dataset of 8 million web pages and possesses 1.5 billion parameters.

3. GPT-3 Evolution: From Research to Applications

• A. Research Paper: "Language Models are Few-Shot Learners" - May 28, 2020

  • Motive: To demonstrate that scaling up language models significantly improves task-agnostic, few-shot performance, allowing models to perform a variety of tasks with minimal or no task-specific training data. This contrasted with previous methods that required extensive fine-tuning datasets.

  • Story: OpenAI introduced GPT-3, an autoregressive language model with 175 billion parameters, 10 times more than any previous non-sparse language model.¹ The paper showed GPT-3's strong performance on many NLP datasets (including translation, question-answering and cloze tasks) and its ability to perform tasks requiring on-the-fly reasoning or domain adaptation, often outperforming models fine-tuned for those specific tasks. The paper also highlighted the model's capability to generate news articles that human evaluators found difficult to distinguish from human-written ones and discussed the broader societal impacts and potential risks.

  • Source: OpenAI - Language Models are Few-Shot Learners (The academic paper is often found on arXiv: arxiv.org/abs/2005.14165).

• B. OpenAI API Launch (Private Beta with GPT-3 Access) - June 11, 2020

  • Motive: To provide developers and researchers access to OpenAI's powerful new AI models (including the GPT-3 family) through a general-purpose "text in, text out" interface. This aimed to enable the development of new applications, help explore the strengths and limits of the technology, and commercialize the technology to fund ongoing research, safety and policy efforts. OpenAI also cited the difficulty for smaller entities to run such large models as a reason for an API-based release.

  • Story: OpenAI announced the release of its first commercial product, an API that allowed users to integrate models like GPT-3 into their products or develop new applications. The API was designed to be simple yet flexible. Given any text prompt, the API would return a text completion. It also allowed for honing performance on specific tasks through training on provided datasets or learning from human feedback. The launch was a private beta to carefully manage the deployment and study the real-world impacts and potential misuses of such powerful AI.

  • Source: OpenAI API

• C. GPT-3 Apps - March 25, 2021

  • Motive: To showcase the growing ecosystem and diverse applications being built using the GPT-3 technology through the OpenAI API, nine months after its initial commercial launch. It highlighted the real-world utility and adoption of the model.

  • Story: The article reported that over 300 applications were using GPT-3, with tens of thousands of developers building on the platform. It provided examples of applications across various categories and industries, from productivity and education to creativity and games, demonstrating the wide range of tasks GPT-3 could power.

  • Source: OpenAI - GPT-3 Apps

4. ChatGPT - Nov. 30, 2022 (Initial Release)

• Motive: OpenAI introduced ChatGPT to gather user feedback, understand its strengths and weaknesses, and ultimately enhance AI systems. Feedback on harmful outputs in real-world scenarios and insights into novel risks and mitigation strategies were particularly sought.

• Story: ChatGPT, a model trained for conversational interaction, can answer follow-up questions, admit errors, challenge incorrect assumptions and decline inappropriate requests. The model was trained using Reinforcement Learning from Human Feedback (RLHF), similar to InstructGPT.²

• Source: OpenAI - ChatGPT. ChatGPT was fine-tuned from a model in the GPT-3.5 series (trained in early 2022) on Azure AI supercomputing infrastructure.

5. GPT-4 - March 14, 2023

• Motive: GPT-4 represents OpenAI's latest step in scaling up deep learning, utilizing more data and computation to create increasingly sophisticated and capable language models. A significant focus was placed on making GPT-4 safer and more aligned.

• Story: OpenAI dedicated six months to enhancing GPT-4's safety and alignment by incorporating extensive human feedback, including input from ChatGPT users. Collaboration with over 50 experts in AI safety and security provided early feedback. GPT-4 is accessible via ChatGPT Plus and as an API for developers.

• Source: OpenAI - GPT-4. GPT-4 was trained on Microsoft Azure AI supercomputers.

---

OpenAI continues to shape the future of artificial intelligence. Understanding the progression of models like GPT-3 and GPT-4 offers insight into the rapid advancements in language technology and its potential impact.

Apply

Please feel free to apply for funding via the following link.

Apply

Feedback

Please feel free to give feedback via the following link.

Feedback

Subscribe

Please feel free to subscribe via the following link.

Subscribe

Apr 2, 2025: Introducing Ace

• About

  • Limited transparency

  • “Not perfect”

• Claims

  • “First”

  • “Superhuman”

Apr 4, 2025: Startup Syntax: First, Only.

• Claim pitfalls

• Other options

Subscribe now

Timeline

Feb 1, 2025: WSJ.com | No One Knows How to Price AI Tools

• Some seem to say AI is overpriced

• Some seem to say AI is underpriced

Subscribe now

AIaaS

As previously reported here the AI Era has begun with AI Native AIaaS. OpenAI GPT and Google Gemini are two obvious elephants in the room.

1. https://openai.com/chatgpt

2. https://gemini.google.com/advanced

It may be worth noting the per-user price point being set by the Two-Elephants of AIaaS: ~$20/mo/user vs. the average per-user price point of the SaaS Era.

Questions

1. How will the market receive ~$20/mo/user AIaaS model?

2. How will OpenAI GPT and Google Gemini address “negation handling”?

AI Vocab: “Negation handling is the ability of AI to understand and follow negative commands. It's a tough task for AI, often leading to errors. For instance, when told to "not include an elephant," AI may focus on "elephant" and still include it. This demonstrates the complexity of negative instructions in AI processing and the need for improved models.”—GPT4.

See five keys for dealing with “AI negation handling” when prompting AI here.

Subscribe

Subscribe to MasterVerse.AI Substack: 

Subscribe now

Disclaimer

***** The information herein is neither professional advice nor a replacement for professional advice and may be AI generated. Please consult a professional provider as needed. MasterVerse.AI is for informational purposes only and may include fact or fiction and provides no guarantee in any form. The reader assumes all risks for reading and is responsible for fact-checking anything and everything herein. ***** 

AI Q&A

The following Q&A is from the MasterVerse.AI Slack Community (anonymized and edited). Please join the community via the button below to get Access to AI.

Join MasterVerse.AI Slack Community

Job Requirements

NI: Can you break down the job requirements for a Freight Auditor who works with OTM? Could you phrase this in a way that would look good on a resume

AI: Certainly! Here are some job requirements, rephrased in a high-impact way suitable for a resume:

• **Proficient in Oracle Transportation Management (OTM) System**: Demonstrates advanced skills in utilizing OTM for tracking, analyzing, and reporting on freight data. Capable of leveraging the full functionality of the system to optimize freight audit and payment processes.

• **Freight Audit Expertise**: Possesses a comprehensive understanding of freight invoicing, billing procedures, and standard rate structures. Proven ability in auditing freight bills for accuracy, identifying discrepancies, and ensuring corrective actions.

• **Solid Financial Acumen**: Proven track record in managing freight cost accruals, reconciliations, and payment processing. Proficient in maintaining accurate financial records in accordance with organizational policies and regulations.

• **Advanced Analytical and Problem-solving Skills**: Demonstrates excellence in analyzing complex freight data and translating insights into actionable improvements. Proficient at resolving disputes and discrepancies with a high success rate.

• **Strong Communication and Collaboration Skills**: Skilled in liaising between carriers, finance departments, and logistics teams to ensure seamless freight audit and payment processes. Excellent at building relationships and engaging stakeholders at all levels.

• **Knowledge of Compliance and Regulations**: In-depth understanding of applicable shipping regulations, contract terms, and tariffs, ensuring all audits are compliant with these standards.

• **Detail-Oriented and Organized**: Proven success in managing high-volume audit records with precision and accuracy, showcasing strong attention to detail and organizational skills.

Remember to adapt these points based on your personal experience and the specific job requirements. Tailoring your resume to align with the job description can increase your chances of making it through resume screening processes.

Job Fit

NI: I have Accounting, Sports Marketing, and Management Major and experience as an Accounts Payable Analyst for ABC, INC and experience as a Freight Auditor for DEF, INC. I have worked with SAP, OTM, MBS, and OnBase. I am looking for a new job. What types of jobs would fit my background? Please only list the top 5 jobs I should be looking for

AI: Based on your experience in accounting, sports marketing, freight auditing, and familiarity with systems like SAP, OTM, MBS, and OnBase, here are five job roles that could be a good match for you:

1. **Supply Chain Analyst**: With your OTM experience and knowledge of freight auditing, a role in supply chain—particularly analyzing and optimizing logistics operations—could be a good fit. You could use your analytic skills to improve efficiency, minimize costs, and enhance customer satisfaction in a supply chain context.

2. **Logistics Coordinator/Manager**: Your experience with freight, familiarity with OTM, and your marketing background would serve well in a logistics role, where planning and coordination of freight operations and customer service play a major part.

3. **Financial Analyst**: Given your experience in accounts payable and familiarity with financial systems (SAP, OnBase), you could explore roles in financial analysis. In this position, your job would involve analyzing financial data, tracking financial performance, and helping guide business decision-making.

4. **Accounts Payable Manager**: With your experience as an Accounts Payable Analyst and your working knowledge of accounting systems, you could aim for a managerial role in Accounts Payable where you would oversee a team, manage vendor relations, and handle escalations.

5. **Transportation Management System (TMS) Consultant**: With your detailed understanding and hands-on experience of transportation management systems like OTM, you could consider roles in consulting or system implementation. You would provide expert advice to clients on how to use TMS to optimize their business processes, or work on implementing and customizing the system based on client needs.

Remember to tailor your resume highlighting the relevant skills and experiences for each job type.

Skills Assessment

NI: Assume that I am not entirely sure my SAP skills could translate to a new job. Could you please redo the list you created to now include the best jobs that I am suited for?

AI: Certainly! While SAP is a valuable skill, it's far from the only one you have. Let's revise the positions, considering your other experiences:

• **Freight Audit Specialist**: Given your experience in this field and skills with Oracle's OTM, this role would further deepen your expertise and open doors to managerial roles in the future.

• **Supply Chain Analyst/Coordinator**: Your experience with OTM and freight auditing would align well. You would work on streamlining logistics operations and handle freight related issues.

• **Accounts Payable Specialist or Supervisor**: Your previous experience as an Accounts Payable Analyst can open doors for you in these roles. While SAP was a tool you had used, the principles and tasks of accounts payable are consistent across other software too.

• **Logistics Account Executive**: Leverage your sports marketing and management major in a client-facing role within a logistics company. Your logistics knowledge can help you understand client needs while your marketing knowledge can be used to draw in new clients and manage relationships.

• **Transportation Coordinator**: In this role, you would be coordinating and overseeing the transit of goods from one place to another. Skills and experience with OTM software and freight auditing would be beneficial.

Remember, the objective is to showcase transferable skills when applying - your knowledge of accounts payable, freight auditing, and your academic background in sports marketing and management, for example. Each new role will likely require learning new systems but your foundational knowledge from prior roles will definitely help.

Location, Location, Location

NI: Can you list the top 5 cities in the US where my skills would be of the best use?

AI: Sure! The following cities are well-known hubs for industries like logistics, supply chain management, and financial services - all sectors where your skills would be exceptionally valuable:

1. **Chicago, Illinois**: Chicago is a major hub for freight and logistics companies, and has many corporations and industries that would value your freight auditing and accounts payable experience.

2. **Houston, Texas**: Known for its large energy industry, Houston also has numerous opportunities in logistics, marketing, and financial services.

3. **Atlanta, Georgia**: Home to many large corporations and a major transportation hub, Atlanta has plenty of opportunities in logistics and supply chain management.

4. **New York City, New York**: While known for finance and marketing, NYC also has a significant presence of industries like manufacturing and retail, where supply chain and logistics professionals are in demand.

5. **San Francisco, California**: If you're interested in tech or startups, San Francisco's vibrant market could be a great fit, as these companies often need expertise in logistics and financial roles.

These cities are just some of the many places where your skills could be in demand. It's always a good idea to research different locations to find the right fit for your personal and career goals. Also, with remote work becoming more common, you might not be limited by location for certain roles.

AI Summary

Uncover valuable insights on job roles suitable for an individual with unique skills such as Oracle Transportation Management (OTM), Accounts Payable, and Freight Auditing. The article also highlights top US cities ideal for these occupations.

AI Access

Join the MasterVerse.AI Slack Community ($14/month/user; currently free): 

• Have AI assist you with tasks

• Collaborate with others curious about AI

Join MasterVerse.AI Slack Community

Subscribe to MasterVerse.AI Substack (free and paid options): 

• See AI Art, Prompts, Q&A, and more…

• Paid subscribers have access to new and 250+ archived posts

Subscribe now

AI Training

Training

• AIaaS Intro - $300/intro/user

  • 1-month access to dedicated AIaaS

  • 2 hours of AIaaS training (1 online training; 2 hours per training)

Buy via Stripe

• AIaaS Bootcamp - $500/bootcamp/user

  • 1-month access to dedicated AI

  • 4 hours of AIaaS training (2 online trainings; 2 hours per training)

Buy via Stripe

Disclaimer

***** The information herein is neither professional advice nor a replacement for professional advice. Please consult a professional provider as needed. MasterVerse.AI is for informational purposes only and may include fact or fiction and provides no guarantee in any form. The reader assumes all risks for reading and is responsible for fact-checking anything and everything herein. ***** 

AI Access

Like justice, AI access may be anything but equal. MasterVerse.AI is powered by Evolution Accelerator and provides AI access.

Evolution was officially founded in 2018 in the Sacramento region. Why? It is reminiscent of Menlo Park in the ‘90s. Learn more about Alex and Evolution here:

Evolution Accelerator helps entrepreneurs with access to coaching, connections, capital, and now AI via MasterVerse.AI Slack community and Substack newsletter.

Join MasterVerse.AI Slack Community

Subscribe to MasterVerse.AI Substack: 

Subscribe now

Disclaimer

***** The information herein is neither professional advice nor a replacement for professional advice. Please consult a professional provider as needed. MasterVerse.AI is for informational purposes only and may include fact or faction and provides no guarantee in any form. The reader assumes all risks for reading and is responsible for fact-checking anything and everything herein. ***** 

Thanks to the for the post below and others for inspiration.

Keith’s Substack: Thoughts & Ideas on the Startup Ecosystem

What GTM strategy misses in these days of Owned vs Earned vs Paid Media

There was an author I once interviewed around his book, “Swimming with the Sharks” - its a straight-from-the-hip handbook by bestselling author and self-made millionaire Harvey Mackay who spells out the path to success for readers everywhere. His summary is that it’s not that dangerous if you know what you’re doing. That’s kinda how I feel about the cha…

Read more

3 years ago · 7 likes · 1 comment · keith newman

SubstackAI: Images // OpenAI GPT-4: Prompts // NI: Curation

The following AI images are based on the post above.

OpenAI GPT-4 Analysis and Summary:

The following are AI analysis and summary of the post above.

In a recent article by Keith Newman, he discusses the transformative shifts in the Media, PR, and Journalism industry. Traditional PR tactics like press releases are no longer effective, with most conventional rules being outdated. He stresses a significant movement toward paid media, where businesses pay to get their stories published in key media and research outlets - a technique best described as "pay to play." 

This method is prevalent across top media outlets that altered their selection criteria from "fit to print" to "fit to pay." Newman suggests that any business looking to propagate its PR needs a reasonable marketing budget to support these efforts. This shift initially began with B2B and Business media before it spread to consumer media. 

Newman advises businesses and individuals to have a strategic plan, cognizant of market realities, when venturing into this new media landscape – identifying their target audience, preferred media channels, and the key message to be conveyed. 

Despite the advantages of direct control and message-shaping in owned media or the trust level found with earned media, Newman proposes for a balanced marketing strategy leveraging both owned and earned media while embracing the "pay to play" model. The author insists on correct use of marketing motions and proper analytic tools to calculate ROI and meet key goals, gradually experimenting and reacting efficiently. 

AI Advantage

Instead of “paying to play”, access to AI may provide marketers the opportunity to increase marketing velocity of “owned media” leading to more “earned media”.

For example, MasterVerse.AI is providing free access to shared AI within a supportive Slack community and dedicated AI within a dedicated channel for $50/mo/user.

The difference between shared and dedicated AI is like exercising at the gym vs. at home. Both have benefits. So too, some AI trumps no AI.

Shared AI is shared by community members (i.e., AI co-working), whereas dedicated AI is not shared and used within a dedicated channel (i.e., AI solo-working).

Both shared and dedicated AI may empower creating more “owned media” vs. “pay to play media”. The cost of AI, may be pennies on the dollar vs. “pay to play media”.

If working with AI alone seems scary, AI “personal trainers” are available via the AI Training options below.

AI Access

• Shared AI in shared Channel - $14/month/user (free for now)

Join MasterVerse.AI Slack Community

• Dedicated AI in dedicated Channel - $50/month/user 

Buy via Stripe

AI Training

• AI Intro - $300/intro/user

  • 2 hours of AI training (1 online training; 2 hours per training)

Buy via Stripe

• AI Bootcamp - $500/bootcamp/user

  • 4 hours of AI training (2 online trainings; 2 hours per training)

Buy via Stripe

Disclaimer 

***** The information herein is neither professional advice nor a replacement for professional advice. Please consult a professional provider as needed. MasterVerse.AI is for informational purposes only and may include fact or faction and provides no guarantee in any form. The reader assumes all risks for reading and is responsible for fact-checking anything and everything herein. ***** 

People 1st, Business 2nd, Podcast 3rd

First, thanks to Keith Newman (KN) at “The Look Back” for hosting Alex Chompff (AC), the Entrepreneur and Investor, who’s powering Evolution Accelerator (EA).

Second, thinking about “what’s next” in business or investing? Wondering who, what, or where is the “gold in the goldmine”?

Third, listen to the podcast episode below to learn more about Alex, business, “what’s next”, and “gold in the goldmine”. Thanks again to KN and AC.

Keith’s Substack: Thoughts & Ideas on the Startup Ecosystem

Alex Chompff

Listen now (34 mins) | Thinking about starting a Co? Alex says this is the best time. Find out why by tapping into our discussion around the DNA of an entrepreneur, and get questions answered like: how do you build entrepreneurial muscle? Also, discover the differences between angel investors, venture capital investors, and accredited investors and learn what sets them apart…

Listen now

3 years ago · keith newman

Looking Learn More About AIaaS?

Join the MasterVerse.AI Slack Community ($14/month/user; currently free):

• Collaborate with other community members

• Ask questions to OpenAI GPT-4 and get answers 

• See images OpenAI DALL-E generated from text-prompts

• Send text-based prompts to OpenAI DALL-E to generate 512x512 images

• See transcriptions OpenAI Whisper generated for audio files

• Send audio files to OpenAI Whisper and receive transcriptions  

Join MasterVerse.AI Slack Community

Subscribe to MasterVerse.AI Substack: 

• See OpenAI GPT-4 questions and answers

• See OpenAI DALL-E and Substack AI images

• Over 200 posts published and ready to learn from

Subscribe now

Who Created MasterVerse.AI?

Alex Chompff (AC) is the Entrepreneur and Investor who created Evolution Accelerator, MasterVerse.AI Substack,and MasterVerse.AI Slack Community. 

AC believes in serving others. Those aren’t mere words. AC is funding the services above so others may learn AI through use and observation. Learn more here.  

To collaborate with AC and others curious about AI, join the MasterVerse.AI Slack Community using the link below:

Join MasterVerse.AI Slack Community

Disclaimer

***** The information herein is neither professional advice nor a replacement for professional advice. Please consult a professional provider as needed. MasterVerse.AI is for informational purposes only and may include fact or fiction and provides no guarantee in any form. The reader assumes all risks for reading and is responsible for fact-checking anything and everything herein. ***** 

Different AI > Same Prompt > Different Images

See below for how different AI generate different images using the same prompt.

To be clear, even the same AI will generate different images using the same prompt.

This is one of the potential powers of AIaaS, a seemingly endless supply of images. Don’t like the image generated? Generate again, again, and again.

Do you want to generate your own images using DALL-E? Join the MasterVerse.AI Slack community where the AI Bot powered by DALLE-E is ready and waiting.

The DALL-E images in this post were AI generated within our Slack community. To join is currently free and gives you access to generating your own AI images.

Join MasterVerse.AI Slack Community

OpenAI DALL-E Image Generator

Substack AI Image Generator

Free Services

Join the MasterVerse.AI Slack Community: 

• See paid answers OpenAI AI Bots powered by GPT-4 gave to questions asked by community members (i.e. NI) 

• Ask your own text-based questions to OpenAI AI Bots powered by GPT-4 and receive paid answers 

• See paid images OpenAI AI Bots powered by DALLE-E gave to text-based prompts made by community members (i.e. NI) 

• Send your own text-based prompts to Open AI Bots powered by DALLE-E and receive paid 512x512 generated images 

• See paid transcriptions OpenAI AI Bots powered by Whisper gave to audio files sent by community members (i.e. NI) 

• Send your own audio files to Open AI Bots powered by Whisper and receive paid transcriptions  

• Ask questions and get help from other community members (i.e. NI) 

• There’s currently no time limit to membership

• More features pending…  

Join MasterVerse.AI Slack Community

Subscribe to MasterVerse.AI Substack: 

• See paid answers OpenAI AI Bots powered by GPT-4 gave to questions asked by community members (i.e. NI) 

• See paid images OpenAI AI Bots powered by DALLE-E gave to text-based prompts made by community members (i.e. NI) 

• See paid transcriptions OpenAI AI Bots powered by Whisper gave to audio files sent by community members (i.e. NI) 

• See 1-month of posts 

Subscribe now

Paid Services

Subscribe to MasterVerse.AI Substack here: 

• See paid answers OpenAI AI Bots powered by GPT-4 gave to questions asked by community members (i.e. NI) 

• See paid images OpenAI AI Bots powered by DALLE-E gave to text-based prompts made by community members (i.e. NI) 

• See paid transcriptions OpenAI AI Bots powered by Whisper gave to audio files sent by community members (i.e. NI) 

• See posts with no time limit

  •  At the type of typing there are 190+ posts ready to read

Subscribe to AI-as-a-Service (AIaaS): 

• I. AIaaS Community Membership - $14/month/user (free for now; see above) 

  • Join via Slack here 

• II. Dedicated AIaaS in our Community - $49/month/user 

  • Buy via Stripe here 

• III. Shared AIaaS in your Community - $149/month/user 

  • Buy via Stripe here  

• IV. Dedicated AIaaS in your Community - $249/month/user 

  • Buy via Stripe here 

• Professional Services 

  • Get help from a professional service provider for your specific need 

    • Pending 

Who Created MasterVerse.AI?

Alex Chompff (AC) is the Entrepreneur and Investor who created Evolution Accelerator, MasterVerse.AI Substack,and MasterVerse.AI Slack Community. 

AC believes in serving others. Those aren’t mere words. AC is funding the services above so others may learn AI through use and observation. Learn more here.  

To collaborate with AC and others curious about AI, join the MasterVerse.AI Slack Community using the link below:

Join MasterVerse.AI Slack Community

Disclaimer 

***** The information herein is neither professional advice nor a replacement for professional advice. Please consult a professional provider as needed. MasterVerse.AI is for informational purposes only and may include fact or faction and provides no guarantee in any form. The reader assumes all risks for reading and is responsible for fact-checking anything and everything herein. ***** 

Context & Thanks

Thanks to Michael Spencer (MS) and Melanie Mitchell (MM) for starting the conversation; here’s the context:

Please note, MM posted:

“Chain of Thought” Reasoning in LLMs

In the last few years, there has been a deluge of papers making claims for reasoning abilities in LLMs (Huang & Chang give one recent survey).  One of the most influential such papers (by Wei et al. from Google Research) proposed that so-called “Chain of Thought” (CoT) prompting elicits sophisticated reasoning abilities in these models. A CoT prompt gives one or more examples of a problem and the reasoning steps needed to solve it, and then poses a new problem. The LLM will then output text that follows a similar set of reasoning steps before outputting an answer. This figure from the paper by Wei et al. gives an example:

Wei et al. tested the CoT prompting method on datasets with math word problems, commonsense reasoning problems, and other domains. In many cases, CoT prompting dramatically improved the performance of LLMs on these datasets. 

Two downsides of CoT prompting are (1) it takes some effort on the part of the human prompter to construct such prompts; and (2) often, being able to construct a CoT example to include in the prompt requires the prompter to already know how to solve the problem being given to the LLM!

A subsequent paper proposed that these problems can be avoided by leaving out the CoT example, and just posing the problem to an LLM with the added phrase “Let’s think step by step.”   Here’s an example from that paper:

Amazingly, this simple addition to a prompt—termed “zero-shot CoT prompting”— substantially improves LLM’s performance on several reasoning benchmarks as compared with prompts without the addition of “Let’s think step by step.”

Why does CoT prompting—whether with an example or with “Let’s think step by step”—have this dramatic effect on LLMs?   Interestingly, while there are many hypotheses, this question has not been definitively answered. 

A key quote from MM:

Please note the power of prompts as it relates to AI. Seemingly simple changes in the input (i.e., “conversation”) with AI changes everything.

The power of prompts may be one of the single biggest lessons to learn as it relates to AI, especially if the goal is to monetize AI-as-a-Service (AIaaS).

Learning how to prompt (i.e. chat, converse, talk, etc.) AI isn’t as easy as it may initially seem, like other languages, it takes time and patience to learn.

The Opportunity

Let’s learn together through observation and use how humans (i.e. Natural Intelligence (NI)) are prompting (i.e. conversing) with AI bots powered by GPT-4.

Please join us in the MasterVerse.AI Slack Community using the button below:

Join the MasterVerse.AI Community

Why Join the MasterVerse.AI Slack Community?

1. AI is here. AI is like the internet, it’s not if but when and where we’ll encounter it; it’s also about NI (i.e. definition here) controlling AI vs. AI controlling NI

   1. If we’ve used Amazon’s Alexa, Apple’s Siri, or even auto-correct when texting or typing, say hello to AI, because we’re using it

2. Since AI is here and we, and even our parents or grandparents, are using AI, wouldn’t it be wise to start to understand it better?

   1. AI is all about the power of prompts (i.e. learn more AI vocabulary here); AI prompts are essentially a language in itself

   2. Why not learn about conversing and controlling AI through prompts via the power-packed duo of observation and use?

Alex Chompff (AC) the creator of MasterVerse.AI believes in learning by observation and use so much that AC is giving un-throttled access to GPT-4 for free for now.

Please note, GPT-4 is neither free nor un-throttled if accessed directly (see here and here). To be answered by AI bots powered by GPT-4 costs money.

In addition to the cost of each answer by AI bots powered by GPT-4, there’s also the time, money, and energy costs of hosting and maintaining the services.

AC is funding MasterVerse.AI based on a mission to serve others. You may benefit from this by joining the MasterVerse.AI Slack Community.

If Slack isn’t your preferred platform, you may also learn about the power of AI prompts by subscribing to the MasterVerse.AI Substack via the button below.

Subscribe now

Why Subscribe to MasterVerse.AI Substack?

Both free and paid MasterVerse.AI subscriptions offer:

1. You see the questions others are asking AI bots powered by GPT-4

   1. This gives valuable insight; other platforms may give access to GPT-4, but users usually only see their own questions, not others

2. You see the answers AI bots powered by GPT-4 give in reply

   1. Yet again more valuable insight, as you see what others see, and what others are paying for; who’s paying? Currently, MasterVerse.AI.

The free subscription lets you read posts within the past month.

The paid subscription lets you read posts without a time-limit. At the time of typing MasterVerse.AI Substack already has a library of 187 published posts ready to read.

The mission of MasterVerse.AI Substack is to help you the reader with:

1. Monetizing AI (AIaaS)

2. Sharing AI Q&A powered by GPT-4

   1. Learn about the power of prompts by observing others prompts post after post

3. Watching AI News

4. Merging Natural Intelligence (NI) + Artificial Intelligence (AI)

   1. i.e. Humans and Machines living and working together

Conclusion

AI is here. It’s really only a question of how much we realize and accept it. Accepting reality is where adapting begins. Let’s learn and master AI together.

Alex Chompff is generously funding two opportunities to adapt to AI by learning how to powerfully and successfully prompt AI:

Option 1: MasterVerse.AI Substack is a looking glass into NI (i.e. definition here) with AI Bots powered by GPT-4 within the MasterVerse.AI Slack Community.

Subscribe now

Option 2: MasterVerse.AI Slack Community is a diverse group of NI (i.e., humans) working with a diverse group of Artificial Intelligence (AI) bots powered by GPT-4.

Join MasterVerse.AI's Slack Community

Thanks again to MS, MM, AC, and the readers of this post. Let’s continue the conversation in the MasterVerse.AI Slack Community.