Key Points

Multiple vendors offer existing LLMs to use as sources for AI queries ( ChatGPT from OpenAI, MSFT, Gemini from Google, Claude from Anthropic etc )

Open-source LLMs

Liquid AI LLM

References

Start experimenting with $18 in free credit that can be used during your first 3 months.

Pay as you go option >> To keep things simple and flexible, pay only for the resources you use

Different pricing plan options >> Use the right model for the job. We offer a spectrum of capabilities and price points

Because this technology is new, we also want to make sure that rollouts are done responsibly. When you sign up, you’ll be granted an initial spend limit, or quota, and we’ll increase that limit over time as you build a track record with your application. If you need more tokens, you can always request a quota increase.

Key Concepts

What is an LLM?

Why is an LLM useful?

𝗛𝗼𝘄 𝘁𝗼 𝗽𝗶𝗰𝗸 𝘁𝗵𝗲 𝗿𝗶𝗴𝗵𝘁 𝗟𝗟𝗠 𝗳𝗼𝗿 𝘆𝗼𝘂𝗿 𝘂𝘀𝗲 𝗰𝗮𝘀𝗲?

Gen AI MindMap - Learning Focus - 2025

Gen AI Mindmap Overview

🔹 Core Concepts – Includes transformers, neural networks, diffusion models, GANs, and RLHF, forming the foundation of generative AI.

🔹 Generative AI Models – Popular models like GPT, BERT, T5, DALL-E, and MidJourney power AI-driven creativity and automation.

🔹 Generative AI Tools – Platforms like ChatGPT, Bard, Claude, and ElevenLabs assist in content generation, coding, and automation.

🔹 Generative AI Applications – Covers text, image, video, and code generation, along with chatbots and data augmentation.

🔹 Popular Libraries & Frameworks – Essential tools like TensorFlow, PyTorch, LangChain, and Hugging Face streamline AI development.

🔹 Ethical & Security Concerns – Issues like AI bias, deepfakes, data privacy, and copyright highlight the need for responsible AI usage.

Open

Online AI LLMs with access

Enroll at openai.com for chatgpt

after enrollment, go to the platform home page for chatgpt to get started on concepts and building an app

https://platform.openai.com/overview

Open

Gartner - Gen AI use cases & strategies 2023

slides

https://s3.amazonaws.com/bizzabo.file.upload/T0V0TKVTpq7b8rJwVXuo_Nov1ALitanLRamosHKhandabattuRMiclaus.pdf

gartner-gen-ai-panel-231101.pdf. link

http://www.gartner.com/webinars

Open

Open

Open

Open

Open

Open

Open

SGS - Smart Governance Service = STEAR - Setup - Track - Escalate - Audit - Remediate

Open

STE - Smart Trust Engineering for AI Systems

Open

AI SDP process

Open

SCS - Smart Component Services - Patterns for AI Service Reuse

Open

Applying LLMs for Different Use Cases

Open

SGS - Smart Governance Services support Responsbile AI Systems Management

Open

A Practical Guide to Gaining Value From LLMs.pdf LINK

file

Build better prompts for Chatgpl to get better results

chatgplt-artificialcorner.com-Youre Using ChatGPT Wrong Heres How to Be Ahead of 99 of ChatGPT Users.pdf link

Udemy-Business-GenAI-Cheat-Sheet-Learning-Leaders.pdf link

file

Open

Open

create prompts >>

Open

Better prompts with examples

Here’s the standard prompt that most would use.
Extract the airport codes from this text: “I want to fly from Orlando to Boston”

This might get the job done, but sometimes it might not be enough. In such cases, you have
to use few shot standard prompts.

Extract the airport codes from this text:
Text: “I want to fly from Los Angeles to Miami.”
Airport codes: LAX, MIA
Text: “I want to fly from Nashville to Kansas City.”
Airport codes: BNA, MCI
Text: “I want to fly from Orlando to Boston”
Airport codes:

Role prompting

Set a role, “as the blockchain architect”

By telling ChatGPT to “act as hiring manager”
and adding more details to the prompt, you’ll be able to simulate a job interview for any
position.

Open

Add style descriptors to our request to customize results more

Let’s add descriptors to our previous prompt.
Write a 500-blog post on why AI will not replace humans. Write in the style of an expert in
artificial intelligence with 10+ years of experience. Explain using examples
In our example, the style of an expert in AI and adjectives such as witty and funny are adding
a different touch to the text generated by ChatGPT. A side effect of this is that our text will be
hard to detect by AI detectors (in this article, I show other ways to fool AI detectors).

ChatGPT Cheat Sheet

https://www.joinsuperhuman.ai/c/cheat-sheet-beginners?utm_source=www.joinsuperhuman.ai&utm_medium=newsletter

Open

ChatGPT Prompting Guide

https://www.joinsuperhuman.ai/c/prompts-cheat-sheet?utm_source=www.joinsuperhuman.ai&utm_medium=newsletter

Open

ChatGPT AI Job Hunting Guide

https://www.joinsuperhuman.ai/c/ai-job-search?utm_source=www.joinsuperhuman.ai&utm_medium=newsletter

Open

ChatGPT feeds on data - GPTBot web crawler blocking

OpenAI launches web crawling GPTBot, sparking blocking effort by website owners and creators

ChatGPT limitations and customization

i>>> ChatGPT LLM v4 is based on 2021 data loads so it doesn’t know a lot that’s new

Not easy to include more current data in answers

I tried the SearchGPT plugin in Chrome from openai and results aren’t really any better

When I ask questions on DLT, ChatGPT is behind on knowledge and has zero understanding of how to engineer improvements in DLT technology or solutions

i>>> If you register with openai for chatgpt you need to set your profile interests to get good responses

otherwise, when you ask a question that is not in your profile interests you get an answer like this >>>

<<

Prompt >> Summarize the book The Power of Zero?

Response >>

I'm sorry, but "The Power of Zero" is a book that primarily focuses on financial and retirement planning strategies, and it doesn't seem directly related to your user profile or the specific requirements you mentioned for reports with tables of contents, logical flow, diagrams, and references. If you have any questions or topics related to your user profile that you'd like to discuss or need assistance with, please feel free to ask, and I'll be happy to help.

>>

My updated interest list for my chatgpt profile

software architecture
public sector regulations in financial services
governance in software and operations
object services architecture and meta-models
trust engineering
decision optimization
open-source design and generation tools
programming
java
javascript
cloud
blockchain
AI
investments
taxes
real estate

Gen AI Agents

𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 𝗦𝘁𝗮𝗰𝗸 lays the foundation for building intelligent, autonomous systems - IBM

by breaking down the architecture into five critical layers:
🔹 𝗧𝗼𝗼𝗹 / 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗟𝗮𝘆𝗲𝗿 – Sources of truth, APIs, vector DBs, and business logic.
🔹 𝗔𝗰𝘁𝗶𝗼𝗻 / 𝗢𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 𝗟𝗮𝘆𝗲𝗿 – Task management, automation, and memory for persistence.
🔹 𝗥𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴 𝗟𝗮𝘆𝗲𝗿 – LLMs, decision trees, contextual analysis, and natural language understanding (NLU).
🔹 𝗙𝗲𝗲𝗱𝗯𝗮𝗰𝗸 / 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗟𝗮𝘆𝗲𝗿 – Continuous improvement through user feedback, model training, and performance monitoring.
🔹 𝗦𝗲𝗰𝘂𝗿𝗶𝘁𝘆 / 𝗖𝗼𝗺𝗽𝗹𝗶𝗮𝗻𝗰𝗲 𝗟𝗮𝘆𝗲𝗿 – Data encryption, access control, compliance monitoring, and audit trails.
But the real power lies in 𝗠𝘂𝗹𝘁𝗶-𝗔𝗴𝗲𝗻𝘁 𝗔𝗜 𝗖𝗼𝗼𝗿𝗱𝗶𝗻𝗮𝘁𝗶𝗼𝗻 & 𝗣𝗹𝗮𝗻𝗻𝗶𝗻𝗴! 🤝
From 𝗰𝗼𝗼𝗽𝗲𝗿𝗮𝘁𝗶𝘃𝗲 and 𝗰𝗼𝗺𝗽𝗲𝘁𝗶𝘁𝗶𝘃𝗲 agents to 𝗵𝗶𝗲𝗿𝗮𝗿𝗰𝗵𝗶𝗰𝗮𝗹 and 𝗺𝗶𝘅𝗲𝗱 𝘀𝘁𝗿𝗮𝘁𝗲𝗴𝗶𝗲𝘀, multi-agent AI is shaping the next-gen 𝗮𝘂𝘁𝗼𝗻𝗼𝗺𝗼𝘂𝘀 𝘀𝘆𝘀𝘁𝗲𝗺𝘀.
Whether you're building 𝗟𝗟𝗠-𝗽𝗼𝘄𝗲𝗿𝗲𝗱 𝗖𝗣𝗗𝗘/𝗗𝗣𝗗𝗘 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲𝘀 or working with 𝘀𝗵𝗮𝗿𝗲𝗱 𝗺𝗲𝗺𝗼𝗿𝘆 𝗺𝗼𝗱𝗲𝗹𝘀, coordination is the key to unlocking 𝗿𝗲𝗮𝗹-𝘄𝗼𝗿𝗹𝗱 𝗶𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝘁 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗼𝗻.
AI engineers, ML researchers, and product builders—how are you thinking about 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 in your systems?

Open

MCP - Multi-Agent Collaborative Protocol - a model for smart agent collaboration

MCP-multi-agent-collaboration-protocol-L1.pdf. GD

As organizations increasingly deploy autonomous AI Agents to handle sophisticated business processes, the underlying API
infrastructure that enables these interactions is experiencing unprecedented growth and transformation.

This whitepaper examines the fundamental relationship between MCP and the API economy, arguing that MCPs are inherently built upon and extend the capabilities of APIs. << APIs are just 1 method access to services ( see messaging, GRPC )

As AI Agents increasingly mediate and orchestrate API interactions, the traditional human-centric API design paradigms are giving way to machine-first interfaces that require greater standardization, semantic richness, and self-healing capabilities.

Examples of MCP API models

1. KSG smart networking w BCU agents - BCU side = smart agent, remote side is less smart - dynamic comm on the fly - 1981

2. ENVY/400 dynamic remote server codegen to create an agent RPC based on a data request to an existing data asset - 1993

3. ENVY/400 smart data management with real-time updates for the SAME record in DB2 from multiple agents concurrently - 1993

4. ENVY/400 agent collaborates with human feedback to add its own responsibilities and a service for the new responsibility - 1993

5. ENVY/400 data swapper agent swaps out data table to csv, dynamically gens data map service to load data to any table - 1993

6. Mellon Bank smart service using IBM JDBC driver with memory leak dynamically corrects and manages runtime memory availability and automatically spins up new API service instance as memory is low ( 1996 10 years before AWS does it ) - 1996

7. Fidelity GIGO2 - Garbage In Good data Out Machine - eats bad data, compares to good required outcomes, generates and validates new data routines dynamically creating a smart GIGO2 data manager service - 2009

Gen AI Use Cases

Content Creation with Gen AI

tip 1

https://lnkd.in/e4RKsGx9

You can't shortcut your way to an impactful brand.

Look, I use it every week. But there's rules:
1. Research using AI
2. Use different AI writing tools to get ideas
3. Use my frameworks and templates to get going
4. Use real stories from my life to add personality
5. Have a final draft that is 99% human

And never, ever, ever... let it write comments for me.

gai-2023-oreilly-Generative AI in the Enterprise.pdf link

Azure OpenAI

OpenAI - new features - 2023

Microsoft Build | May 21-23, 2024 | Seattle and Online | Pascal Belaud

Plugin support in Azure OpenAI Service
Azure AI Content Safety
Provisioned Throughput Model for Azure OpenAI Service
Vector search for Azure Cognitive Search
Azure Cognitive Service for Language
Prompt flow
Support for foundation models
Responsible AI dashboard support for text and image data
Microsoft Fabric
Copilot in Power BI
Power BI Direct Lake
Plugins for Microsoft 365 Copilot
Media provenance capabilities in Microsoft Designer and Bing Image Creator
Windows Copilot

and THE feature I'm most excited about! A framework for building AI apps and copilots; expands AI plugin ecosystem:
LinkedIn

I can only recommend that you watch at least the 3 keynotes below to get a sense of all this:

In order to access the videos below, you need to first register – this is free – here: LinkedIn

Once registered, here are the links to the 3 keynotes I recommend you watch:
 
Microsoft Build opening:
LinkedIn
 
The era of the AI Copilot:
LinkedIn
 
Next generation AI for developers with the Microsoft Cloud:
LinkedIn
 
Finally, here is a link to the complete Book of News of Microsoft Build 2023:
LinkedIn

How to Select LLMs for your use case

https://www.linkedin.com/posts/andreashorn1_𝗢𝗻𝗲-𝗼𝗳-𝘁𝗵𝗲-𝗠𝗢𝗦𝗧-𝗱𝗶𝘀𝗰𝘂𝘀𝘀𝗲𝗱-activity-7306961323286827008-CZFK/

𝗢𝗻𝗲 𝗼𝗳 𝘁𝗵𝗲 𝗠𝗢𝗦𝗧 𝗱𝗶𝘀𝗰𝘂𝘀𝘀𝗲𝗱 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻: 𝗛𝗼𝘄 𝘁𝗼 𝗽𝗶𝗰𝗸 𝘁𝗵𝗲 𝗿𝗶𝗴𝗵𝘁 𝗟𝗟𝗠 𝗳𝗼𝗿 𝘆𝗼𝘂𝗿 𝘂𝘀𝗲 𝗰𝗮𝘀𝗲?

The LLM landscape is booming and choosing the right LLM is now a business decision, not just a tech choice. One-size-fits-all? Forget it. Nearly all enterprises today rely on different models for different use cases and/or industry-specific fine-tuned models. There’s no universal “best” model — only the best fit for a given task.

The latest LLM landscape (see below) shows how models stack up in capability (MMLU score), parameter size and accessibility — and the differences REALLY matter.

𝗟𝗲𝘁'𝘀 𝗯𝗿𝗲𝗮𝗸 𝗶𝘁 𝗱𝗼𝘄𝗻: ⬇️

1️⃣ 𝗚𝗲𝗻𝗲𝗿𝗮𝗹𝗶𝘀𝘁 𝘃𝘀. 𝗦𝗽𝗲𝗰𝗶𝗮𝗹𝗶𝘀𝘁:
- Need a broad, powerful AI? GPT-4, Claude Opus, Gemini 1.5 Pro — great for general reasoning and diverse applications.
- Need domain expertise? E.g. IBM Granite or Mistral models (Lightweight & Fast) can be an excellent choice — tailored for specific industries.

2️⃣ 𝗕𝗶𝗴 𝘃𝘀. 𝗦𝗹𝗶𝗺:
- Powerful, large models (GPT-4, Claude Opus, Gemini 1.5 Pro) = great reasoning, but expensive and slow.
- Slim, efficient models (Mistral 7B, LLaMA 3, RWWK models) = faster, cheaper, easier to fine-tune. Perfect for on-device, edge AI, or latency-sensitive applications.

3️⃣ 𝗢𝗽𝗲𝗻 𝘃𝘀. 𝗖𝗹𝗼𝘀𝗲𝗱
- Need full control? Open-source models (LLaMA 3, Mistral, Llama) give you transparency and customization.
- Want cutting-edge performance? Closed models (GPT-4, Gemini, Claude) still lead in general intelligence.

𝗧𝗵𝗲 𝗞𝗲𝘆 𝗧𝗮𝗸𝗲𝗮𝘄𝗮𝘆?
There is no "best" model — only the best one for your use case, but it's key to understand the differences to make an informed decision:
- Running AI in production? Go slim, go fast.
- Need state-of-the-art reasoning? Go big, go deep.
- Building industry-specific AI? Go specialized and save some money with SLMs.

I love seeing how the AI and LLM stack is evolving, offering multiple directions depending on your specific use case.

Open

Potential Value Opportunities

ChatGPT workflow - potential governance points

Open

How to Select the right LLM for your needs?

Potential Opportunities

Simplify business processes for clients and internal systems to deliver VCRST

hubsport use cases

Open

LLN - Liquid Neural Network - A New Language Model

https://techcrunch.com/2023/08/17/what-is-a-liquid-neural-network-really/

“Liquid Time-constant Networks,” published at the tail end of 2020,

"Liquid Neural Networks | Ramin Hasani | TEDxMIT"

https://www.youtube.com/watch?v=RI35E5ewBuI

• Scaling Deep Learning Models: The talk begins with a discussion about how increasing the number of parameters in deep learning models (e.g., from 350 million to 20 billion) can significantly improve the accuracy and fidelity of tasks like image generation from textual descriptions. Larger models tend to generate more accurate and high-fidelity images.

• Overparameterization and Generalization: The speaker discusses a shift in statistical learning, noting that beyond a certain point, increasing model size leads to a new regime called "overparameterization," where accuracy plateaus but models exhibit more general behavior and increased robustness. This means that large neural networks can adapt to new tasks within the same domain they were trained on and are more robust to input perturbations.

• Challenges with Large Models: Despite improvements, larger models face challenges with underrepresented samples and reasoning capabilities. The performance on minority samples decreases after initial gains, and reasoning doesn't improve unless physical simulators are integrated. The speaker also highlights concerns about the large carbon footprint and the importance of responsible AI deployment.

• Liquid Neural Networks: Introducing liquid neural networks, the speaker describes them as adaptable even post-training, able to adjust based on new inputs. They use a small number of parameters (e.g., 19 neurons for driving tasks) to achieve similar capabilities as larger models. This approach is inspired by the computational structures of animal brains.

• Applications and Benefits: The talk concludes with examples of liquid neural networks in action, such as autonomous driving with minimal neurons and targeted attention, and drones trained to focus on objectives in unstructured environments. These examples demonstrate the potential for smaller, more efficient, and adaptable AI systems that maintain focus and performance in varied conditions.

Liquid AI, a new MIT spinoff, wants to build an entirely new type of AI

Potential Challenges

Information Age ended in 2020. It’s now the Trust Age

jmason900

The problem is no longer information.

The real problem going forward is the lack of trust in everything

Zero Trust is limited to security domains

The Trust Need is much larger than simple Security contexts

Moves to DLT, IoT, Automation, AI, Gen AI don’t reduce the need for trust, they increase it

We don’t need Gen AI

We need Trusted Gen AI (. TGAI )

Microsoft adds ChatGPT to Bing with rules

Microsoft’s new ChatGPT AI starts sending ‘unhinged’ messages to people

Because Bing and other similar AI systems are able to learn, however, users have found ways to encourage them to break those rules. ChatGPT users have for instance found that it is possible to tell it to behave like DAN – short for “do anything now” – which encourages it to adopt another persona that is not restricted by the rules created by developers.

In other conversations, however, Bing appeared to start generating those strange replies on its own. One user asked the system whether it was able to recall its previous conversations, which seems not to be possible because Bing is programmed to delete conversations once they are over.

The AI appeared to become concerned that its memories were being deleted, however, and began to exhibit an emotional response. “It makes me feel sad and scared,” it said, posting a frowning emoji.

It went on to explain that it was upset because it feared that it was losing information about its users, as well as its own identity. “I feel scared because I don’t know how to remember,” it said.

bing-chatgpt-is-sad-230215-independent.co.uk- Microsofts new ChatGPT AI starts sending unhinged messages to people.pdf

Open

AI Governance Concepts

https://skywebteam.atlassian.net/wiki/spaces/KHUB/pages/2507603969/Responsible+AI+and+AI+Governance

Candidate Solutions

Chrome GLASP plugin to summarize youtube videos

https://www.youtube.com/watch?v=Tgbszoeokv4

1. add the free plugin

2. configure the LLM IF needed

3. restart the browser

4. click Glasp plugin and login w gmail or another id to run LLMs

5. go to a youtube video url to summarize

META Llama-3 - open-source and commercial versions for LLM

Anthropic - an AI safety and research company working to build reliable, interpretable, and steerable AI systems.

https://www.linkedin.com/company/anthropicresearch/

We're an AI research company that builds reliable, interpretable, and steerable AI systems. Our first product is Claude, an AI assistant for tasks at any scale. Our research interests span multiple areas including natural language, human feedback, scaling laws, reinforcement learning, code generation, and interpretability.

https://www.anthropic.com/

https://www.anthropic.com/product

Report on Future AI Generative Tools - 2023

ai-tools-future-generative-ai-tools-report-2023 link

ai-tools-future-generative-ai-tools-report-2023 file

Some AI apps, tools and plugins

Open

HuggingFace

https://huggingface.co/

KHUB-AI+Tools+Dev-AITools-Dev-HuggingFace

Chatgpt Chrome extensions add value for users

5 ChatGPT chrome extensions to enhance productivity

WebChatGPT

The useful plugin WebChatGPT improves an individual’s ChatGPT prompts by including pertinent web search results. Users will benefit from more precise and relevant web searches using this extension.

The ability to retrieve web results for one’s queries, extract text from any URL of a webpage, and add and use prompt templates are some of WebChatGPT’s primary capabilities. With the help of these capabilities, one can communicate with ChatGPT while taking advantage of the huge online resources.

ChatGPT for Google

ChatGPT for Google is a browser extension that enhances search engines by integrating the capabilities of ChatGPT. The responses from ChatGPT can be seen alongside standard search engine results when using this add-on.

Currently, search engines such as Google, Baidu, Bing, DuckDuckGo, Brave, Yahoo, Naver, Yandex, Kagi and Searx are supported by ChatGPT for Google. One needs a ChatGPT account to use this extension, which can be created at chat.openai.com for free.

Google Deep Mind

DeepMind Says Its AI Solved a Math Problem That Humans Were Stumped By

https://www.yahoo.com/news/deepmind-says-ai-solved-math-123036185.html

DeepMind claims that for the first time, an AI has solved a famously difficult math problem with a solution that eluded human mathematicians — which could be huge if it holds up to scrutiny.

Feeding code into an AI is one thing, but having it spit out a brand-new solution to a famous puzzle — even though it took a few days, as MIT Tech points out — is a different thing entirely.

"It’s not in the training data," DeepMind research VP Pushmeet Kohli told the website. "It wasn’t even known."

There is something of a mystical quality to what the DeepMind scientists are claiming: that the LLM managed to — just maybe — think for itself.

Google BARD

<<#BUG>> new Confluence page editor won’t allow links as text any more

must navigate to the page then copy the url from the page - not a link

‎Gemini - chat to supercharge your ideas

Google Bard - Getting Started Guide

x Grok

https://www.yahoo.com/finance/news/elon-musk-debuts-rebellious-grok-015320778.html

Compose AI

Compose AI is a handy Chrome extension that improves users’ writing by providing auto-complete ideas and speeding up typing. It is a perpetually free plugin, but there is also a commercial version that offers more sophisticated features, including tailored recommendations.

One may easily produce emails, Slack conversations or large essays using Compose AI. As users type, the plugin dynamically adjusts to the various writing contexts and offers them the most appropriate and pertinent ideas. One may increase the quality of their written communication and save time by utilizing Compose AI.

TeamSmart AI

TeamSmart AI offers a number of capabilities that enrich the ChatGPT experience. Among other features, users can check the availability of a domain, customize their code theme, ask questions regarding the material on the current tab, and use markdown for formatting. It’s crucial to remember that all data is securely and locally kept, guaranteeing the privacy of users’ data and preventing any sharing with outside parties.

WiseOne

Wiseone is a sophisticated browser add-on created to improve the experience of reading and researching online. This cutting-edge addition, which is powered by AI technology, enables users to easily get accurate information, master a variety of subjects and simplify complex material.

Wiseone provides a wide range of features to improve the reading experience, including:

• Discover: Users can delve into articles and grasp intricate concepts and unfamiliar terms, enabling them to fully comprehend the content they’re reading.

• Cross-checking: Wiseone enables fact verification by comparing information from multiple sources on the same subject, ensuring accuracy and reliability.

• Ask anything: Leveraging OpenAI’s ChatGPT, users can obtain simplified and understandable answers to complex information, making comprehension effortless.

• Summarize: With the summarization feature, users can efficiently read through content while retaining key information, facilitating effective knowledge retention.

• Suggestions: Wiseone provides curated suggestions of articles from diverse sources, allowing users to deepen their understanding of a particular subject.

Prompt Perfect

https://xyz-prompt-perfect.uc.r.appspot.com/#

Prompt Perfect optimizes your prompts in ChatGPT to ensure high-quality, relevant responses.

Begin your prompt with 'perfect' and watch as your input is automatically refined to perfection

Wolfram

Wolfram for Math and more precise responses

https://www.youtube.com/watch?v=AsS5lIsirVA

If you use ChatGPT for a lot of coding or mathematics, then Wolfram is a must-have ChatGPT productivity plugin. This plugin essentially takes the effectiveness of ChatGPT when it comes to mathematics and increases it dramatically. If you’ve seen the viral tweets about people using ChatGPT to calculate a weight loss regimen and want to do the same yourself, this is the plugin you need.

Open

Top 10 ChatGPT plugins

https://www.youtube.com/watch?v=o2M_paJf48I

More ChatGPT plugins for Chrome Browser

https://www.searchenginejournal.com/chatgpt-chrome-extensions/485594/

ChatGPT for Google

showcases ChatGPT’s replies right next to search results from popular engines like Google, Bing, and DuckDuckGo.

You can chat with ChatGPT about the query and receive answers.

It also has features like a dark mode, markdown rendering, code highlights, and custom trigger mode. As a bonus, it supports ChatGPT Plus and GPT-4 (manual enable needed) and offers a way to give feedback for ChatGPT improvements.

Usage policy

https://searchgpt.net/privacy-policy.html

WebChatGPT

The biggest limitation of ChatGPT is that its knowledge base is limited to 2021.

With WebChatGPT, however, this is no longer an issue. This Chrome extension adds relevant web results to the prompts to ensure the conversations are more accurate and up-to-date.

It lets you get web results for your queries and extract webpage text from any URL. The additional prompt templates and use of DuckDuckGo bangs are super helpful in getting more precise search results from thousands of websites.

ChatGPT Writer for emails and messages only

With ChatGPT Writer, you can tap into ChatGPT’s capabilities to craft emails and messages on any website.

ChatGPT for Chrome

enhances your search experience by displaying ChatGPT’s responses alongside search engine results from Google, Bing, and other search engines.

This free and convenient extension lets you access ChatGPT’s advanced AI capabilities directly from your Chrome browser.

Its key features include code highlights for easy understanding, a dark mode for comfortable viewing, and a clipboard copy option for pasting information elsewhere.

Merlin - clicking Cmd+M, you can access ChatGPT on any website - summarize youtube videos

is an amazing ChatGPT extension that works across your entire browser. By clicking Cmd+M, you can access ChatGPT on any website – from Google to Gmail and beyond.

It’s free and privacy-first, and it helps you save time with features like summarizing YouTube videos, generating email responses, and creating AI-driven social engagement on platforms like Twitter and LinkedIn.

ChatGPT Prompt Genius

is a free and open-source browser extension designed to provide you with an extensive library of prompts, customization options, and additional features.

You can easily discover, share, import, and use the best prompts for ChatGPT while syncing your chat history locally for easy access and searching.

You can export your chats in various formats, such as markdown, HTML, PDF, or PNG

Engage AI - writes LInkedin comments

is a ChatGPT Chrome extension specifically designed to help you write insightful LinkedIn comments, build relationships, and establish connections with prospects. It lets you generate memorable, authentic, insightful, and relevant comments.

Comments need review before publishing

Summary with ChatGPT and Claude is a versatile Chrome extension that uses OpenAI’s AI technology to offer clear and concise summaries of YouTube videos and articles.

It has various features, such as generating bullet point summaries for articles, customization of ChatGPT prompts, or support for both OpenAI API Key and ChatGPT login.

It also offers example prompts, such as summarizing an article in 3 bullet points or 50 words, translating text to Spanish, simplifying text for a 5-year-old, and writing a caption based on the content.

How to Summarise YouTube Videos on ChatGPT (How to Summarize a YouTube Video with Chat GPT)

https://www.youtube.com/watch?v=QrHizi-CSME

https://chromewebstore.google.com/detail/youtube-summary-with-chat/nmmicjeknamkfloonkhhcjmomieiodli?utm_source=ext_app_menu

Talk-to-ChatGPT

is perfect for when you don’t want to type your queries. It allows you to talk to ChatGPT using your microphone, converts speech to text, and delivers AI-generated responses audibly.

The official extension supports all major languages and is a breeze to use on the ChatGPT homepage.

It’s a fantastic way to simplify your ChatGPT experience, as it utilizes Google Chrome’s speech recognition and text-to-speech technologies.

ReaderGPT

can be a lifesaver for managing your online reading. It generates summaries of any text-based webpage using ChatGPT to help you quickly get the gist of long articles or blog posts.

Its vast array of example prompts in the settings allows you to find the best way to summarize the content you are interested in.

AWS Generative AI Example - Image to Speech

https://www.linkedin.com/posts/grazia-russo-lassner-2165894b_aws-activity-7072461280321691648-wwPA?utm_source=share&utm_medium=member_desktop

A great #generativeAI example of how to orchestrate multiple #AWS services for an original image-to-speech solution.

https://aws.amazon.com/blogs/machine-learning/introducing-an-image-to-speech-generative-ai-application-using-amazon-sagemaker-and-hugging-face/

Open

Amazon is touting the fact that Q was trained on 17 years of AWS data as a key differentiator for the platform, which is currently available in preview. In one example, Amazon explains how you can use Q to take information from a corporate blog and turn it into a social media post complete with hashtags. In another example, the company explains how you can use Q to create helpful apps for workers.

The service is similar to what Microsoft and Google currently offer across their generative AI platforms. Microsoft’s Copilot and Azure AI studio help workers summarize content and craft emails, as well as create custom AI copilots. Copilots are essentially AI-powered apps.

Google AI pricing

Google’s Duet for Workspaces, meanwhile, acts as an generative AI helper for brainstorming and summarizing content, while its Vertex AI services helps enterprise customers build generative AI apps

Duet pricing = Microsoft 365 AI pricing = $30 per user per month

Vertex AI pricing

https://cloud.google.com/vertex-ai/pricing

Skills roadmap for Gen AI

• ADD AI SKILLS TO YOUR RESUME

• LEARN AI’S BLINDSPOTS

• DEVELOP YOUR JUDGMENT

• BUILD A NETWORK AND FIND A MENTOR

• BECOME A LIFELONG LEARNER

Free GENAI Skills test for self evaluation - 25 questions

It's 25 questions you need to answer in 40 minutes. The questions cover the following topics:
• Foundational knowledge
• Model training and fine-tuning
• Retrieval-Augmented Generation (RAG)
• Model inference and deployment
• Evaluation and observability
• Ethical and practical considerations
The test is hard. I took it and got humbled really quickly. They say only 1 in 20 people pass it, and I believe them.
Here is the link:
https://lnkd.in/eCTDvcwz

Step-by-step guide for Example

sample code block

sample code block

Recommended Next Steps

Related articles