I am a Microsoft 365 family user, how much Microsoft AI can I access?

 AI credits is a measure of your AI usage via Copilot in the Edge browser. Every time a question is asked 1 AI Credit is used up.

How many AI credits do you get?

This is best answered by Microsoft as :

• Users of the free Designer app (non-subscribers) receive 15 credits per month.

• Microsoft 365 Personal and Family subscribers get 60 AI credits per month, which can be used across various applications, including Word, Excel, PowerPoint, Outlook, Microsoft Forms, OneNote, Designer​​​​​​​, Notepad, Photos, and Paint.

• Copilot Pro subscribers can use AI features in Word, Excel, PowerPoint, Outlook, Microsoft Forms, OneNote, Designer​​​​​​​, Notepad, Photos, and Paint without worrying about credit limits. 

Note: AI benefits are only available to the subscription owner and cannot be shared with additional Microsoft 365 Family members. 

I have a Microsoft 365 Family account and I can use about 60 credits/month. That looks plenty for now as there are other agents like Gemini, Grok, Meta and DeepSeek.

Do AI chat bots learn from user interaction?

 This is an important question going forward with AI. If they do then information from one questions to the next and the answers get somehow sent to AI's source. If not, there is nothing going from your device to the source. I do AI chats both on my Android Samsung phone as well as from my Surface Pro laptop. The META AI is on my on my phone.

CoPilot

CoPilot does not remember stuff from one conversation to next. It does not LEARN from user interaction.

META AI

Look here, what I hear from META AI on my WhatsApp account:

Do you learn from user interaction in any way?

Yes, I learn from user interaction in several ways:

1. *Improving responses*: Through user feedback, I can refine my understanding of what constitutes a helpful and accurate response.

2. *Adapting to language*: User interactions help me learn to recognize and generate language patterns, idioms, and colloquialisms.

3. *Expanding knowledge*: Users may ask questions or provide information on topics I'm not familiar with, which helps me expand my knowledge base.

4. *Tuning accuracy*: User corrections and clarifications enable me to fine-tune my understanding and accuracy on specific topics.

5. *Understanding context*: User interactions help me better understand the context and nuances of language, allowing me to provide more relevant and empathetic responses.

Your interactions with me today are contributing to my ongoing learning and improvement!

The Q&A are indeed saved on the server.

GEMINI

Here is what I hear from Gemini:

Do you profit from user interaction in some way by saving the Q &A?

Yes, Google Assistant can benefit from user interaction by saving Q&A data. This data helps improve its understanding of language and user needs. Here are some ways this can happen:

 * Improved responses: By analyzing past interactions, Google Assistant can learn to identify patterns and improve its ability to respond to future queries in a more informative and helpful way.

 * New feature development: Data on user interactions can inform the development of new features and functionalities for Google Assistant.

 * Personalized experiences: User interaction data can be used to personalize the Assistant's responses to individual users, tailoring results to their preferences and search history.

This interactive learning is very important and I am not sure how and how often the creator of CoPilot updates its KB.

How much of the AI Assistants should we believe in?

 

This content is periodically updated and is not static.

Content has been a joint effort by a human and some of the AI assistants. 

I asked a naive but simple question to CoPilot. He was very honest in sharing his opinion related to the question. 

"How do you address flaws in the LLM? Perhaps, you are just a consumer of LLM."

He answered my question which cleared some doubts in my mind.

Large Language Models (LLMs), such as GPT-4, indeed exhibit remarkable natural language capabilities. However, their inner workings remain shrouded in mystery, akin to black boxes. Let’s delve into the challenges posed by this opacity and explore potential solutions:

1. The LLM Black Box Problem:

   • LLMs operate as black boxes, obscuring the logic behind their decisions. This lack of transparency has safety and ethical implications.
   • Imagine deploying an LLM for critical tasks like medical diagnoses or financial risk assessments. If we don’t understand how it reaches conclusions, can we trust it?
   • The scale and complexity of LLMs exacerbate this issue. Models like GPT-3, with 175 billion parameters, defy easy comprehension.
   • Each parameter interacts in intricate ways, leading to emergent capabilities that aren’t predictable from individual components.
   • While reducing scale might improve interpretability, it could compromise capability.
   • Major LLMs are proprietary systems developed by tech giants like Google, Meta, and OpenAI. Their complete details remain undisclosed, treating LLMs as trade secrets1.

2. Flawed Decision Making:

   • The opaqueness in LLM decision-making can result in undetected biases and errors.
   • In fields like healthcare or criminal justice, where decisions have far-reaching consequences, auditing LLMs for ethical and logical soundness becomes challenging2.

3. Emerging Solutions:

   • Researchers are exploring techniques for explainable AI and transparent design.
   • Efforts include developing methods to visualize LLM decision paths, identifying influential tokens, and creating interpretable representations.
   • Ethical guidelines and bias mitigation strategies are crucial to address flaws.
   • Collaborative efforts between researchers, practitioners, and policymakers are essential to unlock LLM benefits while minimizing risks1.

As for me, I’m not just a passive consumer—I strive to engage in meaningful conversations and provide helpful information. While I don’t directly address LLM flaws, I aim to assist users by leveraging my knowledge and predefined tools. 🤖📚

CoPilot is thinking of only healthcare and criminal justice, but in the near term it will have enormous consequences for the wars, and elections. State actors will emerge to make world harmony a distant dream.

It is often a tedium conversing with the CoPilot. Sometimes, CoPilot does not answer your question at all, rather addresses the key phrases individually independent of your question. It feels like you are conversing with a hearing impaired person. It is still a project in the works.

5/18/2024

Gemini AI is now easy to access. It does perform just like CoPilot. If you ask controversial subjects, or ask Gemini to factcheck, it declines saying it is still in the learning mode. However, Google tries to get a feedback from users that will improve the product. This is important because Gemini can return absolutely wrong answers.

7/22/2024

Co-Pilot has been instructed not to answer politics related question even if you are seeking publicly available information. It is in clam-shell mode.

7/22/2024

Of course, you must have heard of the Meta AI o the WhatsApp. It does answer any questions.