Showing posts with label AI Bot (Artificial Intelligence Chat Bot). Show all posts
Showing posts with label AI Bot (Artificial Intelligence Chat Bot). Show all posts
Thanks to John Tan for making this wonderful Dharma A.I. bot! See below for instructions.

Click here to enter the bot:


Soh Wei Yu
Instructions: To enter it, you need to have an account with Open AI and generate an Open AI api key which you can generate here,

How to use The AtR AI Chat Bot with your OpenAI API key

To use this bot, you need to have an OpenAI API key and some credit in your account. In this post, we will explain how to get an OpenAI API key and credit, and how to use them with our bot.

Step 1: Sign up for the OpenAI API

To get an OpenAI API key, you need to sign up for the OpenAI API on their official website at You will need to provide your name, email address, phone number, and a reason for using the API. After you submit your application, you will receive an email with a link to activate your account and create a password. Once you log in to your account, you will see your API key on the dashboard. You can copy and paste it somewhere safe for later use.

Step 2: Get $5 in free credit

As a new user of the OpenAI API, you will get $5 in free credit that can be used during your first 3 months. This credit can be used to make API calls to various models, such as GPT-4, GPT-3.5 Turbo, DALL·E, and Whisper. You can check your credit balance and usage on the billing page of your account. Please note that if you make multiple accounts and verify them with the same phone number, you will not receive credit. Therefore, please use only one account per phone number.

Step 3: Use your OpenAI API key with The AtR AI Chat Bot

To use your OpenAI API key with The AtR AI Chat Bot, you need to enter your API key in the input box in

By using this AtR Team's AI Bot, you are essentially paying OpenAI (not to the AtR team) a small amount of money for using the OpenAI API services. Scroll down to find out how much it costs.


Soh Wei Yu
Top contributor

The AtR Team's AI Bot by John Tan

John Tan's The AtR Team's AI Bot was trained by pdfs produced from the Dharmawheel scrapper (a separate project I posted to GitHub in this group earlier) of Acarya Malcolm Smith and Kyle Dixon on Dharmawheel forum (Acarya Malcolm on Dharmawheel: , Kyle Dixon [Krodha] on Dharmawheel:, as well as a few other documents. For the original PDFs generated from the Dharmawheel scrapper, see

Among the many options you can choose from within the Awakening to Reality AI Chat Bot, John Tan thinks Kyle's one produces best answers (perhaps due to the way the answers are written in his PDF, perhaps the level of details and length of posts among the factors, but also, of course, the very good quality and concise writings that Kyle always make). But there are many other options you can ask questions, including the AtR guide, Acarya Malcolm's writings, and some other sources and articles. John Tan has an option (only for himself/admin) where he can combine all sources, but this is not for public.

Just a note, although when you ask someone on the left column (the chatbot), and the AI bot answers you on the left column, in my experience it is the answer on the right column that is even better.
For example, I asked,

"does kyle agree that rigpa translated as pure awareness is accurate?"

The AI bot replies, "Kyle does not agree that the translation of rigpa as "pure awareness" is accurate. He believes that rigpa encompasses a broader understanding and goes beyond the concept of awareness alone. According to Kyle, rigpa refers to a state of direct perception and non-dual awareness that transcends ordinary consciousness."

Which is ok I guess, but the answer on the right column is even clearer:

"No, Kyle does not agree that rigpa is accurately translated as pure awareness. In his posts, Kyle explains that awareness is vague and not the same as rigpa, which is more accurately a discerning knowledge of primordial wisdom. He explains that the difference between awareness and rigpa is as vast as the distance between sky and earth. Furthermore, he quotes Tulku Urgyen Rinpoche who says that the difference between awareness and the definitive rigpa is as vast as the distance between sky and earth."

Do note that both left and right columns do not show Kyle's original message. It only paraphrases or provides answers that are based on Kyle's original posts.

And there is a red button where you can see Kyle's original posts, called Raw data doc.

In another example, I asked the AI bot,

"what is anatman realization called in dzogchen and what does it do in terms of seer seen, subject and object, and how it relates to recognition of rigpa in appearances etc"

The bot replied me on the left column,

"In Dzogchen, the realization of anatman is referred to as "rangtong" or "empty essence." It is a fundamental aspect of understanding the nature of reality and the self. When one realizes anatman in Dzogchen, it brings about a profound shift in how the seer and the seen are perceived. In terms of the subject and object, the realization of anatman helps dissolve the dualistic perception of self and other. It reveals that there is no inherent, independent self or ego, and everything is interconnected and interdependent. This understanding allows for a more direct and non-conceptual experience of reality. Regarding how it relates to the recognition of rigpa in appearances, the realization of anatman helps to remove the veils of ignorance that obscure the true nature of reality. Rigpa, which is the primordial awareness or pure consciousness, can be recognized when the delusions of a separate self and inherent existence are seen through. The recognition of rigpa in appearances is the direct experience of the unobstructed, luminous nature of phenomena, free from conceptual elaboration. It's important to note that Dzogchen teachings can be complex and multifaceted, and different teachers may have slightly different interpretations. Therefore, it's always beneficial to study under the guidance of a qualified teacher to deepen one's understanding of these profound teachings."

Which again, sounds ok to me (with a bit of errors tho - for instance, nobody really calls it 'rangtong' in Dzogchen), but the answer on the right is I think, closer to what Kyle would express:

"In Dzogchen, anatman realization is called vidyā or rigpa, and it is the direct recognition of the empty nature of the subject-object split. This realization results in the recognition of the seer and seen as inseparable, and the subjective and objective phenomena as ultimately empty. This realization gives rise to the recognition of appearances as being the display of primordial wisdom, or appearance as self-display. This recognition of appearances as self-display is seen as vidyā or the discerning knowledge that results from the understanding of the non-existence of the apprehended and apprehender. This recognition is seen as the gateway to resting in the natural state, and to the discovery of the primordial ground ineffable by words and ideas."

Good stuff. I'm very glad John Tan made this bot.

Of course, to be fully representative of Kyle's posts, always check what he originally said by clicking on Raw data doc. Because what you see on that page by the bot is a paraphrasing or summary of what Kyle (or other authors) said, which may not 100% accurately reflect what the original authors said. Also, you can click Download File to save a copy.
p.s. There is a small cost involved by using the AI chat bot:
How to Calculate Costs of Usage

1. Navigate to the OpenAI Pricing page at [this link](

2. Note the price per token for the "text-davinci-003" model which is $0.1200 per 1,000 tokens, or $0.00012 per token.

3. Estimate the number of tokens your interaction (both the prompt you send and the response you receive) will use. In English, one token can be as short as one character or as long as one word. A general rule of thumb is that 75 words approximately equals 100 tokens, and 1 token approximately equals 4 characters of text. You can use [this token calculator]( to help you estimate the token count.

Here's how to estimate your cost:

- If your prompt and response together are estimated to be around 100 tokens, the cost will be 100 tokens * $0.00012 per token = $0.012.
- If your prompt and response together are estimated to be around 500 tokens, the cost will be 500 tokens * $0.00012 per token = $0.06.
- If your prompt and response together are estimated to be around 1000 tokens, the cost will be 1000 tokens * $0.00012 per token = $0.12.


*What is an OpenAI token?*
A token is the unit of account of OpenAI. It's roughly equivalent to 4 bytes, which is about 4 characters in English text. The number of tokens in your prompt determines the cost of each API call.

*What is an OpenAI execution?*
An execution refers to a single interaction with the API, including both the prompt you send to OpenAI and the response it generates. Both the prompt and the response count towards the total number of tokens, which determines the cost of the execution.

*What is an OpenAI prompt?*
The prompt is the question or instruction you send to OpenAI. For example, if you ask OpenAI "Write a tagline for an ice cream shop", that sentence is the prompt.

*What is an OpenAI response?*
The response is the text that OpenAI generates based on your prompt. For example, a response might be “We serve up smiles with every scoop!”

*Can I set an OpenAI billing limit?*
Yes, you can set a billing limit in the OpenAI billing settings. This can help you control your costs and prevent unexpected charges.

*How to monitor my OpenAI API usage and cost?*
You can review your usage and monitor your costs in the OpenAI dashboard, under the section [Account Usage]( This can help you keep track of your spending and ensure you're staying within your budget.

Remember, these costs are estimates and actual usage may vary. Also, keep your API key safe and don't share it with others.

  • Click here to enter the bot:
    • Reply
    • 1h
    • Edited

  • Soh Wei YuAuthor
    John Tan said earlier yesterday, "Actually I m very satisfied with my this program. It has most of what I want. As admin I have some options. Lol"
    "I found Kyle's answers most readable and understandable. Structured and explanations r good, the openai can generate meaningful answers from it. 👍"
    "I have also included the raw documents that r extracted for the openai to summarized. Users can download the file also. When read with the answers provided by the AI bot, it will refine one's understanding."
    "Try it on ur handphone also. Made it mobile responsive. But per question can take about 30s to answer.🤣"
    "Seems to be quite fine even when outside using 4G and on small screen phone. 👍"