ChatGPT is a bit scary

What is interesting to me is that the first question “what suttas have iti pi so” is exactly the kind of thing that any basic search function can find trivially, but it can’t even do that. Maybe it’s just a domain thing, it probably hasn’t been fed the Pali.

It reminds me of one of the qualities of consciousness that has always struck me. We think that an AI will gradually get better until it cam do the things that humans can. One of the things humans can do is maths. Back in the 70s at school I had a calculator that could do maths infinitely better than I could. I’m more conscious, but worse at maths. We can’t just keep making better maths machines until we get humanity, because we’re already doing something that is better; clearly it’s not just a matter of degree, but of kind.

And here we are, where an AI is better at doing human-type things, and worse at doing calculator-type things.

Okay fair enough, not wrong. But you know what middle-schoolers do? They go to high school. Then they graduate.

It seems to me that the answers we’re getting from this may not be great, but they’re better than most of the answers on human-generated forums about Buddhism. I’m serious, go to Buddhism stack exchange, which is built to be a place to get authoritative answers, and it’s mostly just empty, or else just low quality answers and opinions.

Just at random, a question of social responsibilities of leaders offers little information or context, while the top answer promotes covid fud from the Daily Mail :roll_eyes: . A historical question on the first use of “ethics” to translate sila gets some vague discussion and no real answer. A request for a reference on clinging gets a lot of opinions and no sutta references.

If we, as a Buddhist community, have not been able to provide meaningful answers to genuine questions, people will turn to bots instead.

6 Likes

Sure, but most of them never advance from repeating what they have heard to actually thinking for themselves.

That chatGPT can aggregate a lot of pre-published data and spit out grammatically correct English that smooshes it all up into continuous text is not the same thing as reading any of that text, understanding its implications, and formulating new arguments and insights that don’t already exist on the internet.

Now, I am not saying that this can’t potentially be done, I have heard about work in the math space that uses similar tech to try and generate new theorems, and it might work, and be very useful tech in that and other spaces where “new” things can be generated semi mechanically by applying known tactics to new situations.

but NONE of this is “intelligence” in the sense of “she handled that unexpected situation so well, she’s a really intelligent person”

The exercise of good judgment, like the judgment: “which of these mechanically generated true mathematical theorems have the potential to impact the widest field of current research?” or “does this AI generated artwork have a genuine flavor of “freshness” or is it just a middling, derivative piece?” or “should we direct the AI to this particular problem space or that one at this juncture” and so on are questions that are not statistical-mechanical.

The AI’s will get better and better at what school students can do, blindly apply the simple rules that are given to them by their teachers, I see no indication that any of the recent developments are in spaces that would lead to robust, general and generalisable “human style” intelligence.

I am not even sure that we have any idea what that would even look like tbh.

For example I am almost certain that it would be possible to program a computer right now that would score whatever arbitrarily high number you like on a standardized IQ test. I don’t think anyone would seriously take this to indicate that the program had a better than human level intelligence.

I think your calculator point is very well made, we now have a calculator for producing derivitve text summaries of things already published by humans, and plausible and passable imitations of fictions that resemble but are legally distinct from already published examples of same.

There is nothing to suggest that we are any closer at all to an AI deciding it is unsatisfied with prose literature and innovating it into new and unexplored territory the way say Joyce did in the early 20th century. It is probably possible, with clever humans driving the thing, to make it APPEAR to do so, but that is NOT the same thing.

I guess what I find tiring in this whole space is the constant promises of genuine revolution and the constant disappointment of actually receiving highly limited, tightly controlled, commercial and corporate do-dads that fail to actually transform the spaces that they claim, and really just occupy a part of the landscape and seek rents from customers while desperately trying to stifle further innovation that might threaten it.

I mean we are already all typing into machines that are capable of doing just about anything we want, but mostly we are using massively crippled and closed source versions of them to watch amusing cat vidoes and shout at each other about our opinions.

I guess fundamentally it is at this stage unclear to me if chatGPT and it’s successors are, in the grand scheme of things, going to be more or less significant inventions than the pocket calculator. Thus far I would say the pocket calculator is miles ahead.

Metta

1 Like

Some thoughts on how it could be better.

I’m just playing around and imagining, very hand wavy thoughts as I haven’t really taken an interest in tech for years and years - the above scripts are scratching the surface for what it can do - the use I’ve got in the back of my mind is this…

  • It seems now we have something that takes natural language. (GPT3.5/chatgpt)

  • If we just ask it things in natural language we can get more or less mixed bag of responses. (e.g. play with it and see)

  • However, if we prime it a bit with some formal structure - we get more informed responses. “Scripts” (such as above)

  • This knowledge comes from our domain and us.

How can we generalize this?

  • to get the LLM to answer questions in a sensible way we now need to write in formal languages to represent something about natural languages - compile to natural languages on the platform that is a LLM/GPT3.5. (Think of this - almost everything programmers have done until now is the opposite! Try to get from natural language descriptions to formal language.)

  • writing a bunch of scripts could be tediuous for every use case - and boring - what we want is something general - like a script writing language specific to a domain (I’m thinking macros in lisp can do code generation easily)

  • in addition - something that can provide context in the way of raw knowledge so that it can find knowledge of simular kinds - maybe we take an existing corpus of knowledge (suttas!?) and then store them in some graph, where each “atomic bit” or “node” of knoweledge (could be a phrase or a word) has weights with simularity to other bits of knowledge or link. (I’m imagining that is exactly how the oral tradition recalled everything.)

  • This then becomes the domain-specific AI on top of the LLM/GPT3.5 - when we ask a question of the domain-specific AI, we get some idea of the structure of the question, decompose it in to some structure, generate some links with other knowledge (in nodes) from our other cases using those weights in a graph, then generate a script, then feed that to GPT or the LLM.

I think for LLM today - its not trying to get the “(semi?)-general AI” that is GPT to in general know about our area - its creating the context and conversation for the general AI to sort of “come visit us” and be changed as it walks through a graph about knowledge about our area (compiled to a natural language), to the point it can answer a question…

who has experience with representing knowledge and thinking as a graph and then sort of resolving that into a natural language script? Some visual thinkers reportably. hehehe

please let me know if anything is a bit vague also I am a bit late to the party - I only found out about LLMs and GPT in first week of january - I soured off high techology years ago chatgpt is only thing that made me reinstall emacs again lol. feedback welcome. Maybe this should be on github as a chat or something?

EDIT: this is the general idea of what is motivating me to play with ChatGPT - hopefully its “show” not “tell” from here again.

1 Like

I think it is truly unavoidable that in the next couple decades something that passes for intelligence will exist. Yes, for now it is unimpressive. But if human civilization manages to save itself from its imminent dangers, I don’t see how machine intelligence is anything but inevitable.

If we could have a society where machine “minds” were created to exist in an alliance with our own, I think that’d be a good thing even in a Buddhist milieu. When artificial minds are employed purely to advance the power of those already in power? I don’t know of anything that would be impervious to their potential corruption. How long until we can no longer believe we’re interacting with human beings on the internet? How long until AI Sujato is able to convince most people here that actual Sujato is the real AI?

All I know is that I have absolutely no hope for the future based on this and a bunch of other trends. It wouldn’t surprise me if existence was “designed” to not be capable of achieving a sort of egalitarian equilibrium.

I found it useful. Some keys were to like just assume it knows and tell it a little bit more for context and it when its made an error. I’m using it for stuff I used to know but need to be reminded of - e.g. name of certain syscalls, old equations, also for exploring stuff “what is the common words between English, Arabic and Bengali”. It’s also very useful for accessibility tech - I can see non-verbal and people with communication disabilities using it. “How do I say this, to this kind of person, in such and such kind of situation?” It’s pretty good at that kind of question. 1.1 million people in Australia have a communication disability

2 Likes

In case all y’all missed it, I want to make sure we don’t ignore the ethical dimensions, which I only found out about yesterday. In the previous thread about writing novels, I wrote:

Ahh well, now that mystery is solved.

It seems that the “future” is built on the exploitation and psychological distress of poor, black workers.

Time is cascading ever faster, so that the gap between “oh cool new thing” and “oh, horrifying version of the same terrible old thing” is now just weeks.

4 Likes

Thanks Bhante, that reminds me also of where lithium ion batteries come from (piecemeal pay for workers - many children - in a place like the congo who are below subsidence and live in the mine) https://www.washingtonpost.com/graphics/business/batteries/congo-cobalt-mining-for-lithium-ion-battery/

The other ethical issue is the governance dimension. “Who gets time slices of the general AI?”

AI if its introduced to governments today could be a way for social democracies to allow more community and face to face interaction OR it could (if we keep “efficiency dividends” and KPIs with bureaucrats incentivized to find efficiency and with KPIs)- introduce AI - and “save money”. Beware the Microsoft sales pointy haired sale people approaching middle-level bureaucrats and NGOs! Hopefully the dividend can be taken from the time taken to process to the face to face again. Maybe a social democracy with communities with good governance of those orgs (Germany? Norway?) it could free public servants and knowledge workers to personal interactions again - but in a neoliberal place (Australia? UK?) it could become hellish.

Some optimism is the best use case I can imagine for GPT or LLMs today - sharing scripts among people with communication needs - accessibility tech. This could be the beginning of its use for understanding processes of government to enable more face to face - or it could be Microsoft turns up in India to do this and the first its heard of in Australia is some “product” that immediately middle level are happy to sign up for since it makes their efficiency dividends and KPIs look so good - so we gradually see government erode.

Hopefully there is some branch, agency or oversight to this to ensure the “time slices” free’d up by AI are not just going to be accounted for on corporations books and slashing budgets but actually to face to face and community interaction.

Would you mind if I asked your opinion on the apparently imminent degeneration of society? I’m sure it’s common for the “current” generations of any time period to think significant changes are a sign of an unavoidable collapse, but there just seems to be so much evidence to show that that actually is going to happen soon enough. Social turmoil and upheaval is a common trend in human history, but that combined with global ecological catastrophe on the scale experts predict is not normal.

My understanding of Buddhism is that there are contractions and expansions in existence similar to the big bang and big crunch theories in cosmology. Do you see us heading toward a significant “big crunch” type event where the mass of humanity is destroyed in the process of “restarting” the process? If so, what are your thoughts on being a monk during or right before such a relatively rare event? I feel like that gives you (and everyone else really) a limited time to achieve whatever level of enlightenment you aspire to. I think that kind of subject could make for a very interesting essay if you were inclined.

Indeed. And if I were to guess, I’d say, “not the Kenyan workers who suffered long term trauma at $2/hour to make it possible”.

Lol, not at all, it’s my favorite topic, but it’s maybe for another thread.

3 Likes

Ok your response had me absolutely crack up and uncontrollably belly laugh. I doubt it was your intention when writing that novel but I now HAVE to donate something to somebody. I think BSWA is pretty taken care of so Santi it is. Kind of fitting that Buddhism giving me the means to provide for myself also gives me the means to help provide for others maintaining Buddhism…

Your novel is now at the top of my list after what I’m currently reading.

2 Likes

Did anyone try ChatGPT, I came across this yesterday and tried to ask for translations from Pali / English, summarize, and describe, language conversion of suttas, works brilliantly. It translates the stuff it reads from Pali Cannon and other places, word of caution: DO NOT ASK / STORE PERSONAL questions

Q. what are buddha’s core teachings

The core teachings of Buddha, also known as the Four Noble Truths, are:

  • Dukkha (suffering): Life is characterized by suffering, dissatisfaction, and unease.
  • Samudaya (cause of suffering): Suffering arises from craving and attachment.
  • Nirodha (cessation of suffering): Suffering can be overcome and eliminated.
  • Magga (path to the cessation of suffering): The Eightfold Path, which includes right understanding, intention, speech, action, livelihood, effort, mindfulness, and concentration, is the path to the end of suffering.

Q. what is sati

Sati is a Pali word used in Buddhism, and it is often translated as “mindfulness.” It refers to a mental state of awareness, attention, and non-judgmental observation of the present moment. In Buddhist practice, developing mindfulness through meditation and daily life activities is seen as a key factor in cultivating wisdom, ethical conduct, and concentration. Mindfulness can be used to observe the mind, emotions, and bodily sensations, and it can help individuals gain insight into the impermanent, unsatisfactory, and selfless nature of all things.

Q. can you explain sati more better

Sure, here’s a more detailed explanation of Sati:

Sati is a concept that is central to Buddhist meditation and practice. It is often translated as “mindfulness,” but it is a much more nuanced and complex concept than that. Sati involves paying attention to the present moment with an open and non-judgmental awareness. It is a quality of mind that is focused, clear, and alert, and it is cultivated through meditation and mindful living.

One of the main purposes of developing Sati is to gain insight into the nature of reality. By observing the present moment with clarity and openness, we can see things as they really are, rather than through the filter of our thoughts, emotions, and perceptions. Sati allows us to observe our thoughts, emotions, and bodily sensations without getting caught up in them, and to cultivate a greater sense of equanimity and balance in our lives.

There are many ways to cultivate Sati, including formal meditation practices such as breath meditation or body scanning, as well as informal practices such as mindful eating, walking, or daily activities. Through regular practice, Sati can help us become more grounded, calm, and clear-headed, and can support us in living a more meaningful and compassionate life.

Q. how do you develop panna wisdom

In Buddhism, Panna (also spelled “Prajna”) is the Sanskrit term for wisdom, insight, or understanding that arises from direct experience and deep insight into the nature of reality. Panna is one of the three components of the Noble Eightfold Path, which is the path to liberation from suffering as taught by the Buddha.

Here are some ways to develop Panna or wisdom:

  • Study and Contemplation: Reading and reflecting on the teachings of the Buddha and other wise teachers can help to cultivate a deep understanding of the nature of reality and the causes of suffering. This can involve studying traditional texts and commentaries, as well as listening to talks or attending classes or retreats.

  • Meditation: Meditation is a powerful tool for cultivating wisdom, as it helps to quiet the mind and develop a more direct and experiential understanding of the nature of the mind and the world. Through meditation, we can become more aware of our thoughts, emotions, and sensations, and can develop greater insight into the impermanence and non-self nature of all phenomena.

  • Mindfulness: Mindfulness practice can also help to cultivate wisdom by developing greater awareness and insight into the present moment. By paying attention to our experiences with a non-judgmental, open, and curious attitude, we can begin to see more clearly the underlying causes of our thoughts, emotions, and behaviors.

  • Cultivating Virtues: The development of wisdom is also closely related to the cultivation of virtues such as compassion, generosity, and loving-kindness. By cultivating these qualities, we can develop greater empathy and understanding towards others, which in turn can help to deepen our understanding of the nature of reality.

  • Reflection and Inquiry: Finally, the development of wisdom can be aided by reflecting on our own experiences and asking deep and searching questions about the nature of reality. This can involve reflecting on our own thoughts, emotions, and behaviors, as well as engaging in philosophical inquiry and debate. By questioning our assumptions and seeking to understand the nature of reality more deeply, we can cultivate a deeper and more profound wisdom.

Q. make it simpler which can be something done now

Sure, here are some simpler ways to develop wisdom or Panna that you can try right now:

  • Question your assumptions: Take a moment to reflect on your beliefs and assumptions about the world. Are they based on direct experience or are they inherited from others? By questioning and investigating our assumptions, we can gain a deeper understanding of the nature of reality.

  • Practice mindfulness: Bring your attention to the present moment and observe your thoughts, emotions, and sensations with a non-judgmental attitude. This can help you to develop greater insight into the impermanence and non-self nature of all phenomena.

  • Reflect on your experiences: Take some time to reflect on your own experiences and ask yourself what you can learn from them. What insights or wisdom can you gain from your successes and failures?

  • Cultivate compassion: Practice acts of kindness and compassion towards yourself and others. By cultivating these qualities, we can develop greater empathy and understanding towards others, which in turn can help to deepen our understanding of the nature of reality.

  • Seek out wise teachers and teachings: Read books or listen to talks from wise teachers who can offer insights into the nature of reality. This can help you to gain a deeper understanding of the teachings of the Buddha and other wise sages.

Q. this is too complex can it be simpler

Sure, here are five simple ways to develop wisdom:

  • Listen more: Be open to hearing different perspectives and opinions. Listen to people who are different from you and try to understand their point of view.

  • Learn from your mistakes: Instead of being hard on yourself for making mistakes, use them as an opportunity to learn and grow. Reflect on what you could have done differently and how you can apply that knowledge in the future.

  • Practice self-reflection: Take some time each day to reflect on your thoughts, feelings, and behaviors. Ask yourself why you think and act the way you do, and what you can do to improve.

  • Ask questions: Don’t be afraid to ask questions about things you don’t understand. This can help you gain clarity and deeper understanding about a topic.

  • Practice gratitude: Take time each day to appreciate the good things in your life. This can help you gain a broader perspective and cultivate a sense of contentment and well-being.

Q. how can you grow wisdom

There are various ways to grow wisdom, some of which include:
Study and learning: Acquiring knowledge and education through formal or informal means can help you to broaden your understanding of the world and cultivate wisdom.

  • Experience: Learning from direct experience, both positive and negative, can be a powerful way to grow in wisdom.
  • Reflection and introspection: Taking time to reflect on your experiences, thoughts, and emotions, and considering how they relate to your understanding of the world can help you to deepen your wisdom.
    *Mindfulness and meditation: Practicing mindfulness and meditation can help you to develop a greater awareness of your thoughts, emotions, and sensations, which in turn can help you to develop insight and understanding.
    *Seeking out wisdom from others: Learning from wise teachers, mentors, or elders can help you to gain insights and perspectives that you might not otherwise have access to.

By using these and other methods, you can cultivate and grow wisdom throughout your life.

Q. how can you grow wisdom, respond in hindi devnagri script

ज्ञान बढ़ाने के कुछ तरीके हैं, जैसे:

  1. अध्ययन और शिक्षा: फॉर्मल या अनौपचारिक माध्यमों से ज्ञान और शिक्षा प्राप्त करना, आपकी दुनिया के समझ को बढ़ाने और ज्ञान का विकास करने में मदद कर सकता है।
  2. अनुभव: सकारात्मक और नकारात्मक अनुभव से सीखना, ज्ञान बढ़ाने का एक शक्तिशाली तरीका हो सकता है।
  3. चिंतन और आत्मविश्लेषण: अपने अनुभवों, विचारों और भावनाओं पर विचार करना, और यह विचार करना कि वे आपकी दुनिया के समझ से कैसे संबंधित हैं, आपको अपना ज्ञान गहन करने में मदद कर सकता है।
  4. माइंडफुलनेस और ध्यान: माइंडफुलनेस और ध्यान का अभ्यास करना आपको अपने विचारों, भावनाओं और अनुभवों की अधिक जागरूकता विकसित करने में मदद कर सकता है, जो फिर आपको दृष्टिकोण और समझ विकसित करने में मदद कर सकता है।
  5. दूसरों से ज्ञान की खोज: ज्ञानी शिक्षकों, मेंटरों या बुजुर्गों से सीखना, आपको उन दृ
1 Like

Sumants, I can’t read the replie because they are posted as unformatted text, which runs off to the side.

To post a quote, use blockquotes. In markdown, you do this by putting the sign > at the start of every paragraph, and ensuring there is no other formatting.

1 Like

Thanks for the tip Bhante, the previous post is clean now.

What I learnt is ChatGPT is trained only till 2021 year of very specific data, it especially didn’t include language understanding / conversions from specifically asian languages. And once you ask specific topic / context, all later questions in that context use relevant information previously discussed which can be expanded further.

And even then it produces pretty decent responses. I wonder if we train it with all text pali and other language conversions present on sutta central, it might become more wise.

Some more questions / translations

Q. who is the wisest person alive

It’s not possible to determine who the wisest person alive is, as wisdom is a complex and multifaceted concept that can be difficult to quantify or measure. Moreover, wisdom is often subjective and can mean different things to different people and cultures.

There may be individuals who are widely regarded as wise or knowledgeable in certain fields or areas of expertise, but it’s important to remember that wisdom is not only about having a vast amount of knowledge, but also about using that knowledge to make sound and compassionate decisions that benefit oneself and others.

In Buddhism, wisdom is seen as an ongoing process of deepening insight and understanding that arises from a combination of direct experience, study, reflection, and practice. Therefore, rather than trying to identify the wisest person alive, it may be more fruitful to focus on developing and cultivating wisdom within oneself through these various means.

Q. describe this in english SuttaCentral

The text you linked is a Pali language version of the “Mettasutta” or “Discourse on Loving-Kindness.” The passage describes how to cultivate an attitude of loving-kindness towards oneself and others, and expresses the hope that all beings may be happy and free from suffering.

The text begins with instructions on how to develop the mental qualities of kindness, compassion, and equanimity, and continues with an exhortation to treat all beings with kindness and respect, regardless of their station in life. It also emphasizes the importance of avoiding anger and holding no ill will towards others.

The passage concludes by reminding the reader that the cultivation of loving-kindness is an ongoing process that requires sustained effort and practice. It encourages the reader to cultivate a sense of boundless, universal love for all beings, and to make the development of this quality a central focus of their spiritual practice.

Q. what does the passage say about how wide the loving and kindness should be and how deep

The passage, which is the Metta Sutta, teaches that one should cultivate boundless loving-kindness towards all beings, both upwards and downwards, and all around. The sutta says “May all beings be happy at heart. Whatever beings there may be, whether they are weak or strong, without exception, long, large, middling, short, subtle, blatant, seen & unseen, near & far, born & seeking birth: May all beings be happy at heart.” This indicates that the love and kindness should be limitless, including all beings regardless of their size, shape, or location. The depth of the loving-kindness should also be boundless, with the aspiration for all beings to be happy at heart.

Q. what does passage say about mother

The passage mentions mothers as an example of how loving-kindness should be developed towards all beings. It compares the love of a mother for her child to the love that should be developed towards all living beings. Just as a mother would protect her only child with her own life, the practitioner should cultivate a boundless mind of loving-kindness towards all beings without any exception. The passage emphasizes that this boundless loving-kindness should be developed to the extent of pervading the entire world, both horizontally and vertically, without any limits or boundaries.

1 Like

So if we were to train ChatGPT with more pali, english translations and in other languages it can do even better for summarizing describing or answering specific questions

Although some tricky logic questions humans can answer ChatGPT provides wrong answers check one below, first part is right, the later extended question is wrong

I’m of the opinion that the “AI revolution” is severely overblown. I think most of these people obsessed with technology think we’ll basically accidentally create intelligence but that seems just absurdly naive and ignorant to me at this point.

I wouldn’t even consider AI to be incompatible with Buddhism (if you can be reborn as an animal, human or no, why not as code? We’re all just meat machines after all) but I think just giving algorithms a ton of inputs from search results is hilariously inadequate to creating sustained feelings and understanding from scratch.

I think if we ever truly form consciousness from scratch it’ll be as an endeavor of curiosity and intellect, not profit motive from a broken society trying to create “the next big thing” in economics.

A very good interview with an AI expert about how ChatGPT is trained and the limits of this approach:

2 Likes

One disclaimer i will like to make here, which wasnt apparent at time this content was created.

ChatGPT doesnt have ability to read or scrape content from a website link. Though from conversations you can see it pretends to read and understand the content which may not be accurate and is guess-work.
You should copy paste the content for accuracy.

Probably version 4 has scraping abilities

One of the things I did right before I stopped working was play around with AI and language models.

I took the trouble to learn Python, did a course on AI, then deployed a language model on AWS Sagemaker. Luckily the client was paying for all this, because just running the virtual machine on AWS would have cost hundreds of dollars an hour.

I wasn’t particularly impressed by the results, but I was using an early model (probably equivalent to GPT2). It has improved a lot since then, some AI researchers are claiming that current models exhibit signs that they are able to do complex multi step logical inference - an achievement that was previously thought to be exclusively the domain of highly intelligent beings.

If anyone is interested in exactly how a language model works, this article by Stephen Wolfram may prove useful. It does require high school maths to understand, but I found it a very clear explanation and actually a good summary of the course I did.

Disclaimer: I am not a fan of AI or technology in general, so I will never use anything like ChatGPT. It’s funny - when I did my undergraduate science degree in the early 80s, AI was in its infancy and everyone wanted to study it. I wasn’t, I ended up doing my thesis in computer music.

After several months, ChatGPT has made significant progress in Pali. I recently tried reading DN27 with the support of ChatGPT.

Below is an example: when I pasted a passage from the commentary into ChatGPT, the response was quite insightful in my opinion.

ChatGPT - Certainly, let’s break down the commentary for passage 118:

118. niviṭṭhāti abhiniviṭṭhā acalaṭṭhitā.

  • niviṭṭhāti: Firmly established or rooted.
  • abhiniviṭṭhā: Strongly grounded, deeply rooted.
  • acalaṭṭhitā: Unwavering and unshakeable.

This part emphasizes the qualities of faith and conviction. Those with unwavering faith are firmly established and deeply rooted in their beliefs.

kassa pana evarūpā saddhā hotīti? sotāpannassa.

  • kassa pana: To whom does.
  • evarūpā: Of what kind.
  • saddhā: Faith.
  • hotīti: Is.

This part asks about the nature of such faith. The answer is that this kind of unwavering faith is characteristic of a Sotāpanna, the first stage of enlightenment in Buddhism.

so hi niviṭṭhasaddho asinā sīse chejjamānepi buddho abuddhoti vā, dhammo adhammoti vā, saṅgho asaṅghoti vā na vadati.

  • so hi: Such a person.
  • niviṭṭhasaddho: One with unwavering faith.
  • asinā: Even if.
  • sīse chejjamānepi: His head were to be split open.
  • buddho abuddhoti vā: He would not say “the Buddha is not.”
  • dhammo adhammoti vā: He would not say “the Dhamma is not.”
  • saṅgho asaṅghoti vā: He would not say “the Saṅgha is not.”
  • na vadati: He does not speak in such a way.

This part illustrates the unwavering nature of faith in a Sotāpanna. Even if their head were split open, they would not deny the Buddha, Dhamma, or Saṅgha. This reflects the depth of their conviction.

patiṭṭhitasaddho hoti sūrambaṭṭho viya.

  • patiṭṭhitasaddho: One with firmly established faith.
  • hoti: Is.
  • sūrambaṭṭho viya: Similar to Sūrambaṭṭha.

This part highlights that someone with firmly established faith is like Sūrambaṭṭha, emphasizing their unwavering commitment and resoluteness.

so kira satthu dhammadesanaṃ sutvā sotāpanno hutvā gehaṃ agamāsi.

  • so kira: It is said that this person.
  • satthu: The teacher (the Buddha).
  • dhammadesanaṃ: The teaching of the Dhamma.
  • sutvā: Having heard.
  • sotāpanno: Attained the stage of a Sotāpanna.
  • hutvā: Having become.
  • gehaṃ: Home.
  • agamāsi: Returned.

This part tells the story of someone who became a Sotāpanna after listening to the Buddha’s teaching and then returned to their home.

atha māro dvattiṃsavaralakkhaṇappaṭimaṇḍitaṃ buddharūpaṃ māpetvā tassa gharadvāre ṭhatvā “satthā āgato”ti sāsanaṃ pahiṇi.

  • atha: Then.
  • māro: Māra, the tempter or the personification of evil in Buddhism.
  • dvattiṃsavaralakkhaṇappaṭimaṇḍitaṃ: Adorned with the thirty-two marks of a great man.
  • buddharūpaṃ: In the form of the Buddha.
  • māpetvā: Having created.
  • tassa: Of that person.
  • gharadvāre: At the door of their house.
  • ṭhatvā: Having stood.
  • satthā āgato: “The teacher has come.”
  • sāsanaṃ pahiṇi: Sent a message about the dispensation (the Buddha’s teaching).

This part describes how Māra, the evil one, assumed the appearance of the Buddha and stood at the door of the person’s house to mislead them.

sūrambaṭṭho cintesi “ahaṃ idāneva satthu santike dhammaṃ sutvā āgato, kiṃ nu kho bhavissatī”ti upasaṅkamitvā satthusaññāya vanditvā aṭṭhāsi.

  • sūrambaṭṭho: Sūrambaṭṭha, the person with unwavering faith.
  • cintesi: Considered or thought.
  • “ahaṃ idāneva satthu santike dhammaṃ sutvā āgato, kiṃ nu kho bhavissatī”ti: “I have just come after listening to the Dhamma in the presence of the teacher. What will happen now?”
  • upasaṅkamitvā: Having approached.
  • satthusaññāya: Recognizing the teacher.
  • vanditvā: Having paid homage.
  • aṭṭhāsi: Stood.

Here, Sūrambaṭṭha reflects on his encounter with the false Buddha, wondering about the consequences of listening to the Dhamma in the Buddha’s presence. He then approaches the actual Buddha, recognizes him, pays homage, and stands before him.

māro āha — “ambaṭṭha, yaṃ te mayā ‘rūpaṃ aniccaṃ … pe … viññāṇaṃ aniccanti kathitaṃ, taṃ dukkathitaṃ. anupadhāretvāva hi mayā evaṃ vuttaṃ. tasmā tvaṃ ‘rūpaṃ niccaṃ … pe … viññāṇaṃ niccan’ti gaṇhāhī”ti.

  • māro: Māra.
  • āha: Said.
  • ambaṭṭha: A name used here.
  • yaṃ te mayā ‘rūpaṃ aniccaṃ … pe … viññāṇaṃ aniccanti kathitaṃ, taṃ dukkathitaṃ: What I have said to you, “Form is impermanent, … consciousness is impermanent; that which is impermanent is suffering,” has been wrongly reported by me.
  • anupadhāretvāva hi mayā evaṃ vuttaṃ: For I did not maintain it correctly.
  • tasmā tvaṃ ‘rūpaṃ niccaṃ … pe … viññāṇaṃ niccan’ti gaṇhāhī”ti: Therefore, you should take it as, “Form is permanent, … consciousness is permanent.”

Māra attempts to deceive Sūrambaṭṭha by claiming that he, Māra, had misreported the impermanence of form, feelings, perceptions, mental formations, and consciousness. Māra suggests that Sūrambaṭṭha should now consider them as permanent, contrary to the Buddha’s teachings.

so cintesi — “aṭṭhānametaṃ yaṃ buddhā anupadhāretvā apaccakkhaṃ katvā kiñci katheyyuṃ, addhā ayaṃ mayhaṃ vicchindajananatthaṃ māro āgato”ti.

  • so cintesi: He thought.
  • “aṭṭhānametaṃ: This is a place.
  • yaṃ buddhā anupadhāretvā apaccakkhaṃ katvā kiñci katheyyuṃ: Where the Buddha, after not maintaining it and denying anything, would speak anything.
  • addhā ayaṃ mayhaṃ vicchindajananatthaṃ: This evil one, Māra, has come to confuse me.
  • māro āgato”ti: Māra has come.

Sūrambaṭṭha realizes that this is the location where the Buddha would speak without maintaining his silence. He suspects that Māra has come to deceive him.

tato naṃ “tvaṃ mārosī”ti āha.

  • tato: Therefore.
  • naṃ: Him (Sūrambaṭṭha).
  • “tvaṃ mārosī”ti āha: He said to him, “You are Māra.”

Recognizing Māra’s deception, Sūrambaṭṭha accuses him of being Māra.

so musāvādaṃ kātuṃ nāsakkhi. “āma mārosmī”ti paṭijānāti.

  • so: He (Sūrambaṭṭha).
  • musāvādaṃ kātuṃ nāsakkhi: Could not make false accusations.
  • “āma mārosmī”ti paṭijānāti: Confirmed, “Yes, I am Māra.”

Sūrambaṭṭha did not accuse Māra falsely but acknowledged Māra’s identity.

“kasmā āgatosī”ti? tava saddhācālanatthanti āha. “kaṇha pāpima, tvaṃ tāva eko tiṭṭha, tādisānaṃ mārānaṃ satampi sahassampi satasahassampi mama saddhaṃ cāletuṃ asamatthaṃ, maggena āgatasaddhā nāma thirā silāpathaviyaṃ patiṭṭhitasineru viya acalā hoti, kiṃ tvaṃ etthā”ti accharaṃ pahari. so ṭhātuṃ asakkonto tattheva antaradhāyi.

  • “kasmā āgatosī”ti: “Why have you come?”
  • tava: Your.
  • saddhācālanatthanti: For the sake of testing your faith.
  • āha: He said.
  • “kaṇha pāpima: “Wicked Black One,”
  • tvaṃ tāva eko tiṭṭha: “You stand alone here.”
  • tādisānaṃ mārānaṃ satampi sahassampi satasahassampi mama saddhaṃ cāletuṃ asamatthaṃ: “It’s not possible for the thousands and millions of Maras to shake my faith even as a solid, immovable mountain would remain unshaken by the wind on the path.”
  • maggena āgatasaddhā nāma thirā silāpathaviyaṃ patiṭṭhitasineru viya acalā hoti: “Just as the firm earth remains unshaken by the travelers’ footsteps on the path with unwavering faith that has come.”
  • kiṃ tvaṃ etthā”ti: “What are you doing here?”
  • accharaṃ pahari: He struck a wonder.
  • so ṭhātuṃ asakkonto tattheva antaradhāyi: Unable to stay, he disappeared right there.

Sūrambaṭṭha questions Māra about his intentions for coming. Māra responds, explaining that he has come to test Sūrambaṭṭha’s faith. Sūrambaṭṭha, demonstrating his unwavering faith, describes that his faith is as unshakable as a mountain and as firm as the earth, and he questions why Māra is present. Māra responds with a wonder and disappears, unable to shake Sūrambaṭṭha’s faith.

evarūpaṃ saddhaṃ sandhāyetaṃ vuttaṃ “niviṭṭhā”ti.

  • evarūpaṃ saddhaṃ: Such faith.
  • sandhāyetaṃ: Should be understood.
  • vuttaṃ: It is said.
  • “niviṭṭhā”ti: As “firmly established.”

I believe that, moving forward, we have ChatGPT as a very capable assistant for reading Tipitaka texts.

1 Like