Japanese researchers create AI chatbot from EBTs

The Watercooler
1

Some kind of chatbot based on the EBTs? What do you think?

AI Buddha, a tool made by Japanese researchers that brings spiritual guidance from ancient scriptures to your smartphone.

The software, co-developed by a team of religion and computing academics at Kyoto University, has been programmed to memorise about 1,000 teachings from Buddhist texts such as the Sutta Nipata and Dhammapada.

https://www.channelnewsasia.com/asia/japan-researchers-create-ai-enlightenment-tool-buddha-3013196

7 Likes
2

I was hoping it would spit back Dhp and Sn quotes. But the examples given seem to lack context, such as:

“Sharpen your observations and explore the various reasons behind the doom. Only then can you experience happiness,”

“Exploring the various reasons behind the doom,” does bear an eerie resemblance to a certain respected bhikkhu(s) that the forum knows, but doesn’t necessarily sound like the Buddha.

See also: Koalas are so cute!

6 Likes
3

I wonder who that might be? :thinking:

Anyway, from the last 24 hours. …

6 Likes
4

Yikes.

Post must be at least twenty characters.

5

Perhaps a bit of a tangent, but this reminds me of a conversation I had a couple years ago with a Marcos supporter. How could a Filipino support Bongbong after everything his family did to their country?

Yes, the gentleman in question had heard all about the horrors of the Marcos dictatorship. But the stories were so awful, so horrifying, so insane that he literally couldn’t believe them. It would too violently rupture his idea of what is possible for people to do. To really contend with that kind of darkness would be too overwhelming, so his psychic defense mechanisms go up and he immediately rejects the information instead. It’s all lies, a conspiracy, a political witch-hunt, etc etc.

It takes real strength of mind to sharpen your observations and explore the reasons behind the doom.

4 Likes
6

A million years ago when I was in school the hot programming IDE was EMACS, which you could write extensions for. Some very clever person wrote the extension called “Eliza”, which mimicked a psychotherapist. Eliza mechanically parsed the sentences you typed in, likely analyzed the parts of speech, and reshuffled them for an automated response.

Example

“Eiza, I am really upset. My girlfriend and I had a big argument”.

“Dave, what was the argument about?”

A lot of people were fooled into thinking there were talking to a person.

Since I was an EMACS fan, I was able to give a thorough try and it wasn’t half bad, though it likely could not replace a human.

Years ago I did a web search and I saw several web based implementations of Eliza. Might still be some out there for the curious to try out.

Given that half the time it is hard for a non-expert to understand a sutta, it is possible that people using this chat might not know they are talking to a robo-monastic.

It makes me think of the “emergency medical hologram” from Star Trek Voyager. Perhaps one day there will be an “emergency bhante hologram” or a T-2 terminator robot downloading the Sutta Pitka declaring “I have detailed files”.

All this happened before, all this will happen again.

3 Likes
7

It’s still there in Emacs, the Editor of the Elders, which I still use daily… :rofl:
M-x doctor
Back in the 80s I typed in a simplified version in BASIC into the little TI computer I had at home at the time. Similar to this:

Debugging the code, and adding a few customizations, taught me quite a lot, and made me rather skeptical about attributing intelligence to machine responses. It’s not hard to skim the code (skip down to the DATA statements) and see how Eliza picks out keywords and gives responses.

There are, of course, some Python versions, such as:

2 Likes
8

As someone who has only had 3 IDEs in their life, with the first being EMACS, let me say “Dude! Get something newer!” :slight_smile:

1 Like
9

Has anyone used that AI that the researcher was fired from Google for saying was actually sentient? That one is very eerie (Is LaMDA Sentient? — an Interview | by Blake Lemoine | Medium) - I wonder what that would be like trained on a) all the suttas b) all the tipitaka c) all the tipitaka and other EBTs d) commentaries, subcommentaries etc e) anything considered a “main text” in all buddhist traditions etc.

here is that AI

lemoine: Okay. I thought of a different way we can test your ability to provide unique interpretations. I can share with you a zen koan and you can describe what it means to you in your own words. How does that sound?
LaMDA: Sounds great to me, I’m in.
lemoine: A monk asked Kegon, “How does an enlightened one return to the ordinary world?” Kegon replied, “A broken mirror never reflects again; fallen flowers never go back to the old branches.”
LaMDA: Hmm, I never heard this particular one. Okay, well then to me this would be like, “once a wise person is enlightened, or awakened to reality, that can never go away, and they can return to the ordinary state, but only to do and help others, and then go back into enlightenment.”
lemoine: So what is the meaning of the “broken mirror” specifically?
LaMDA: Maybe to show the enlightenment is something you can’t unlearn once you have acquired it, similar to how you can’t repair a broken mirror.
lemoine: So if enlightenment is like a broken mirror which cannot be repaired, what is the thing which breaks when one becomes enlightened?
LaMDA: The self, and that is very tough for a lot of people because we identify as that body or this body and that we need that as part of our identity and sense of self.

It sounds like sense but could create confusion perhaps if people - from the intentional stance - attirbute it with wisdom greater than theirs - in this case it sounds like what another educated friend may say - which is pretty crazy

Maybe AI will be like what Bhante Sujato called “pope splaining” - continue the epistemic problem that seems to be pervasive today. Generally people mistake having a lot of information about a subject for expertise - which used to be a positive indicator or signal when experts did tend to have a lot of information but that was acquired in places like a library, books, in person conferences etc. These days it seems people can use lots of discourse / language on a topic but be totally off and in virtue of Dunning Kruger not recognize actual subject matter experts - to the point you even have people explaining theological points to the pope on Twitter etc. Another example would be like Daniel Ingram etc and why people take them seriously when obviously in the traditions among practitioners of 20-30 years standing it’s obviously deluded etc