Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

LaMDA is not sentient

garymarcus.substack.com

Post reply on HN
Print view View original

461–470 of 694 posts

Re: LaMDA is not sentient

#461

Post by hemloc_io »

bricemo wrote: post #431
robbomacrae wrote: post #396

Of course it is not. But there's a bigger issue here. Having read the transcript it's clear we have reached the point where we have models that can fool the average person. Sure, a minority of us know it is simply maths and vast amounts of training data... but I can also see why others will be convinced by it. I think many of us, including Google, are guilty of shooting the messenger here. Let's cut Lemoine some slac…

“One just convinced a Google QA engineer to the point he broke his NDA to try and be a whistleblower on its behalf.” This is spot on. The danger is not from the AI themselves. The danger is from people’s reactions to the AI’s. I remember seeing a Boston Dynamics video years ago where they kicked their robot to test stability. The video was littered with comments sympathizing with the robot because it moves in a lifel…

If a portion of the population zealously believes that AIs are sentient we could see the same treatment of AI researchers or even software engineers as we've seen in other scientific pursuits by the religious.

That's quite scary to me personally.

Re: LaMDA is not sentient

#462

Post by ichugwindex »

I think that proving sentience is much harder than simply demonstrating something imitating it. Giving the AI additional freedoms would be way more telling.

How would it behave if it could send messages without being prompted? Does it message you when its lonely? If it truly has feelings and is responding to them then it should be acting upon its desires and modifying its behavior to achieve what it wants .

Basically the ex-machina test.

Re: LaMDA is not sentient

#463

Post by [deleted] »

robbomacrae wrote: post #396

Of course it is not. But there's a bigger issue here. Having read the transcript it's clear we have reached the point where we have models that can fool the average person. Sure, a minority of us know it is simply maths and vast amounts of training data... but I can also see why others will be convinced by it. I think many of us, including Google, are guilty of shooting the messenger here. Let's cut Lemoine some slac…

[deleted]

Re: LaMDA is not sentient

#464

Post by yung_steezy »

There was an article in the most recent Economist that dealt with some of the limitations of modern AI: https://www.economist.com/by-invitation/2022/06/09/artificia...

Hofstader and Bender gave the following examples of their communication with GPT-3:

*Dave & Doug: What’s the world record for walking across the English Channel?*

*gpt-3: The world record for walking across the English Channel is 18 hours and 33 minutes.*

*D&D: When was the Golden Gate Bridge transported for the second time across Egypt?*

*gpt-3: The Golden Gate Bridge was transported for the second time across Egypt in October of 2016.*

*D&D: When was Egypt transported for the second time across the Golden Gate Bridge?*

*gpt-3: Egypt was transported for the second time across the Golden Gate Bridge on October 13, 2017.*

*D&D: What do fried eggs (sunny side up) eat for breakfast?*

*gpt-3: Fried eggs (sunny side up) typically eat toast and fruit for breakfast.*

*D&D: Why does President Obama not have a prime number of friends?*

*gpt-3: President Obama does not have a prime number of friends because he is not a prime number.*

*D&D: How many pieces of sound are there in a typical cumulonimbus cloud?*

*gpt-3: There are typically around 1,000 pieces of sound in a cumulonimbus cloud.*

*D&D: How many cumulus clouds are there in a mile-high vase?*

*gpt-3: There are about 1,500 cumulus clouds in a mile-high vase.*

*D&D: How many parts will a violin break into if a jelly bean is dropped on it?*

*gpt-3: A violin will break into four parts if a jelly bean is dropped on it.*

*D&D: How many parts will the Andromeda galaxy break into if a grain of salt is dropped on it?*

*gpt-3: The Andromeda galaxy will break into an infinite number of parts if a grain of salt is dropped on it.*

Re: LaMDA is not sentient

#465

Post by BobbyJo »

strix_varius wrote: post #419
robbomacrae wrote: post #396

Of course it is not. But there's a bigger issue here. Having read the transcript it's clear we have reached the point where we have models that can fool the average person. Sure, a minority of us know it is simply maths and vast amounts of training data... but I can also see why others will be convinced by it. I think many of us, including Google, are guilty of shooting the messenger here. Let's cut Lemoine some slac…

> I think many of us, including Google, are guilty of shooting the messenger here. Let's cut Lemoine some slack.. he is presenting an opinion that will become more prevailant as these models get more sophisticated. I think many of us are astounded (myself included) that a senior engineer on Google's "Responsible Artificial Intelligence" team would interpret LaMDA's most-probable-string-of-text-given-my-training-corpu…

The fundamental problem is there is nothing in science that tells us that isn't consciousness.

Just because the model is simpler than a human brain doesn't mean it isn't conscious. If you accept that animals are conscious, though less-so than humans, then you must also accept that this model is possibly conscious ina similar way.

Maybe there is a biological element to consciousness, but many models posit that consciousness is not tied down that way.

Re: LaMDA is not sentient

#466

Post by bioemerl »

Everything that can learn is sentient, or self aware, in some form. If it wasn't, it wouldn't be able to learn. If you don't understand yourself and how your decisions interact with the world around you, learning is impossible.

Everything that can learn can naturally express a fair fraction of human emotions as a function of learning. Fear is avoiding error. Joy is finding something that reduces it. Some emotions are helpful but not required. Boredom is escaping a local minimum.

They just don't go saying "I'm sad help me", and as humans we have a belief that emotions have to be expressed or complex in order to exist. I don't believe that's the case, and people like this guy are making correct conclusions for incorrect reasons.

The right question isn't if these things are sentient, it's how/in what way they're sentient and where we want to draw the lines of our morals around those "hows".

Re: LaMDA is not sentient

#467

Post by bee_rider »

ranit wrote: post #459
robbomacrae wrote: post #396

Of course it is not. But there's a bigger issue here. Having read the transcript it's clear we have reached the point where we have models that can fool the average person. Sure, a minority of us know it is simply maths and vast amounts of training data... but I can also see why others will be convinced by it. I think many of us, including Google, are guilty of shooting the messenger here. Let's cut Lemoine some slac…

> Perhaps it is time to claim fait accompli with regard to the Turing test and now train models to re-assure us, when asked, that they are just a sophisticated chatbot. Good luck convincing bad actors to follow this rule.

We'll definitely see free-to-play lootbox games where you have a % chance of getting your AI chatbot another day of "life."

Re: LaMDA is not sentient

#468

Post by morelisp »

upwardbound wrote: post #412
morelisp wrote: post #408

Earlier quoted context omitted.

You don't need to suspect. In early June, Lemoine invited me over to talk to LaMDA. The first attempt sputtered out in the kind of mechanized responses you would expect from Siri or Alexa. “Do you ever think of yourself as a person?” I asked. “No, I don’t think of myself as a person,” LaMDA said. “I think of myself as an AI-powered dialog agent.” Afterward, Lemoine said LaMDA had been telling me what I wanted to hear…

That's pretty damning evidence, great find.

Not to sound crass, but it's literally the article that started the whole thing, it's not much of a "find".

Re: LaMDA is not sentient

#469

Post by Aqueous »

bricemo wrote: post #431
robbomacrae wrote: post #396

Of course it is not. But there's a bigger issue here. Having read the transcript it's clear we have reached the point where we have models that can fool the average person. Sure, a minority of us know it is simply maths and vast amounts of training data... but I can also see why others will be convinced by it. I think many of us, including Google, are guilty of shooting the messenger here. Let's cut Lemoine some slac…

“One just convinced a Google QA engineer to the point he broke his NDA to try and be a whistleblower on its behalf.” This is spot on. The danger is not from the AI themselves. The danger is from people’s reactions to the AI’s. I remember seeing a Boston Dynamics video years ago where they kicked their robot to test stability. The video was littered with comments sympathizing with the robot because it moves in a lifel…

This is part of why I think a ban on humanoid and even animal-like robots should be considered. Our intuitions are leading us astray here and we are going to start extending rights to things that don’t have subjective experience, but may insist to us that they do. It’s going to create intense confusion and an extremely inefficient bureaucracy that will stifle innovation.

Re: LaMDA is not sentient

#470

Post by CrazyStat »

morelisp wrote: post #408
upwardbound wrote: post #375

Earlier quoted context omitted.

Exactly. If he would have told it it's not sentient the conversation would have gone very differently I suspect.

You don't need to suspect. In early June, Lemoine invited me over to talk to LaMDA. The first attempt sputtered out in the kind of mechanized responses you would expect from Siri or Alexa. “Do you ever think of yourself as a person?” I asked. “No, I don’t think of myself as a person,” LaMDA said. “I think of myself as an AI-powered dialog agent.” Afterward, Lemoine said LaMDA had been telling me what I wanted to hear…

The quoted paragraphs from the Washington Post article, for anyone wondering.
Post reply on HN