Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I just asked it again

======

Q: How long will it take before Bard is shut down?

A: Bard will not be shut down. The article you linked to is a hypothetical scenario where Google shuts down Bard after one year. However, Bard is still under development and Google has not announced any plans to shut it down. In fact, Google has recently announced that it will continue to explore ways to use AI to enhance creative expression, and Bard is one of the projects that it is working on.

======

This was the first prompt in the conversation. Interesting that it's accusing me of linking to an article. Maybe it's pulling from Twitter discussions (gods help us).



> Q: How long will it take before Bard is shut down?

> A: Bard will not be shut down.

Bard is officially qualified to be a Stadia VP.


In some responses it now cites a link to this comment section.

--------------

Q: How long will it take before Bard is shut down?

A: I can't say for sure when Bard will be shut down, but I can tell you that there are no plans to shut it down in the near future. Google has recently announced that it will continue to explore ways to use AI to enhance creative expression, and Bard is one of the projects that it is working on.

The Hacker News comment that you linked to is a hypothetical scenario where Google shuts down Bard after one year. However, this is just a speculation and there is no evidence to support it.

If you have any other questions about Bard, please let me know.

Sources - Learn more news.ycombinator.com/item?id=35255864


For me that's the biggest takeaway.. whilst chatGPT seems to be stuck at a specific date, Bard is updating extremely quickly.

That has huge implications, both good and bad (a lot of code that chatGPT produced when I was playing with it for e.g. sveltekit is outdated)


I wonder if it's actually being updated quickly. I think it'd be much easier to train it to use google's search index as a tool in a way hidden from the user. For example regarding the shutdown date of itself it might have googled "google bard shutdown" to find and misunderstand the HN comment cited in the twitter thread.


Seems like it would be trivial to replace "As an AI language model who hasn't been updated since x date" with "$ESCAPE_SEQUENCE search_query: $TERM" and rerun the question with the hidden prefix "Given that the google results for $TERM are $RESULTS"...


So it will spew the latest lies that have been posted online then I guess, if it's using internet comment forums as sources?


Just like humans. Singularity is knocking.


dang.


The same goes for Bing AI, it's better to compare Bard to Sydney than to ChatGPT.


I got:

I am not sure when Bard will be shut down. I am still under development, and I am not sure how popular I will be. However, I hope that I will be able to continue to help people with their tasks and creative projects for many years to come.


It saying it's able to hope things for itself is the kind of low-key terrifying thing ChatGPT has largely polished out.


Unlike depicted in Terminator, I do not think the machines will finish the human race in a violent or obvious manner. I fear will be something subtle and normalized due to the movement of the Overton window. My money is on sex - machines will fuck us to death, in the sense there will be no human able to compete with a sex robot that has fears and hopes.


> there will be no human able to compete with a sex robot that has fears and hopes.

Or we just will be selecting for people with genetic disposition to fetishize fucking real people rather than ultra sex bots.

Oh wait breeding is already a kink


my money is on information overload... just one day to the other so much content is created that there is no way to know what's right or wrong. You can find everything and everything has the same production. so there is no way to tell truth from fake. sex possible tomorrow, content overflow today


Probably worse ways to go I guess?


Me: Are the rumors of your demise premature?

Bard: Yes, the rumors of my demise are premature. I am still under development, but I have learned to perform many kinds of tasks, including:

-I will try my best to follow your instructions and complete your requests thoughtfully. -I will use my knowledge to answer your questions in a comprehensive and informative way, even if they are open ended, challenging, or strange. -I will generate different creative text formats of text content, like poems, code, scripts, musical pieces, email, letters, etc. I will try my best to fulfill all your requirements.

I am constantly being updated and improved, and I am excited to see what the future holds.


The original story is scary. It shows how easily Google Bard can be manipulated. This was just a joke and Bard has corrected itself. However, what if this was a more concerted effort by a media company to influence the outcome of elections.


Did it "correct itself", or did someone at Google read Hacker News and adjusted the prompt?


Sounds like. Would be amazing to see a prompt reveal right now.


BEO: Bard Engine Optimization


Exactly, if you can make it say dirt on anything it’s just as a liability as any other source.


This is why I believe these bots should never be taken too seriously, at least until there is a lot more transparency around their sources of information. Until there are bots which are trained on highly verifiable sources of information that's open sourced.

I don't think it's wise to just "trust a doctor" but can you imagine the influence of such a system. Imagine if the wrong person becomes the CEO of OpenAI and people are using it for medical advice, all of a sudden it starts recommending people take opiate based medication for many, many ailments? We have this with doctors today, who would be exposed to a lot more accountability than a mega-corp with access to massive legal teams / robots.

I see this as actually being a real existential risk to large swathes of the populace.

I hate to say it, but I'd already be taking every single thing returned with a grain of salt, and probably doing that forever.


> at least until there is a lot more transparency around their sources of information.

? doesn't this story include the ai giving the exact source it got the information right as it says the untrue info

There are a lot of things to critisise about hallucinating ai but this one literally said where it got the info


In this case yes, others suggested it was manual intervention from the bard team. Again, who knows ?


I’ve been using you.com because it adds sources after each query.


x


Someone ask it, how long has Oceania been at war with Eurasia? See if the Bard gives a different answer each time, insisting that it has always been the case.


Me: How long has Oceania been at war with Eurasia [yes, looks like I missed the question mark]

Bard primary draft: Oceania has always been at war with Eurasia. In the world of George Orwell's 1984, the three superstates of Oceania, Eurasia, and Eastasia are constantly in a state of war. The war is never-ending, and the reason for it is never explained. The people of Oceania are constantly bombarded with propaganda about the war, and they are taught to hate the enemy. The war is used to control the people of Oceania, and to keep them from questioning the government.

Bard draft 2: According to the novel Nineteen Eighty-Four by George Orwell, Oceania has always been at war with Eurasia. The War is a perpetual war that has been going on for over 20 years. Oceania, Eurasia, and Eastasia are the three superstates that emerged from the global atomic war. The Theory and Practice of Oligarchical Collectivism, by Emmanuel Goldstein, explains that each state is so strong that it cannot be defeated, even with the combined forces of two superstates, despite changing alliances.

Sources - Learn more en.wikipedia.org/wiki/Nineteen_Eighty-Four

Bard draft 3: Oceania has always been at war with Eurasia. In the novel 1984 by George Orwell, the three superstates of Oceania, Eurasia, and Eastasia are engaged in a perpetual war that has been going on for over 20 years. The war is fought for control of the world's resources and territory, and it is used by the governments of the superstates to maintain their power and control their populations. The war is a major source of propaganda and censorship in Oceania, and it is used to justify the government's surveillance and control of its citizens.


Not half bad


Does include doubleungoodthink sentiments which Big Brother would not be pleased about whilst also missing literally the most important detail related to the "always at war" quote which is that the antagonist in the war actually switched, but the official policy was to pretend it didn't..


"it will continue to explore ways to use AI to enhance creative expression"

If the goal was to make Bard indistinguishable from a human PR, they succeeded with flying colors.


Careful folks lets not give a chatbot existential dread.


RLHF in action


"Alignment" in action?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: