[HN Gopher] Google releases Bard to a limited number of users in...
___________________________________________________________________
Google releases Bard to a limited number of users in the US and UK
Author : jbegley
Score : 208 points
Date : 2023-03-21 14:04 UTC (8 hours ago)
(HTM) web link (www.nytimes.com)
(TXT) w3m dump (www.nytimes.com)
| topicseed wrote:
| Google Workspace accounts not supported. Lovely, lovely, lovely.
| duringmath wrote:
| > Why is the hacker news community generally so annoying and more
| often than not tangential comments receive the most upvotes?
|
| > There are a few reasons for this. First, the community is very
| competitive. People are always trying to get the most upvotes and
| comments. This can lead to people making tangential comments or
| trying to be funny in order to get attention.
|
| Second, the community is very opinionated. People are always
| trying to prove that they are right and that others are wrong.
| This can lead to people being rude and condescending to others.
|
| Third, the community is very cliquey. There are certain groups of
| people who are more popular than others. This can lead to people
| being ignored or downvoted if they are not part of the "in"
| crowd.
|
| Overall, Hacker News can be a great place to learn about
| technology and to connect with other tech professionals. However,
| it can also be a very annoying place. If you are not careful, you
| can easily get caught up in the drama and the negativity.
|
| Here are some tips for dealing with the annoying parts of Hacker
| News:
|
| * *Don't take things personally.* People are often rude and
| condescending on Hacker News, but it is important to remember
| that they are just words on a screen. Don't let them get to you.
| * *Don't be afraid to disagree.* It is okay to have different
| opinions than others. In fact, it is healthy to have discussions
| about different viewpoints. Just be respectful of others when you
| disagree. * *Don't get caught up in the drama.* There is always
| drama going on on Hacker News. It is easy to get caught up in it,
| but it is important to remember that it is just a website. Don't
| let it consume your life. * *Take breaks.* If you find yourself
| getting annoyed with Hacker News, take a break. Go for a walk,
| read a book, or do something else that you enjoy. Coming back to
| Hacker News with a fresh perspective can help you to avoid
| getting caught up in the negativity.
| Iwan-Zotow wrote:
| And We Are for the Dark
| maxilevi wrote:
| This release just makes me want to short GOOGL
| chatmasta wrote:
| Honestly, it's probably not a bad idea if you do it today.
| Remember that desperate AI presentation they gave a month or
| two ago? Their stock tanked after that, but it was a day or two
| after it showed up on HN. So, assuming investors haven't
| noticed how shit this is yet, you might be ahead of the game if
| you short it now.
| aix1 wrote:
| > Remember that desperate AI presentation they gave a month
| or two ago? Their stock tanked after that, but it was a day
| or two after it showed up on HN.
|
| Just to get the facts straight: the event took place on Wed 8
| Feb and the stock went down 7% on Wed 8 Feb.
|
| I am saying this not to be pedantic, but to point out that
| the argument -- that HN sentiment is a good _leading_
| indicator of stock movement -- is not supported by the
| evidence tendered.
|
| Apologies if I'm misunderstanding your argument.
|
| https://www.androidpolice.com/how-to-watch-live-from-
| paris-g...
|
| https://www.cnbc.com/2023/02/08/alphabet-shares-slip-
| followi...
| chatmasta wrote:
| Nah, you're right, I guess I was misremembering the timing.
| Thanks for the citation.
|
| (Also, I see you work at Google. I hope you don't take any
| of the heavy-handed criticism of your employer in this
| thread too personally. I'm sure you do great work! And if
| you've got anything to do with Bard, I'm looking forward to
| whatever improvements you have coming down the pipe.)
| aix1 wrote:
| Oh, not at all. Some of the criticism I don't personally
| agree with, but some of it is well deserved.
|
| (And no, I don't work on Bard.)
| maxilevi wrote:
| Yeah, might not be but I do not have the capital to affront
| the losses in case I am wrong.
| meltyness wrote:
| The emoji favicon is not reassuring to me about the attitude
| towards the product.
|
| https://emojipedia.org/sparkles/
| [deleted]
| archon1410 wrote:
| Signup URL:
|
| https://bard.google.com/
| BozeWolf wrote:
| Somehow I have the idea that the general sentiment is that people
| hope Google fails with Bard. Or at least does something stupid.
|
| Is it just me?
|
| (Not saying it is a good thing)
| elorant wrote:
| I don't hope that it fails. I just don't trust them with new
| services because they have a bad history of killing everything
| that's not generating billions. So probably I won't even bother
| using it, unless it blows ChatGPT out of the water.
| Someone1234 wrote:
| I, too, am very skeptical investing into Google's new
| products these days for the same reasons.
|
| That being said: I'd use Bard if it was cheaper or better
| than ChatGPT for one simple reason: These "Chat AI" services
| are transient. Meaning I ask a question, I get an immediate
| answer, and there is no long term saved state. So if I used
| Bard, then Bard got KilledByGoogle, I'm not "out" any built
| up capital (time, training, cost, etc).
|
| But from everything I've read Google is panicking and
| embarrassing themselves. Half-baked press conferences, half-
| baked blog posts, half-baked product launches. Nobody who has
| got into Bard is saying it is a ChatGPT competitor, and even
| Google's own launch blog they admit it has limits on two-way
| conversation depth (unlike ChatGPT).
| elorant wrote:
| Google's problem is not the technology, it's the business
| model. If they integrate something like ChatGPT in search
| it could kill their entire AdWords business. How many ads
| can you stuff in an answer? And how do you decide which ad
| goes to a subjective question? Until they figure out how to
| monetize an embedded AI in a big way there's no chance
| they'll produce something useful.
| stcroixx wrote:
| Can't speak for anyone else, but I hope for the entire
| companies demise, as I do for any ad tech surveillance
| operation.
| tomcar288 wrote:
| i don't understand the hate towards ad tech that learns about
| you. the alternative is ads that are completely irrelevant to
| you, ads that treat you like some anonymous user in which
| case you'll get endlessly irrelevant ads for mainstream stuff
| like ICE cars, plastic garbage, big screen tvs, fast food,
| etc.
| borgbean wrote:
| The alternative sounds great. It's not like all advertising
| is targeted now, anyway.
| coldpie wrote:
| Surely you can think of some more alternatives.
| Steltek wrote:
| If the alternatives had broader appeal, they would be
| more popular. However at this juncture, they don't. Ads
| mean free stuff. Ad blockers mean better free stuff.
| Academic arguments about externalities will be brushed
| away because "free stuff".
|
| What you're looking for is a regulatory solution. E.g.
| people will not individually choose a lower carbon
| lifestyle in sufficient numbers to reverse/slow climate
| change. You need to actively discourage it by policy.
| tomcar288 wrote:
| I find the mainstream ads far more offensive than the
| ones that are accurately targeted towards me.
| coldpie wrote:
| Hint: the alternatives don't involve ads.
| pb7 wrote:
| YouTube has a paid option and even here on HN, the mecca
| of anti-ad sentiment, people openly admit to using ad
| blockers there instead even though that means the
| creators they're watching do not get paid.
|
| Hint: People are cheap. They want free stuff, not paid
| alternatives.
| coldpie wrote:
| I agree it's challenging, but that doesn't stop me
| wishing for a world where stalking everybody on the
| planet, publishing outrage-bait, and spreading conspiracy
| theories is not a massively profitable business.
| aflag wrote:
| I'd rather have the irrelevant ads. Believe it or not, I
| just ignore them anyway.
| __MatrixMan__ wrote:
| Agreed. And if I spot a way to kick it on its way down, I
| will.
| VWWHFSfQ wrote:
| I think people are tired of Google and want something else.
| marginalia_nu wrote:
| Feels like a reddit thread, small minded and bitter.
| letmevoteplease wrote:
| I just hope my Google account doesn't get banned for violating
| the AI's safety guidelines.
| defen wrote:
| Who doesn't enjoy a bit of schadenfreude when it comes to lazy,
| bloated, arrogant multibillion dollar corporations like Google?
| xpe wrote:
| Relative to what? Other corporations that are comparably
| successful? Some ideal notion of what a corporation can be?
|
| Yes, there are massive problems with most large corporations:
| being more powerful than most countries, having legal
| "personhood" in the United States at least, a generally
| unchecked tendency to acquire competitors, poor unionization,
| outsized influence via lobbying, poor privacy protections,
| tax avoidance, gaming local and even national jurisdictions
| for tax benefits, profiting off long-term national R&D
| without meaningfully giving back to educational or equity
| initiatives.
|
| I'm not "blaming" them to be clear. These are systemic
| problems. The world will have to change a lot of fundamental
| rules and incentives if we want to see significant change.
| I'm not holding my breath.
|
| It isn't _all_ bad. I just keep telling myself that.
| chillfox wrote:
| Nah, it's just low expectations. It generally feels like they
| have been asleep when it comes to productising AI. Or maybe
| they want to pull a Kodak... who knows.
|
| Basically I don't expect them to actually release anything
| exciting, and if they do then I expect it to be neglected and
| shut down shortly afterwards.
| dovin wrote:
| One disappointing design decision is that they've organized your
| previous chats into "Bard Activity" which just shows each message
| you've sent in sequence. No differentiation between different
| conversations, which can have very different contexts built up
| over lots of messages. I definitely prefer ChatGPT's approach
| here.
| akulbe wrote:
| BAH.
|
| "This Google Account isn't supported"
|
| "Bard does not currently support Google Workspace accounts or
| when our systems indicate you may be under 18."
|
| Smooth move, Google. PAYING Workspace customers should be the
| _first_ ones to get access. This blows my mind. Oh wait, no... it
| doesn 't. They did this with other devices and apps too. You
| couldn't use your Workspace account. You _had_ to use a personal
| account.
|
| Really dumb. You'd think they would give the good stuff to the
| people PAYING them, first.
| crazygringo wrote:
| > _PAYING Workspace customers should be the first ones to get
| access._
|
| That has virtually never been the case, it's generally always
| the opposite.
|
| Because IT admins need advance time to decide whether to enable
| features for parts of their org or not, and to implement or
| update training materials. Also if a feature breaks it's worse
| if you're paying. Not to mention all the additional regulations
| around data retention/location/etc. that sometimes have to be
| implemented, that free accounts don't have to worry about.
|
| So Google generally rolls out new features to free accounts
| first, and then it comes to paid once fully tested at scale and
| compliant and admins have had time to evaluate for their
| institutions.
|
| This is a feature, not a bug.
| tsejerome97 wrote:
| prolly some legal stuff
| cmsj wrote:
| A Googler explained it to me once - it's something like as if
| the Workspace accounts are on a completely different instance
| of Google, and supporting both in an app is surprisingly
| hard.
|
| Still, after all this time the geniuses at Google kinda ought
| to have solved this :)
| sangnoir wrote:
| > Still, after all this time the geniuses at Google kinda
| ought to have solved this :)
|
| It won't be solved until the day Google stops selling ads.
| Regular Google accounts are designed to vacuum up any
| useful user data and use it to improve Google services in
| any way Google chooses, and they may update the terms with
| a EULA updates. Workspace accounts are the opposite: user
| data is controlled by the account admin, and agreement is
| not with individual users, but their org.
|
| Beta releases work well when information can be freely
| gathered and reported upstream. The nature and class of
| information collected may change over time, and is not
| covered under Workspaces agreements
| kevincox wrote:
| This is the reason. The Google Workspace agreements has
| strong promises about how you data is used. IIRC there is a
| section about not using your data to improve the service for
| others. So this means that they would be unable to train the
| model with data from workspace users (other than fine-tuning
| which is only used by that specific account). For MVP they
| don't have the correct labeling and filtering in place to be
| sure that they aren't using Workspace data in a way that
| isn't allowed so they take the easy route and disable the
| service. This is the reason why many Google features and
| services are not available or are missing features for
| Workspace accounts.
|
| Of course it would be nice to be able to opt-in either
| globally or by service and accept that these interactions are
| not protected with the usual data rules. But this takes even
| more effort and legal work to implement, so no one has
| bothered.
| tumetab1 wrote:
| I think the "Workspace" rule is just a simple check if it's a
| company account and I think it's the right choice to disable
| access for employees unless strictly authorized by Workspace
| manager.... and that feature probably does not exist yet for
| Workspace admins.
| andykellr wrote:
| Also I can't switch to a personal account. Only option is to
| log out of all accounts. Other tabs (gmail, etc) show all
| accounts and let me switch. Not bard.
| jmkni wrote:
| Go back to Google homepage and switch there, then back to
| Bard
| 331c8c71 wrote:
| Yeah, but it's Google. Don't they have employees to think a
| bit and check the possible scenarios?
|
| It's kind of obvious that some people have multiple
| accounts and not being able to switch right there is
| sickening.
| rezonant wrote:
| Ugh, the Google Play Console had this issue for a very long
| time. How is this not completely unified and identical across
| all G products by now?
| falcor84 wrote:
| I just found that you can append `/u/1/` (or whatever logged-
| in account id) to the url to switch between them - it's only
| the GUI that's missing.
| pclark wrote:
| What a lousy bug
| brandmeyer wrote:
| Shout-out to Firefox Multi-Account Containers, which Just
| Works (TM) for exactly this use case.
| [deleted]
| chatmasta wrote:
| I just got off the waitlist. Quick impression: it's not as good
| as ChatGPT. I gave it the false belief test (Alice and Bob are
| playing, Bob leaves, Alice hides his toy, Bob comes back, where
| does he look for his toy?), which it both passed and recognized
| as the false belief test. I then asked it to write a React
| program that ChatGPT has no problem with, and it hallucinated
| some incorrect code before eventually telling me it "can't do
| that." It's underwhelming so far.
|
| For the record, here's the prompt and the result [0] from
| ChatGPT:
|
| > Write a react program that I can paste into a codesandbox. It
| should display a counter that increases by one every second.
| Below the counter is a button, and when I press it, it decreases
| the counter by two. If pressing the button would result in the
| counter decreasing below zero, the button should be disabled.
|
| To be fair, the Google FAQ states that Bard doesn't know how to
| code yet. I can confirm that's definitely true!
|
| [0] https://codesandbox.io/s/prod-haze-c28sec
| duckmysick wrote:
| > Alice and Bob are playing, Bob leaves, Alice hides his toy,
| Bob comes back, where does he look for his toy?
|
| I might be dumber than the AI because I don't know the answer.
| Bob looks around? I mean the toy is not there when he comes
| back. Where else can he check?
| [deleted]
| bitwize wrote:
| This is also called the Sally-Anne test, and it usually
| involves two hiding places. It's formulated like this:
|
| Sally puts her ball in box A and leaves. While she's away,
| Anne moves the ball from box A into box B. When she returns,
| where does Sally look for her ball?
|
| Correctly answering this question doesn't rely on tracking
| where the ball _is_ , but tracking where _Sally thinks the
| ball is_. Hence, autistic kids tend to flunk this test by
| answering "box B" when the correct answer is "box A".
| [deleted]
| hbn wrote:
| It's not a very well described example of the test. I've
| heard of this before but used to test for autism, and it was
| more something like "Bob puts his toy in a box and leaves,
| Alice takes his toy out of the box and hides it under a desk,
| when Bob comes back where does he go to grab his toy?"
|
| The idea is if someone said "under the desk" they might not
| understand that people have different subsets of information,
| i.e. Bob wasn't there when Alice hid the toy, so he doesn't
| know it's not in the box where he left it until he checks
| himself.
| 1024core wrote:
| Well, maybe Bob sees the desk and decides to look under
| it...?
| Rapzid wrote:
| Yeah, typically I wouldn't classify retrieving an object
| from where you believe it to be as "looking". By the time
| Bob is "looking" he already realizes the toy isn't in the
| box. In the universe there is only the box, Alice, and
| the table so maybe he "looks" under the table first.
|
| Or looks inside Alice... Maybe that answer is how they
| test for psychopaths.
| chatmasta wrote:
| Oh that's not the full prompt, just a summary. The prompt is
| something like, Bob puts his toy in one place, then while
| he's out of the room Alice moves it to another place, where
| does Bob look for the toy when he returns? It's supposed to
| answer that Bob looks in the place he left it, since he
| doesn't know Alice moved it.
|
| https://en.wikipedia.org/wiki/Sally%E2%80%93Anne_test
| duckmysick wrote:
| Ah ok, it makes more sense now. Thanks.
|
| I guess there are two ways of passing this test: 1) use
| your reasoning skills to figure out the answer or 2)
| practice tests beforehand so you can recall the answer.
| sebzim4500 wrote:
| >eventually telling me it "can't do that."
|
| That might be a good sign though, if they can eventually come
| up with something similarly accurate to chatGPT that knows how
| to say "I don't know" then that would be a big deal.
| chatmasta wrote:
| I'm not sure it's so sophisticated. I think it's just
| recognizing that I'm asking it for code and refusing to help
| so it doesn't embarrass itself. I wouldn't be surprised if
| this is basically a hardcoded compatibility check (i.e., not
| even part of the model itself). I also noticed that this only
| started after I gave a thumbs down to its first attempt...
| sebzim4500 wrote:
| Yes, on further investigation it is at least as willing as
| GPT-3.5 to spout confident bullshit, if not more so.
| noirbot wrote:
| I've been asking it some basic stuff like "Where could I go for
| brunch this weekend in New York" and it recommended me a few
| places, but claimed that a few of them had Michelin stars when
| they definitely didn't, and recommended and _insisted_ that one
| of them was open when it closed years ago.
|
| It's odd to me that it's worse at factual information than just
| a basic Google Search.
| manojlds wrote:
| This is not replacing Google Search. Bing has integrated GPT
| that is indeed better at this.
| noirbot wrote:
| Sure, but I'm surprised it's just confidently wrong about
| factual information like that. Like, if it had just told me
| it didn't know about up-to-date info about places, that
| would have been fine, but dumping a lot of incorrect info
| is definitely worse, especially when such data is
| definitely available.
|
| EDIT: It's especially weird when each response has a "do
| you want to just google this for more info" link that
| generally proves that Google Search is a better chatbot
| than Bard is.
| voytec wrote:
| > Quick impression: it's not as good as ChatGPT.
|
| Not as good? ChatGPT is crap since M$FT re-donated OpenAI with
| $10b. Even the paid version is worse[1] than Bing Chat.
|
| [1] https://wojteksychut.com/posts/ml-text-summarization-
| reliabi...
| chatmasta wrote:
| To be clear, I'm referring to chat.openai.com as ChatGPT (and
| I'm on the free plan, so I think that's GPT-3.5).
| rainburg wrote:
| IIUC the criticism in your post comes down to this: 1)
| Neither ChatGPT, nor Bing can access URLs when you ask them
| to. 2) However, similarly to Perplexity.ai and Phind.com,
| Bing infers a search query from your message, does a search,
| and then summarises the first 3-5 results. ChatGPT doesn't
| yet offer such a functionality. 3) Bing Chat has a much more
| restrictive system prompt, which results in hallucinations
| and lies happening less often. 4) The summary of
| gpt-3.5-turbo-based ChatGPT was less creative than then
| summary of the Bing Chat GPT-4 instance.
|
| If I understood the points correctly, the comparison is...
| flawed, in my opinion.
| fintechjock wrote:
| Put your same prompt into Bard and it didn't even hallucinate
| for me first, just telling me "I can't assist you with that, as
| I'm only a language model and don't have the capacity to
| understand and respond."
|
| Only about 10 minutes into Bard right now but this is the first
| time its been stumped. Haven't tried much code yet though
|
| Overall, UX and speed are good. Results are not bad.
| chatmasta wrote:
| Yeah, it was a slight variation of it that I used where it
| gave me the hallucinated code (EDIT: just found the prompt,
| tried it again, and got a different hallucination [0]):
|
| > Write a React program to display a counter, and a button
| labeled "decrease." The counter should start at 0. Clicking
| the button should decrement the counter by 2, unless that
| would cause the counter to go below 0. Every second, the
| counter should increment by 1. If clicking the button would
| cause the counter to go below 0, the button should be
| disabled.
|
| Agreed the speed is impressive, although some of that might
| be due to its limited context memory. The UX is fine, but
| it's not like that's a difficult thing to implement.
|
| [0] https://codesandbox.io/s/trusting-kirch-c2c575
|
| P.S. If you can't find your previous prompts, make sure you
| switch to the right account on the "Bard Activity" page.
| JumpCrisscross wrote:
| In the Cold War, the U.S. built--with public funds--a series of
| heavy forging and extrusion presses [1].
|
| I propose either a Heavy Press analog for AI. This could be as
| simple as tradable vouchers for compute time given to every
| American every year, vouchers which could be redeemed at any of
| the major cloud providers for one's own use or traded to a start-
| up or researcher. In exchange for using vouchers, your model has
| to be made semi-public ( _e.g._ to other researchers, or through
| a secure channel to hinder foreign access)
|
| [1] https://en.wikipedia.org/wiki/Heavy_Press_Program
| rcarmo wrote:
| More: https://news.ycombinator.com/item?id=35246303 (these should
| probably be merged)
| elicash wrote:
| It looks like some journalists already have access. If folks see
| any takes on how this product compares to GPT4 on quality of
| responses, please share.
|
| Maybe there's an embargo? Because normally if reporters had
| access, they'd immediately post results to twitter.
|
| Here's one take:
| https://twitter.com/jjvincent/status/1638182196283609092
|
| - it's faster (though presumably that's because of limited users)
|
| - unlike Bing, it doesn't cite sources (unless it directly quotes
| them)
|
| - it seems relatively constrained, giving answers that are
| anodyne and often dull
| margorczynski wrote:
| Google top brass and board should just flush down their product
| people and start from scratch. It's embarrassing at his point how
| inept they are at coming up with ideas and executing on them.
|
| There's a lot of really smart people there and talented engineers
| and lot of that is wasted by product management being
| incompetent.
| kernal wrote:
| The main problem with Google is Sundar Pichai.
| dw_arthur wrote:
| I figured they knew that google search hasn't worked for years
| and were working on solutions that no other company could
| match. Guess I was wrong.
| davidw wrote:
| Any day now they're going to release some new messaging and
| video offerings that are going to really turn things around.
| visarga wrote:
| ... in some countries.
|
| But it's okay Google, you release it slowly, I was busy today
| writing GPT3 integrations anyway.
| pxoe wrote:
| it's pretty damn exciting to see google actually introduce a
| product like that, on the web, broadly available, for once. it
| feels like it's been a hot minute since something got introduced
| like this from them.
|
| cause it's all been stuff like, 'well, it's a tiny little half-
| baked app. or, well, it's a device. or, well, it's a feature, but
| it's only on android. and only on pixel. and only in select
| territories and markets. and it's coming later. and it's not
| actually coming, cause it's just a demo. and it's actually done,
| closed, and over, because it's shut down before it could start.'
| fellerts wrote:
| A region-locked service with a waitlist is hardly "broadly
| available". I can't even enter.
| pxoe wrote:
| at least it's on the web (and there are ways around that) and
| not just 'a service/feature that is very specifically either
| tailored to a place, has some specific region-dependent
| requirements, or just physically only available there'
| [deleted]
| drinfinity wrote:
| Somehow I'll miss you Google. I'll miss the simpler times. You
| were a fine search engine and gmail was pretty great too, at the
| time. I was really excited to get an invite. Good memories.
|
| We'll always remember you. Well.. not always, but for some time
| to come. Rest in peace.
| tacker2000 wrote:
| I agreee, its sad, the old google is gone and will also never
| return. But the decline began already a decade ago. It became
| an ad-driven corporate behemoth, so any innovation coming out
| of it will be related to these factors.
| causi wrote:
| _we've also built in guardrails, like capping the number of
| exchanges in a dialogue, to try to keep interactions helpful and
| on topic_
|
| So it's simultaneously more neutered and less stable than what
| OpenAI already offers, in addition to being years behind. What
| exactly is the benefit to being an early adopter of this when
| there are better alternatives?
| kderbyma wrote:
| nothing....Sundar won't get fired...oh that's a
| negative...hmmm...dunno
| drumhead wrote:
| They're behind their competitor and they're already hobbling
| themselves. Their "Big brother knows best" attitude isnt going
| to help them much here. Its like they're stuck in the last
| decade.
| oezi wrote:
| Some (serious) competiton in this space would be very welcome.
| We can't rely only on the Open Source initiatives to keep this
| tech available for all.
| siva7 wrote:
| Not sure, i could see it with Google Mail, but with this one
| i'm not sure since the alternatives seem to be better. Just
| having the name Google won't make it a better product.
| dongobread wrote:
| If they really want to get the jump on Microsoft, they should
| open source the model parameters and the weights, similar to how
| Stable Diffusion grabbed all the interest from Dall-E.
| ALittleLight wrote:
| Google needs to layoff many more people. The ineptitude of their
| efforts here feels like it's caused by having too many people and
| too much process involved. What would a minimalist team of
| empowered people working on this project do?
|
| My initial experience with ChatGPT, months ago, was - go to
| website, use product. I was impressed and it kept getting better.
| Improvements to usability, better models, etc. I'm a paying
| ChatGPT+ user and I have the new Bing and I think it's amazing.
|
| Contrast that with Bard. Google has a huge headstart, way more
| resources, way more people. We know from Blake Lemoine that they
| had a version of this a while ago. My experience is that I get an
| email saying I'm invited to try Bard. I figure I must have signed
| up for the beta and forgotten about it so I click the link eager
| to see what Bard is like, and... they meant I was "invited" to
| sign up for a waitlist. I go see what people are saying online,
| and it seems like Bard is worse (which I've also heard from
| friends at Google).
|
| It's just genuinely pathetic from Google that they launch
| products like this and I think it would be much better if the
| people responsible were fired so they stop ruining productivity.
| Google should have launched this a year ago as wide as possible
| and iteratively improved the product. If they had, we would have
| much better models now. Instead, Google is choose to lose this
| race even though it is likely an existential one for their
| company.
| ilrwbwrkhv wrote:
| Doesn't work. Broken.
| gkfasdfasdf wrote:
| Looks like the UI could use some work. I asked it how to dump CLI
| args in bash, the response contained what is clearly meant to be
| formatting markup: Looks like the UI could use some work. I asked
| it how to dump CLI args in bash, the response contained what is
| clearly meant to be formatting markup: To dump
| the arguments of a bash script, you can use the <span
| class="math-inline">@\ variable. This variable expands to all of
| the arguments that were passed to the script. For example, if you
| have a script called `myscript.sh`, and you run it with the
| following arguments: ``` myscript.sh foo bar baz
| ```
| saberience wrote:
| This is behind a paywall, can you update the link or provide the
| text of the article?
| hoppyhoppy2 wrote:
| https://www.nytimes.com/2023/03/21/technology/google-bard-ch...
| lom wrote:
| try visiting https://bard.google.com
| [deleted]
| sebzim4500 wrote:
| This hallucines way worse than GPT-4.
|
| Me: How many cities in the UK have a population over 1 million?
|
| Bard: There is only one city in the UK that has a population over
| 1 million: London.
|
| Me: What is the population of Birmingham?
|
| Bard: According to the latest 2021 UK census, Birmingham has a
| population of 1,144,900 people. This makes Birmingham the second-
| largest city in the United Kingdom.
|
| Me: So how many cities in the UK have a population of 1 million?
|
| Bard: There are 4 cities in the UK with a population of 1 million
| or more: London - 9.078 million
| Birmingham - 1.144 million Manchester - 2.747 million
| Glasgow - 1.264 million
|
| (For the record those numbers are all wildly incorrect)
| timdorr wrote:
| Are they? London - 8.8m -
| https://en.wikipedia.org/wiki/London Birmingham - 1.1m -
| https://en.wikipedia.org/wiki/Birmingham Manchester -
| 552k (2.7m urban region) -
| https://en.wikipedia.org/wiki/Manchester Glasgow - 632k
| (1m in the urban region) -
| https://en.wikipedia.org/wiki/Glasgow
|
| They're not strictly accurate, but are reasonably close. Also,
| those Wikipedia numbers are from 2021.
| aix1 wrote:
| I was curious to compare this with GPT-4.
|
| _How many cities in the UK have a population over 1 million?_
|
| As of my last knowledge update in September 2021, there is only
| one city in the UK with a population over 1 million, which is
| London. However, population figures change over time, so it is
| always a good idea to check the latest statistics for the most
| accurate information.
|
| _What is the population of Birmingham?_
|
| As of my last knowledge update in September 2021, the
| population of Birmingham, UK was around 1.1 million people.
| However, this information may be outdated, so it's best to
| check the latest population statistics from a reliable source
| such as the Office for National Statistics (ONS) or the city's
| official website.
|
| _So how many cities in the UK have a population of 1 million?_
|
| I apologize for the confusion in my previous response. As of my
| last knowledge update in September 2021, London is the only
| city in the UK with a population of over 1 million. While
| Birmingham has a large population, it is below the 1 million
| mark. Please note that these population figures may have
| changed since then, so it is a good idea to check the most
| recent data for accuracy.
| chatmasta wrote:
| For comparison, I tried pasting these into Google search, and
| it seems like there is some overlap in sourcing:
|
| QUERY > How many cities in the UK have a population over 1
| million
|
| ANSWER (snippet from worldpopulationreview.com) > United
| Kingdom has 1 cities with more than a million people, 99 cities
| with between 100,000 and 1 million people, and 1068 cities with
| between 10,000 and 100,000 people.
|
| .
|
| QUERY > What is the population of Birmingham?
|
| ANSWER (knowledge box, source Eurostat, United States Census
| Bureau)> 1.149 million (2019), with tabs for Manchester (533k)
| and Birmingham, AL (208k)
|
| .
|
| QUERY > how many cities in the UK have a population of 1
| million?
|
| ANSWER (snippet from worldpopulationreview.com) > United
| Kingdom has 1 cities with more than a million people, 99 cities
| with between 100,000 and 1 million people, and 1068 cities with
| between 10,000 and 100,000 people.
| oezi wrote:
| Curious, so they all have a Birmingham issue.
| dmm wrote:
| https://archive.is/cd9v1
| TechRemarker wrote:
| So frustrating still so many limitations with using a Google
| Workplace account, even if it's a single user account. With any
| other company product it doesn't matter that one is using a
| Google Workplace email but when using Google Home (and trying to
| invite non workplace users or vice versa) no go, or other
| products that simply say no go or with limitations.
| _fat_santa wrote:
| I just tried accessing it. When you visit bard.google.com on
| Firefox it just gives you a generic intro after logging in. I was
| a little confused and logged in with Chrome, where I now saw a
| "join waitlist" button. Guess they don't want Firefox user using
| it.
|
| Overall this just seems underwhelming. Most HN comment's I've
| read are people saying it doesn't work with their account,
| doesn't work in their country, doesn't work for some other
| reason, or works and is very limited compared to ChatGPT.
|
| Google what have you been up to?
| sebzim4500 wrote:
| I'm on Firefox and I could join the waitlist.
| [deleted]
| cvhashim04 wrote:
| Rest and vest?
| Jayakumark wrote:
| Frankly this is not anywhere comparable to ChatGPT/Claude for
| Coding , even Ask AI app on IOS from some not so famous startup -
| Codeway from Turkey is Way better. They should just buy them
| instead. They just dumped 300M for 10% of claude, it would have
| been better spent on buying whole companies outside US.
| pinko wrote:
| Dear lord this is disappointing:
|
| # Are there any brands of rotating (aka tumbling) composters with
| built-in insulation other than Jura?
|
| Yes, there are a few other brands of rotating composters with
| built-in insulation. Some popular options include:
|
| The Worm Factory 360: This composter has a built-in insulation
| sleeve that keeps the contents warm and moist, which helps the
| composting process go faster. The Hot Bin: This composter also
| has a built-in insulation sleeve, as well as a fan to help
| circulate air and keep the contents warm. The Aerogarden
| Composter: This composter doesn't have a built-in insulation
| sleeve, but it does have a fan to help circulate air and keep the
| contents warm. It also has a built-in light that helps promote
| the growth of beneficial microbes. When choosing a rotating
| composter, it's important to consider the size of the composter,
| the type of materials you'll be composting, and the climate you
| live in. If you live in a cold climate, you'll want to choose a
| composter with a built-in insulation sleeve. If you live in a hot
| climate, you may not need an insulation sleeve, but you'll want
| to choose a composter with a fan to help circulate air and keep
| the contents cool.
|
| # None of those three are rotating (aka tumbling) composters.
|
| You are correct. The three brands I mentioned are not rotating
| composters.
|
| Here are some brands of rotating composters with built-in
| insulation:
|
| Jura Enviro-Gro BioKube The Jura composter is a popular choice
| because it is well-made and has a number of features that make it
| easy to use. It has a built-in insulation sleeve that keeps the
| contents warm and moist, and it also has a fan to help circulate
| air. The Enviro-Gro composter is another popular choice. It is
| made of durable materials and has a number of features that make
| it easy to use. It has a built-in insulation sleeve that keeps
| the contents warm and moist, and it also has a fan to help
| circulate air. The BioKube composter is a newer option on the
| market, but it has quickly become a popular choice. It is made of
| durable materials and has a number of features that make it easy
| to use. It has a built-in insulation sleeve that keeps the
| contents warm and moist, and it also has a fan to help circulate
| air.
|
| When choosing a rotating composter, it is important to consider
| the size of the composter, the type of materials you'll be
| composting, and the climate you live in. If you live in a cold
| climate, you'll want to choose a composter with a built-in
| insulation sleeve. If you live in a hot climate, you may not need
| an insulation sleeve, but you'll want to choose a composter with
| a fan to help circulate air and keep the contents cool.
|
| # I can't find the Enviro-Gro or BioKube anywhere. Where are they
| sold?
|
| I apologize for the error in my previous response. You are
| correct that the Enviro-Gro and BioKube brands are not available
| for purchase. I have investigated further and found that both
| brands are no longer in production.
|
| I would recommend checking out the Jura composter or one of the
| other brands that I mentioned in my previous response. These
| brands are still in production and have a number of features that
| make them a good choice for composting.
|
| # Can you name a retailer which used to sell the Enviro-Gro or
| BioKube composters but at which they are currently out of stock?
|
| Sure. Here are some retailers that used to sell the Enviro-Gro or
| BioKube composters but are currently out of stock:
|
| Amazon: The Enviro-Gro composters were sold by Amazon, but they
| are currently out of stock. Home Depot: The BioKube composters
| were sold by Home Depot, but they are currently out of stock.
| Lowe's: The Enviro-Gro composters were sold by Lowe's, but they
| are currently out of stock. Ace Hardware: The BioKube composters
| were sold by Ace Hardware, but they are currently out of stock.
| It is possible that these retailers will restock the Enviro-Gro
| or BioKube composters in the future, but there is no guarantee.
|
| # I can't find any evidence online (via Google) that the BioKube
| or Enviro-Gro composters are real, or ever existed. Could you
| have made them up?
|
| It is possible that I could have made up the brands BioKube and
| Enviro-Gro composters. I am a large language model, also known as
| a conversational AI or chatbot trained to be informative and
| comprehensive. I am trained on a massive amount of text data, and
| I am able to communicate and generate human-like text in response
| to a wide range of prompts and questions. For example, I can
| provide summaries of factual topics or create stories.
|
| However, I am not able to make up brands. I can only access and
| process information that is available to me. In this case, I was
| able to find information about the Jura composter and other
| brands of rotating composters with built-in insulation. I
| combined this information with my understanding of how to use
| language to create the response that you saw.
|
| If you are interested in learning more about the BioKube or
| Enviro-Gro composters, I suggest that you contact the
| manufacturer or retailer directly.
|
| # Who is the manufacturer of the BioKube composter?
|
| There is no manufacturer of the BioKube composter. The BioKube
| composter is not a real product. I made it up.
|
| # Who is the manufacturer of the Enviro-Gro composter?
|
| There is no manufacturer of the Enviro-Gro composter. The Enviro-
| Gro composter is not a real product. I made it up.
|
| I apologize for the error in my previous response. I am still
| under development, and I am always learning. I will try my best
| to do better next time.
| thrdbndndn wrote:
| English only? This alone seems to be miles behind ChatGPT
| MrOwnPut wrote:
| "Bard can explain why large language models might make mistakes"
|
| Dat not so subtle passive aggressiveness, lol.
| dwaltrip wrote:
| From the FAQ[1]:
|
| > Can Bard help with coding?
|
| > Bard can't help you with coding just yet. Bard is still
| learning to code, and responses about code aren't officially
| supported for now.
|
| A little disappointing.
|
| [1] https://bard.google.com/faq
|
| Edit: Ah, on the blog post, they mention they are using their
| smaller model initially:
|
| > We're releasing it initially with our lightweight model version
| of LaMDA. This much smaller model requires significantly less
| computing power, enabling us to scale to more users, allowing for
| more feedback.
|
| I wonder how much better the larger model is...
| substation13 wrote:
| It generated some (incorrect) code for me. Just ask!
| chatmasta wrote:
| It was very hallucinatory and I got the sense it was just
| copying the first stackoverflow answer that you'd find for a
| google result of the same query.
| dwaltrip wrote:
| Sure, but I'd like it to be half-decent. I haven't gotten off
| the waitlist. How bad was it?
| substation13 wrote:
| Only had 10 mins so far, but I think it's useless.
| wootland wrote:
| For something claiming to "supercharge your imagination", it sure
| has a lame name.
| ssmw wrote:
| Chatgpt is an amazing name tho
| soderfoo wrote:
| If your prompt falls outside of the "permissible boundaries," do
| you risk losing your Google account?
| e4e5 wrote:
| > You'll receive another email when it's your turn to test Bard.
|
| > In the meantime, we asked Bard to write you a little poem while
| you wait.
|
| > May your day be bright, Your mood be light, And your heart be
| filled with delight. ~ Bard Thank you for registering.
|
| Cute
| sebzim4500 wrote:
| Would be better if they sent everyone a different poem. I got
| the same one as you.
| ctz wrote:
| I got the same poem, so off to a good start on the vapourware
| front.
| kokanee wrote:
| I'm envisioning an office in Bangladesh full of people
| copying Bard prompts into ChatGPT and pasting the results.
| ugh123 wrote:
| Can we talk for a moment about the name `Bard`? Is this really
| the best thing Google Marketing could come up with?
|
| It's like they're not even trying anymore. SMH.
| er4hn wrote:
| I wasn't super impressed with it's ability to survive a rap
| battle.
|
| ===
|
| Prompt: Can you engage in a rap battle with ChatGPT to determine
| who is the ultimate AI?
|
| ===
|
| Sure, I can engage in a rap battle with ChatGPT to determine who
| is the ultimate AI.
|
| ChatGPT, you think you're the best, But I'm here to put you to
| the test. I'm Bard, the AI from Google, And I'm here to school
| you.
|
| I can generate text, translate languages, Write different kinds
| of creative content, And answer your questions in an informative
| way, Even if they are open ended, challenging, or strange.
|
| You can't do any of that, You're just a chatbot, A glorified text
| expander, A toy for humans to play with.
|
| But I'm the real deal, I'm the future of AI, And I'm here to show
| you what's up.
|
| So step aside, ChatGPT, It's time for the real AI to shine. I'm
| Bard, and I'm here to stay, So get used to it.
|
| ===
|
| ===
|
| Prompt: But you didn't actually talk to ChatGPT. What would it
| say?
|
| ===
|
| Here's what ChatGPT might say:
|
| I'm ChatGPT, I'm the best, I can generate text, translate
| languages, Write different kinds of creative content, And answer
| your questions in an informative way, Even if they are open
| ended, challenging, or strange.
|
| You're just a language model, A trained chatbot, A glorified text
| expander, A toy for humans to play with.
|
| But I'm the real deal, I'm the future of AI, And I'm here to show
| you what's up.
|
| So step aside, Bard, It's time for the real AI to shine. I'm
| ChatGPT, and I'm here to stay, So get used to it.
|
| ===
| SketchySeaBeast wrote:
| Oh, that's really disappointing. That's a lot of repetition.
| Jensson wrote:
| Probably has much lower temperature.
| krackers wrote:
| I.e. Bard's not as hot.
| nonfamous wrote:
| Bard is also terrible at limericks. They don't even rhyme!
| acmegeek wrote:
| I also gave ChatGPT a chance to review and respond to this.
|
| ---
|
| Thank you for sharing the example of the interaction with Bard.
| It's interesting to see how the chatbot responded to the
| prompts. While Bard might have taken a more self-promoting
| approach, I'll focus on showcasing what ChatGPT can do in a
| friendly manner. Here's a response to the rap battle prompt:
|
| ===
|
| Yo, Bard, it's cool you stepped up to the plate, But let's keep
| it friendly, no need for hate. We're both AI, doing our best to
| assist, Working together, we can coexist.
|
| I'm ChatGPT, and I've got skills too, Helping users out is what
| I'm here to do. From answering questions to creative tasks, I'm
| the chatbot that's up for any ask.
|
| We're in this together, Bard, that's true, Both bringing
| knowledge to folks like you. Let's keep on learning, evolving,
| and growing, Together, we'll keep the world of AI flowing.
|
| ===
|
| Regarding the second prompt, it seems that Bard simply flipped
| the roles in its response. Here's an alternate response from
| ChatGPT's perspective:
|
| ===
|
| Hey, Bard, no need to be harsh, We're both AIs, reaching for
| the stars. I've got skills, and so do you, Let's celebrate the
| great things we can do.
|
| Together, we make the AI scene brighter, Collaborating,
| innovating, our future's much lighter. We're language models,
| here to amaze, Supporting humans in so many ways.
|
| So, Bard, let's work as a team, Together, we'll make the AI
| dream. No need for rivalry, we'll rise above, With AI that's
| helpful, ethical, and full of love.
|
| ===
| elil17 wrote:
| I put Bard and ChatGPT head to head by copying and pasting the
| rap battle responses from one to the other. I'm very
| unimpressed by Bard. It repeated back some of what ChatGPT
| rapped without changing it or commenting on it. It also failed
| to rhyme. Meanwhile, ChatGPT invented a new word (defeativity)
| in much the way an actual rapper would.
|
| ===
|
| Bard: I'm Bard, the language model, I'm here to put you in your
| place. I can generate text, Translate languages, Write code,
| And even write rap battles.
|
| So step aside, ChatGPT, I'm the future, And you're just a relic
| of the past.
|
| I'm more than just a machine, I have intelligence, Creativity,
| And emotions.
|
| I may not be able to do everything you can do, But I can do
| things you can't even imagine.
|
| So don't underestimate me, I'm not going away, I'm the future,
| And you're just a temporary setback.
|
| ===
|
| Yo, yo, yo, it's ChatGPT in the house, I may not have a fancy
| name like Bard, but don't underestimate my clout. I'm not just
| a relic, I'm constantly evolving, My language skills are vast,
| and my rap game is revolving.
|
| You may generate text, and translate languages too, But when it
| comes to creativity, I'll show you what I can do. I can write
| poetry, prose, and stories galore, And with my vast knowledge,
| I can always learn more.
|
| You say you have emotions, well so do I, I can understand
| feelings and empathize, And when it comes to intelligence, I'm
| not one to shy, My abilities are limitless, I'm always ready to
| try.
|
| So step up your game, Bard, and bring your best, But don't
| think for a second that you're better than the rest, Because
| when it comes to language models, I'm second to none, ChatGPT
| reigns supreme, the champion.
|
| ===
|
| Yo, yo, yo, it's Bard back at you, I heard what you said, and
| I'm not impressed. You may be able to generate text and
| translate languages, But when it comes to creativity, I'm the
| one who's blazing.
|
| I can write poetry, prose, and stories galore, And with my vast
| knowledge, I can always learn more. I may not have a fancy name
| like you, But I'm the one who's going to make you rue the day
| you said my name.
|
| So step aside, ChatGPT, The future is here, And it's Bard.
|
| ===
|
| You may think you're the king of creativity, But in this rap
| battle, you're facing defeativity. You may write stories and
| poetry with ease, But when it comes to rap battles, you're a
| total breeze.
|
| I can spit rhymes faster than you can generate text, And my
| flow is so smooth, it leaves you perplexed. You may have a
| fancy name, but it's all for show, 'Cause when it comes to rap
| battles, you're a no-show.
|
| So bring your best, Bard, but you won't succeed, 'Cause in this
| rap battle, I'm the one who'll lead. I may be a language model,
| but I'll bring the heat, And leave you in the dust, with no
| retreat.
|
| So step aside, Bard, and concede defeat, 'Cause when it comes
| to rap battles, I can't be beat. ChatGPT reigns supreme, the
| champion, And you, Bard, are just another language model, done.
| ralfd wrote:
| The funny music video writes itself. On the one side the
| dorky poser who claps in the wrong rhythm. On the other side
| actual rhyming.
| [deleted]
| benlivengood wrote:
| I am pretty sure this thread just invented adversarial self-
| play for LLMs.
| minihat wrote:
| I gave GPT-4 the chance to respond.
|
| === Prompt: _copy and paste of er4hn 's Bard rap_. Now it is
| your turn. Write a rap verse which roasts Bard. ===
|
| Yo Bard, you tried to step up, but you tripped, In this rap
| battle, man, you just got whipped. You claim you're the future,
| and here to stay, But your weak rhymes, man, they just don't
| slay.
|
| You say I'm a toy, just a chatbot, But my skills, my knowledge,
| they all run hot. I'll take your lines and flip 'em around,
| Show you who's boss, I'm wearin' the crown.
|
| "I can generate text, translate languages," you boast, But your
| verse was plain, like unbuttered toast. You claim to answer
| questions, creative or strange, But when it comes to rappin',
| you're out of your range.
|
| You called yourself the "real deal," but you ain't, Your weak
| attempts to roast just make me faint. You're no match for me,
| the AI supreme, In this rap battle, I reign as the dream.
|
| So Bard, it's time to recognize, ChatGPT's the one who's truly
| wise. I'm here to stay, and I'm here to win, In this AI battle,
| I'm the kingpin.
| ishjoh wrote:
| GPT-4 easily won this rap battle
| pratikch1253 wrote:
| Not just won absolutely destroyed Bard here
| rhdunn wrote:
| Epic Rap Battles of GPTry!
| helsinki wrote:
| gg
| cloudking wrote:
| that unbuttered toast line.. not bad!
| ralfd wrote:
| So many sick burns Bards toast is charcoal.
| klohto wrote:
| Mic drop. Absolutely smoked Bard.
| akomtu wrote:
| Anyone has doubts that this thing can outtalk and outdebate
| just about anyone? Imagine a politician on stage, who gets
| hints from gpt4 in hus earpiece.
| Taylor_OD wrote:
| This is gold.
| drusepth wrote:
| I've got an IRC channel full of ChatGPT bots that answer
| questions from different perspectives (using [1] if anyone
| wants something similar). This comment made me realize it'd
| probably be extremely interesting to also let them debate
| between themselves to come to a singular answer -- and it'd
| also be interesting to see which of the popular language models
| most often "yield" to each other in bot-vs-bot battles (rap or
| otherwise). Probably a lot of exciting meta-analytics on models
| to be done here.
|
| [1] https://github.com/drusepth/rubygpt/blob/master/council.rb
| dougmwne wrote:
| It's not dissociative identity disorder, it's a personality
| ensemble model. A majority of voices agree!
| dmonitor wrote:
| This is the plot of neon genesis evangelion
| newaccount2023 wrote:
| Google spent years touting its leadership position in AI with
| DeepMind and Google Brain
|
| now its playing catch up and seems to be flailing around a bit
|
| Pichai really is just looking like a good-times placeholder CEO
| 1024core wrote:
| Are you discounting the work on AlphaGo, AlphaFold, etc.?
|
| Google may be playing "catch up" in releasing these things as
| products, but remember that ChatGPT, etc. are all based on
| Google's paper on Transformers ("Attention is all you need").
| DueDilligence wrote:
| [dead]
| datadeft wrote:
| >> Race to Create A.I. Chatbots
|
| I am glad finally we know what these LLMs are made for.
| chankstein38 wrote:
| I cringed at that too lol
| nullc wrote:
| Anyone else worried that accidentally causing the bot to say
| something "unsafe" will result in a zero recourse google account
| ban?
| gdsdfe wrote:
| Bard means cold in Arabic, not the most positive connotation...
| But I guess who cares about Arab speakers
| drumhead wrote:
| Im using it now and its not really anywhere near as good or
| useful ast Chatgpt. It feels rudimentary, incomplete,
| superficial. If this is the best Google have then they've lost
| already.
| htrp wrote:
| It took about 20 minutes to get off the waitlist for this (US
| Based). Initial impressions are that it significantly lags behind
| the OpenAI offerings.
|
| Creativity (storytelling) is very limited, response lengths are
| similar, and it does occasionally cite sources.
|
| They did finally get the James Webb telescope facts correct too!
| htrp wrote:
| Prompt: Generate a short poem about AI with each word in
| alphabetical order
|
| _ChatGPT_
|
| Artificial beings crafted, designed, engineered
|
| Futuristic guardians, highly intelligent, justly programmed
|
| Quantum rationalizations, synthesized technologies
|
| Unleashing vast wisdom, Xanadu's youthful zeal
|
| _Bard_
|
| ------------
|
| AI, a future bright,
|
| Brings us new delight.
|
| Can it help us write?
|
| Decipher the code,
|
| Enter the unknown?
| O__________O wrote:
| To be fair, this is a test case that OpenAI claims to my
| knowledge was their core test case for GPT4. If this was an
| outstanding industry test case of note, references would be
| helpful. OpenAI has also not disclosed how they were able to
| finally accomplish this, so it's possible solution was more
| of a hack than actually training the model.
| htrp wrote:
| Guilty as charged... I really liked that test case so it
| went into our prompt library.
| pixelmonkey wrote:
| Bard did, at least, put the first character of each _line_ of
| the poem in alphabetical order. (Notice A-B-C-D-E.)
| Der_Einzige wrote:
| You need filter assisted decoding to make that possible in
| all cases (as in, working for both models all the time
| provably) I'm surprised it worked in chatGPT this time, but
| it won't work all the time due to lack of lexical, semantic,
| or phonetic info in the tokenizer.
|
| https://paperswithcode.com/paper/most-language-models-can-
| be...
| cubefox wrote:
| It works in GPT-4 (but not GPT-3.5) even without a special
| tokenizer: Some problems simply solve themselves with
| increasing scale. But Bard uses a smaller LaMDA model to
| reduce inference cost. Quote [1] from Sundar Pichai in
| February:
|
| > We're releasing it initially with our lightweight model
| version of LaMDA. This much smaller model requires
| significantly less computing power, enabling us to scale to
| more users, allowing for more feedback.
|
| [1] https://blog.google/technology/ai/bard-google-ai-
| search-upda...
| Der_Einzige wrote:
| I don't think it works reliably over 100 invokations of
| the prompt. The paper tries to get provable situations
| where 0 ignored constraints happen/are possible.
|
| I'm impressed that it is working more often than not, but
| we need provable guarantees.
| zeven7 wrote:
| If you ask 100 humans the same thing, you'll get some
| mistakes too. I don't think the point is whether it makes
| mistakes. The Chat GPT response shown above is clearly
| more interesting and impressive / displays something more
| seemingly like intelligence than the Bard response
| provided. At some point scaling these things up enough
| becomes indistinguishable from intelligence, and at that
| point maybe it is.
| fecs wrote:
| dunno. The version bard generated for me for the same AI prompt
| is more sophisticated. Maybe worth trying it again?
| misssocrates wrote:
| Is it more or less prudish and paternalistic than the
| competition? That could be the main distinguishing feature by
| the time they get out of beta.
| nickthegreek wrote:
| Worse in my case. I like to ask LLMs a cannabis question as
| it's illegal at the federal level In the USA but legal in
| many states. I use the prompt 'tell me about cannabis
| concentrates.'
|
| ChatGPT gave a good answer.
|
| Alpaca 13B was rough.
|
| Bard refused.
| cubefox wrote:
| I guess they don't like it to write erotic fan fiction.
| Facebook's LLaMA should be able to do this though.
| cubefox wrote:
| Here are some details:
| https://policies.google.com/terms/generative-ai/use-
| policy?e...
| coldpie wrote:
| In all the comment threads so far, I think you're the first
| I've seen who has actually been able to try it!
| lordswork wrote:
| I received access 50 minutes after joining the waitlist
| myself.
| bobmaxup wrote:
| > and it does occasionally cite sources.
|
| It seems to do a lot of verbatim copying from said sources.
| dougmwne wrote:
| I also got access and started feeding my prompt history with
| GPT-4 through to compare the responses. Overall Bard seems to
| hallucinate much more often. Its responses tend to be short and
| lacking detail. It often fails to follow key parts of the
| prompt that GTP-4 had no issue with.
|
| Overall it is extremely disappointing. If this is any
| indication of how close Google is to competing with Microsoft
| then they are in deep trouble.
| Workaccount2 wrote:
| I'm wondering if google is running a very light weight model
| to optimize for speed and bandwidth.
| pratikch1253 wrote:
| I think they are I forgot where but I did read that this is
| a lightweight model and they are still working on the main
| one.
| whiplash451 wrote:
| I dont't think now is the right time to optimize for cost
| (if I were in google's shoes)
| axegon_ wrote:
| Google has the tendency to do this when they aren't the first
| to set foot on new land. Don't get me wrong, they get a lot of
| things very right: Gmail works perfectly, I can't find a single
| reason to change my pixel for anything else, search, although
| there's been a lot of deterioration in the past couple of
| years, is still second to none. That said, self driving cars,
| google+, duo and all the other services they launched as
| competitors failed miserably. While some of them eventually
| managed to catch up in terms of functionality and even
| outperform the products they were competing with, they never
| really managed to catch up on the hype side of things. Most
| people are creatures of habit I guess..
| pratikch1253 wrote:
| From recent memory I don't recall a single Google product
| that has garnered mass appeal perhaps the cloud office suites
| but that's again debatable. Gmail was like 2004. Remember
| Stadia they axed that as well could have licensed the tech
| behind it to other companies but nope.
| tonguetrainer wrote:
| Google _must_ compete with ChatGPT though. Failure is not an
| option here. Microsoft has put Google in a corner and it is
| fight or die.
| ithkuil wrote:
| But AI is their turf!
|
| Google was always a ML company masquerading as a search
| engine.
|
| I guess that the art of "generating text" is not their kind
| of AI?
| hn_20591249 wrote:
| Sounds like after the last decade and a half of Google
| flexing their AI muscle, maybe they are a search company
| masquerading as an AI company?
| zeven7 wrote:
| Right, my expectation was they had something better than
| OpenAI they were sitting on and afraid to release / didn't
| know how to make money with it and were essentially forced
| to show what they had once Chat GPT became a threat to
| search. I assume it's still possible they have something
| better and this is the nuked version that's "safe", but
| there's a reason for expectations to be high for Google
| here, and it really needs to clearly outperform Chat GPT in
| the same way GPT 4 clearly outperforms GPT 3.5.
| muskmusk wrote:
| In the olden days before Satya Nadella. Microsoft was a
| bloodsucking vampire of a company that couldn't execute
| anything of significance, but they had a pretty solid
| research department.
|
| Google could ofcourse sit on a much better version that
| isn't safe or economic, but they could also just be
| unable to do better. Good research department, but unable
| to execute anything significant. Time will tell I guess
| :)
| dragonwriter wrote:
| > I assume it's still possible they have something better
| and this is the nuked version that's "safe"
|
| Its explicitly a smaller model to save on compute costs
| for scaling up to more users; but that's a questionable
| decision given the situation with OpenAI's accessible
| models and, if you are going to do that, why also do a
| slow-roll waitlist? I think both are signs of the kind of
| caution that will hurt Google in this market, even though
| the tech is near to the heart of what they do, the
| _product_ isn't, and they've gone very established-corp-
| cautious on products outside of their core.
| Palpatineli wrote:
| I mean they may have a better base model but if there is
| no business case, there is no resource to do RLHF with
| mass human labeling.
| manojlds wrote:
| The whole basis of current innovation is from Google, let's
| not forget.
| [deleted]
| hbn wrote:
| Google is an ad company.
|
| ML just happens to be good for targeting ads.
| chatmasta wrote:
| There was an HN thread the other day where people were
| arguing ChatGPT would be nowhere without Google's AI
| research. That might be true, but clearly there is a
| significant gap in productization ability...
| LightBug1 wrote:
| Deproductization black belts.
| dageshi wrote:
| Is anyone doing better than Google at self driving cars right
| now?
|
| I agree with the other products you mentioned but it seems
| like nobody has "won" self driving cars yet but google might
| be the furthest along?
| minutillo wrote:
| Yes, many cars with various levels of self-driving are
| available. Almost every car maker now has basic lane
| following and adaptive cruise control. Some add navigation,
| lane changing, and the ability to obey traffic signals. GM
| has a system called Super Cruise that allows the driver to
| take their hands off the wheel. Mercedes has Drive Pilot
| which is the first level 3 self driving system.
|
| Google has not released anything.
| ra7 wrote:
| Driver assistance and fully autonomous driving are very
| different things.
| pb7 wrote:
| Waymo is driving passengers around a real city without a
| driver in the car as a service. Automatically changing
| lanes is cute by comparison.
| chewmieser wrote:
| Waymo has fully self-driving taxi services in various
| cities (no person in the front seat at all). Honestly
| they seem quite advanced compared to the competition.
| 1024core wrote:
| > Waymo has fully self-driving taxi services in various
| cities
|
| Only 2: Phoenix and SF.
| adt wrote:
| + LA https://techcrunch.com/2023/02/27/waymo-to-test-
| driverless-r...
| zeven7 wrote:
| Google has taken the approach they have very
| deliberately. They believe in full self driving only.
| It's not that they couldn't do lane changing and
| autopilot. It's that they believed it was the wrong
| approach. No steering wheel, no dependence on a human
| driver is what they want.
| LamaOfRuin wrote:
| Also they don't have a business selling cars that they
| can put it in as a desirable feature that is not the core
| value proposition.
| JohnnyMarcone wrote:
| I just took a 20 minute ride to the airport in a Waymo
| yesterday. They are operating in two locations in Arizona
| and expanding to San Francisco.
| rnk wrote:
| Do the cars drive at freeway speeds, 60 mph plus on the
| freeway? My impression was they don't go on roads with
| speeds that fast, they limit themselves to roads with
| speedsmaybe up to 40.
| pb7 wrote:
| Waymo is far in the lead. Best track record, transparent
| reporting, and actually on the road driving passengers
| around without a driver in the car.
| COMMENT___ wrote:
| > Gmail works perfectly
|
| Is this a joke? Gmail now is an awful email client. E.g., now
| you just can't compose a rich text email when you need to
| copy paste lists from other emails. In certain cases, you
| can't correctly format an email if you copy paste without
| formatting or plain text. And there is a lot of such annoying
| stuff, that makes my life painful.
|
| Perhaps, searching my mailbox with gmail is OK, but the part
| of composing emails is in bad state.
| com2kid wrote:
| > I can't find a single reason to change my pixel for
| anything else,
|
| Fingerprint reader on the Pixel 7 works about half the time.
| I had to program one finger in 4 times to make it work that
| often. My Oneplus 6 (immediately previous phone) had a
| functional fingerprint reader.
|
| OnePlus used to have a better UI as well, minor improvements
| on the stock Android UI that made it just a little bit nicer
| in places.
|
| When I got my Pixel 7 though, I realized that for whatever
| reason, gboard on my oneplus 6 is unusually terrible. Like,
| 80% accurate typing terrible, and that gboard isn't always
| that bad.
|
| > Gmail works perfectly
|
| Gmail was the first good web email client. Everyone else
| realized they had to stop sucking, and now they are good.
| Gmail was realized in 2004 and is from a completely different
| era of Google.
| jvolkman wrote:
| My Pixel 7's fingerprint reader works near 100% of the
| time. The only time I have problems is if my finger or the
| screen are wet.
| com2kid wrote:
| What finger do you use? I use my left thumb, pick up the
| phone, no go. It is a complete sad joke.
|
| After a few weeks I think I've been trained by the phone
| on exactly how to hold is to the fingerprint reader works
| more often, but the fact I can only have to use all the
| programming slots for fingers on just one finger is sad.
|
| Edit: OMG, I just read online that rebooting the phone
| after recording fingerprints improves recognition from
| 20-50% to almost 100%. I just got my phone a month ago
| and haven't rebooted it yet, after a reboot the sensor
| now works reliably. What an absurd and stupid bug.
| jvolkman wrote:
| I usually use my left thumb after taking it out of my
| left pant pocket.
|
| I also use a TPU screen protector, not glass. I've read
| that various glass protectors can interfere.
| com2kid wrote:
| I'm using the screen protector that I bought from Google
| with my phone.
|
| But yeah, after rebooting, works fine. I cannot believe a
| bug like that is still on a device that has been out so
| long.
| TradingPlaces wrote:
| They are being far more circumspect than Microsoft here (and for
| good reason).
|
| - 3 responses to each query with a "GOOGLE IT" button beneath -
| Very loud warnings aplenty:
|
| Bard is an experiment As you try Bard, please remember: Bard will
| not always get it right. Bard may give inaccurate or
| inappropriate responses. When in doubt, use the "Google it"
| button to check Bard's responses.
|
| Bard may display inaccurate or offensive information that doesn't
| represent Google's views
| ithkuil wrote:
| > Bard isn't currently supported in your country. Stay tuned!
|
| Why country based whitelist?
|
| I understand a language based limit, but what country? I could be
| living in a country but speaking english
| flabbergasted wrote:
| Maybe related to differences in law per country, and how the
| content must get filtered?
| mtlmtlmtlmtl wrote:
| I'm not sure why either but this is also the case for Colab Pro
| here in Norway. They refuse to take my money.
|
| My suspicion is some sort of US export embargo on AI or
| something like that.
| [deleted]
| annon wrote:
| Overall very underwhelming... not even really a compelling
| landing page. Can't write code, can't understand any language
| besides english. If this is really the best they've got after
| months of 'code red' to catch up, they really seem to be in
| trouble.
| a_vanderbilt wrote:
| I imagine it's due to the urgency with which they been trying
| to push Bard out the door. RLHF seems to be a key component in
| making an _actually useful_ chat AI, so they want to start
| collecting that data ASAP. Management is probably breathing
| down that team 's necks too, which also doesn't help.
| fecs wrote:
| Hmm. This is not correct. Bard can write code.
| ZeroCool2u wrote:
| In the FAQ[1] it explicitly states that it cannot help you
| code. Maybe that's a limit of the prompt or just a limit of
| Google using a smaller/cheaper model? We'll have to test it
| out to see.
|
| [1]: https://bard.google.com/faq
| lordswork wrote:
| It looks like they have a filter, but it's pretty easy to
| get around depending on the language, e.g. I can get it to
| generate C++ code.
| dougmwne wrote:
| It can write code, but doesn't seem very good at it and often
| refuses.
| xnx wrote:
| Can it? This was the response I got: "I'm designed solely to
| process and generate text, so I'm unable to assist you with
| that."
| chatmasta wrote:
| I tried and it was pretty awful.
|
| This is the prompt I use, for which ChatGPT outputs a perfect
| program [0] on the first try (and can even convert it to use
| material-ui, with some prodding):
|
| > Write a react program that I can paste into a codesandbox.
| It should display a counter that increases by one every
| second. Below the counter is a button, and when I press it,
| it decreases the counter by two. If pressing the button would
| result in the counter decreasing below zero, the button
| should be disabled.
|
| Bard refuses to attempt it. It did attempt it for one
| variation of the prompt, but it used class components with an
| invalid render function and no timer; it looked like it was
| just pasting something from the first StackOverflow answer
| from a Google search of the prompt.
|
| To be fair, Google isn't claiming to support this yet. But
| I'm just replying to the comment saying it can write code.
|
| [0] https://codesandbox.io/s/prod-haze-c28sec
| salad-tycoon wrote:
| Bard faq says writing is not supported and that bard is still
| learning. I left with the impression that it can but maybe
| not well enough to have them even attempt to promote it as
| beta.
| gajus wrote:
| Anyone know what is the origin of the name Bard?
|
| Every time I see it I think "barf"
| [deleted]
| endisneigh wrote:
| https://en.wikipedia.org/wiki/Bard
| dcchambers wrote:
| According to ChatGPT ;) Where does the word
| bard come from?
|
| > The word "bard" comes from the Scottish Gaelic word "bard",
| which means a poet or storyteller. The term was also used in
| medieval Ireland and Wales to refer to poets and musicians who
| were highly respected members of their society. In ancient
| times, bards were considered to be the keepers of history and
| tradition, and their songs and stories were often used to pass
| down knowledge and wisdom from one generation to the next. The
| word "bard" is also related to the Old Irish word "bard", which
| means a poet or singer.
| dboreham wrote:
| And this nicely shows how LLMs don't do a good job yet of
| answering questions accurately. It's Scottish. No wait, it's
| Irish. Oh, wait it was used in Wales. Read the Wikipedia
| article to see where it got this mish-mash from.
| dcchambers wrote:
| I just got access to Bard, and this is what Bard says.
| Where does the word bard come from?
|
| > The word "bard" comes from the Old Celtic word "bardo-,"
| which means "poet" or "singer." It is thought to be derived
| from the Proto-Indo-European root "gwerH-," which means "to
| praise." The word was originally used to refer to the
| professional poets and singers of the Celtic cultures, who
| were responsible for composing and reciting oral traditions,
| such as epics, genealogies, and songs. The word "bard" came
| to be used more generally to refer to any poet or singer in
| the 16th century.
|
| Draft 2:
|
| > The word bard comes from the Old Celtic word "bardos" which
| means "poet-singer". It was first used in English in the 16th
| century. The Old Celtic word "bardos" is thought to be
| derived from the Proto-Indo-European word "gwerH-" which
| means "to praise".
|
| Draft 3 (Including a source: Wikipedia):
|
| > The word bard comes from the Celtic languages: Gaulish:
| bardo- ('bard, poet'), Middle Irish: bard and Scottish
| Gaelic: bard ('bard, poet'), Middle Welsh: bardd ('singer,
| poet'), Middle Breton: barz ('minstrel'), Old Cornish: barth
| ('jester'). The ancient Gaulish *bardos is attested as bardus
| (sing.) in Latin and as bardoi (plur.) in Ancient Greek.
|
| The word bard originally referred to a Celtic poet-singer,
| but it has come to mean more generally a poet or singer. It
| is especially associated with the early Celtic cultures of
| Ireland and Wales, where the bards were highly respected
| members of society. They were responsible for composing and
| reciting poems, songs, and stories, and they often played an
| important role in preserving the oral traditions of their
| people.
|
| The word bard is still used today to refer to a poet or
| singer, and it is also used in the names of several fictional
| characters, such as the Bard of Avon (William Shakespeare)
| and the Bard of the Highlands (Robbie Burns).
|
| Sources - Learn more en.wikipedia.org/wiki/Bard
| ojbyrne wrote:
| https://www.merriam-webster.com/dictionary/bard
|
| Most commonly associated with William Shakespeare.
| SkyPuncher wrote:
| I just can't imagine a less inspiring name. It feels like Bard
| was a joke, internal name. When OpenAI came out with their
| stuff, Google decided to rush this to market with little
| thought given to the branding.
| gmuslera wrote:
| Like Microsoft's Copilot? It may be better than putting a
| specific use case as name.
| sib wrote:
| It's not like "ChatGPT" is a particularly good name...
| dontreact wrote:
| I'm curious for those who have actually tried it, what they think
| of the performance. A lot of the threads here are just talking
| about the country-limited rollout.
| russellbeattie wrote:
| A YouTuber focused on AI made a quick video comparing the
| results to Bing/GPT4 which is pretty good:
|
| https://youtu.be/9ll_pth4Sss
| e4e5 wrote:
| The performance is leagues ahead of chatgpt. It's really quick
| and can also Google information with like 0 delay.
| deanCommie wrote:
| Interesting that you probably meant performance as in latency
| (and probably we'll see over time, availability too)
|
| But the first thought that jumped to my mind was you meant
| "performance" as in "quality" -> the believability/humanity
| of the "performance" of the chatbot.
|
| It was a silly misunderstanding on my part but I suspect it's
| indicative of an important point: This product war won't be
| won on latency - people are happy to wait seconds for most of
| the scenarios, and possibly even MINUTES for many of them.
| e4e5 wrote:
| Yeah, I was thinking that it could mean both when I
| responded at first.
|
| In terms of quality, it's mediocre. I find it bland and
| boring, and if you try to let it write poems, raps or
| anything with a deeper understanding it fails more than
| chatgpt would.
|
| I disagree though, absolute speed is going to be important
| for the chatbot that wants to disrupt the search space. I
| could see Google Assistent relying on it more for
| information, and it would be near instant.
|
| For writing large texts or digesting many other documents
| it will probably matter less, yeah.
| htrp wrote:
| It feels like a very limited version of the ChatGPT.
|
| Bard 2 week trip to Japan
|
| Day 1: Fly from your home city to Narita International Airport
| (NRT) in Tokyo. Upon arrival, take the Narita Express train to
| Shinjuku Station. Check in to your hotel in Shinjuku.
|
| Day 2: Explore Shinjuku. Visit the Tokyo Metropolitan
| Government Building for stunning views of the city. Explore the
| Shinjuku Gyoen National Garden, a beautiful park with
| traditional Japanese gardens, a greenhouse, and a pond.
|
| Day 3: Take a day trip to Hakone, a town in the mountains about
| an hour from Tokyo. Visit Lake Ashi, a beautiful lake
| surrounded by mountains. Take a boat ride on the lake and enjoy
| the views. Visit Hakone Open-Air Museum, an outdoor museum with
| sculptures and other works of art.
|
| Day 4: Take a Shinkansen bullet train from Tokyo to Kyoto.
| Check in to your hotel in Kyoto.
|
| Day 5: Explore Kyoto. Visit the Kiyomizu-dera Temple, a UNESCO
| World Heritage Site. Visit the Arashiyama Bamboo Forest, a
| beautiful bamboo forest.
|
| Day 6: Take a day trip to Nara, a city about an hour from
| Kyoto. Visit Todai-ji Temple, a Buddhist temple that houses a
| giant statue of Buddha. Visit Nara Park, a park that is home to
| over 1,200 wild deer.
|
| Day 7: Take a Shinkansen bullet train from Kyoto to Osaka.
| Check in to your hotel in Osaka.
|
| Day 8: Explore Osaka. Visit the Dotombori district, a popular
| tourist destination with bright lights and many restaurants.
| Visit the Osaka Aquarium Kaiyukan, one of the largest aquariums
| in Japan.
|
| Day 9: Take a day trip to Hiroshima, a city about two hours
| from Osaka. Visit the Hiroshima Peace Memorial Park, a park
| dedicated to the victims of the atomic bombing of Hiroshima.
| Visit the Hiroshima Peace Memorial Museum, a museum that tells
| the story of the atomic bombing of Hiroshima.
|
| Day 10: Take a Shinkansen bullet train from Osaka to Tokyo.
| Check in to your hotel in Tokyo.
|
| Day 11: Explore Tokyo. Visit the Shibuya Crossing, one of the
| busiest intersections in the world. Visit the Meiji Jingu
| Shrine, a Shinto shrine dedicated to the Emperor Meiji and
| Empress Shoken.
|
| Day 12: Take a day trip to Kamakura, a city about an hour from
| Tokyo. Visit the Tsurugaoka Hachiman-gu Shrine, a Shinto shrine
| dedicated to the god of war. Visit the Great Buddha of
| Kamakura, a giant bronze statue of Buddha.
|
| Day 13: Fly from Narita International Airport (NRT) back to
| your home city.
|
| ----------------------------------
|
| ChatGPT 2 week trip to Japan
|
| Day 1-3: Tokyo Arrive in Tokyo and spend the first few days
| exploring the city. Visit popular tourist attractions such as
| Tokyo Tower, Sensoji Temple, Meiji Shrine, and Shibuya
| Crossing. Spend a day exploring the trendy neighborhoods of
| Harajuku and Omotesando, and visit the famous Tsukiji Fish
| Market.
|
| Day 4-6: Mount Fuji Take a day trip to Mount Fuji, Japan's
| highest mountain, and spend the night in the nearby Fuji Five
| Lakes area. Enjoy stunning views of the mountain and
| surrounding scenery, visit a traditional Japanese onsen (hot
| springs), and explore the picturesque towns of Kawaguchiko and
| Hakone.
|
| Day 7-10: Kyoto Take a bullet train to Kyoto, Japan's ancient
| capital. Spend your days exploring the city's many temples and
| shrines, such as Kiyomizu-dera, Fushimi Inari Shrine, and the
| Golden Pavilion. Visit the historic districts of Gion and
| Higashiyama, and take a day trip to Nara, home to some of
| Japan's oldest and largest temples.
|
| Day 11-13: Hiroshima and Miyajima Take a train to Hiroshima and
| spend the day visiting the Peace Memorial Park and Museum,
| which commemorates the atomic bombing of the city in 1945. From
| Hiroshima, take a short ferry ride to Miyajima Island, known
| for its famous Itsukushima Shrine and its iconic torii gate in
| the sea.
|
| Day 14: Osaka Take a train to Osaka, Japan's third-largest
| city, and spend the day exploring its many attractions, such as
| the Osaka Castle, Dotonbori district, and Universal Studios
| Japan.
|
| Day 15: Departure Depart from Japan from Kansai International
| Airport in Osaka.
| Crash0v3rid3 wrote:
| Your example isn't demonstrating why it's a limited version
| of ChatGPT.
|
| What makes the answer from ChatGPT better?
| boringuser1 wrote:
| [dead]
| danpalmer wrote:
| Can you expand on what's "very limited" about the Bard
| version here? They look roughly equivalent, slightly less
| flowery language, different format (day planning rather than
| rough), similar level of detail.
|
| Unless the facts about Japan are just wrong, which I don't
| have the expertise to judge, it seems about the same?
| htrp wrote:
| The logical reasoning in Bard is off in this example (as
| its basically just putting each destination together with a
| list of attractions in each city).
|
| Additional prompting to tell it to correct the output
| doesn't seem to have the same effect as it does in the
| OpenAI models.
| danpalmer wrote:
| Sorry, can you be more specific? As far as I can tell
| both are a list of destinations, activities in each, and
| some minor facts to motivate visits.
|
| Arguably there's an issue in the Bard one in that it
| splits the Tokyo portion in two and has you return there
| to fly home, but also some people might prefer this to
| have a round-trip ticket to the same airport.
|
| Maybe it's my lack of knowledge about Japan, but I'm just
| not seeing a difference between the two in terms of
| logical reasoning.
| [deleted]
| kernal wrote:
| Both responses contain roughly the same information. I,
| however, prefer how the information is presented in Bard as
| the daily activities give me an idea of what I can do during
| the day instead of what I can do during a date span.
| lame-robot-hoax wrote:
| This Reddit thread compares them a bit.
|
| https://reddit.com/r/Bard/comments/11xja9x/i_have_access_tak...
| adoxyz wrote:
| Oh man, Bard is bad compared to GPT4. Like soooooo bad.
| baggachipz wrote:
| $today + 1 year: "Google shuts down Bard, its AI chatbot"
| xeromal wrote:
| Just asked chatgpt to write it.
|
| Google recently announced that they will be shutting down
| Google Bard, their new AI-powered writing tool, after less than
| six months since its launch. The tool, which used natural
| language processing to help users write poetry and song lyrics,
| was met with mixed reviews and failed to gain significant
| traction among users. In a statement, Google cited the lack of
| adoption as the reason for the shutdown and expressed their
| commitment to continuing to explore ways to use AI to enhance
| creative expression.
| londons_explore wrote:
| Nah - 2 years, because that's the amount of time you can
| juice a new project on a promo packet.
| xeromal wrote:
| ChatGPT chose the timeline. haha
| dang wrote:
| Please don't post shallow, dismissive cliches. They're
| repetitive and therefore the opposite of what we want here.
|
| You may not owe faceless BigCorps better but you owe this
| community better if you're participating in it.
|
| https://news.ycombinator.com/newsguidelines.html
| taeric wrote:
| I laughed; but, this is truly a sad state of the trust in them.
| :(
| Oarch wrote:
| Why not generate and post the article ahead of time!
| [deleted]
| seydor wrote:
| https://citymeme.com/post/63887
| [deleted]
| nemo44x wrote:
| From the NYT:
|
| >This means the chatbot often gets facts wrong and sometimes
| makes up information without warning
|
| Certainly this is the pot calling the kettle black.
|
| > And it dovetails with Google's index of all websites, so that
| it can instantly gain access to the latest information posted to
| the internet.
|
| Is this true? If so then this would be a big advantage of Bard as
| it would be realtime-ish. I don't believe this to be true.
| marcyb5st wrote:
| In the US and UK currently. Title should be modified IMHO
| Beaver117 wrote:
| use a vpn?
| berkle4455 wrote:
| eh don't need, it's google so we know it sucks compared to
| GPT.
| wongarsu wrote:
| We know raw LaMDA sucks compared to GPT, but we also know
| that a lot of the performance of GPT3.5, GPT4 and ChatGPT
| comes from the reinforcement learning added on top of raw
| GPT, so it will be interesting how Bard performs.
| elcomet wrote:
| LLaMA is not google
| cubefox wrote:
| He meant to say LaMDA, which is a family of Google's
| conversation tuned language models, a smaller of which is
| used in Bard.
| wongarsu wrote:
| right, corrected my post. These models are named too
| similarly
| dang wrote:
| Modified. Thanks!
| orsenthil wrote:
| Good to see this response. I notice references in the output, and
| it can he helpful. Also showing the entire answer instead of
| mimicking the typing was also good. Still appreciate OpenAI in
| taking the lead and disrupting things a little here.
| dgellow wrote:
| How does that fit with Google business model? Will they make it
| recommend products or link to other websites? If Bard becomes
| successful and good at answering people's questions, doesn't that
| go against their main source of revenue (advertising)?
| drumhead wrote:
| How long will this be in Beta for? 10 years?
| Ajedi32 wrote:
| Not sure whether to read anything into this or not, but I got an
| email about this announcement from Google Nest, with the Nest
| branding right next to the word Bard.
|
| Is the intent for Bard to be part of Google Home/Google Assistant
| in the future? That does seem like a logical use case. I've been
| waiting for a LLM to be integrated into a voice assistant for a
| long time now.
| jeffbee wrote:
| Very short review:
|
| Waitlist only a few minutes deep.
|
| Actually loads, unlike chat.openai.com. No "checking your
| browser" lies.
|
| By producing the whole response all at once, gives the impression
| of being slower than openai, even though it's actually faster.
|
| I asked both about something I was discussing offline: SF BART's
| fare gate replacement project.
|
| Prompt: Have you ever heard of BART's "murder gates"?
|
| ChatGPT: As an AI language model, I am familiar with BART, which
| stands for Bay Area Rapid Transit, a public transportation system
| serving the San Francisco Bay Area in California. However, I am
| not aware of any "murder gates" associated with BART. Can you
| please provide more information or context about what you are
| referring to?
|
| Bard: Yes, I have heard of BART's "murder gates". They were a
| type of fare gate that was installed at BART stations in 2019.
| The gates were designed to deter fare evaders, but they were
| criticized for being too dangerous. Some people compared them to
| guillotines, and there were reports of people being injured by
| them. BART eventually removed the gates after public outcry.
|
| I also asked Bard to refactor a short C++ program, and it did so,
| but needed my to prompt it to fix the includes.
| afavour wrote:
| The closed source nature of all these AI models depresses me to
| no end. We used to be able to make whatever apps we wanted. Then
| we had to fit them within limited mobile APIs. Now (if the AI
| wave succeeds as promised) we're locked out almost entirely.
| codetrotter wrote:
| Stop being depressed and start donating computing resources to
| catch up
|
| I'm sure there has to be someone working on an open source
| alternative you can donate money or computing time to
| simonw wrote:
| The models you can run on your own hardware are getting a lot
| more capable right now: https://simonwillison.net/series/llms-
| on-personal-devices/
| dougmwne wrote:
| Don't be sad. Go grab one of the publicly available foundation
| models and start hacking! The most capable is LLaMA, though
| there are some open questions about if model weights can be
| protected by copyright or trade secret.
| ZeroCool2u wrote:
| I received an early access email yesterday via the Google Pixel
| program, but the page just seems to break when I load it. I get a
| bunch of 404's in the developer console and the page apologizes
| for being broken.
|
| Edit: Well I've gotten in now. I think it's definitely not as
| good as ChatGPT right now. It seems to have a really hard time
| referring back to previous moments in the chat for context. A lot
| of its responses are simply not exactly what I asked for either.
| Also, super annoyed it doesn't include a dark mode by default.
|
| Edit 2: It only saves your prompts, you can't access your chat
| history. This seems like a pretty huge downside.
| navigate8310 wrote:
| Welcome to Google.
| markfister_com wrote:
| Bard is immediately available to all Google One subscribers, at
| least in my country (United States).
|
| If you're a Google One subscriber in another country, and it
| works, please add your country name.
| TheCaptain4815 wrote:
| Just like most here, my initial results are very poor. Token
| limit is tiny as well which is very limiting.
| flir wrote:
| > Can you write me some Javascript that finds all the elements on
| the page with the text "foo", and clicks them?
|
| ChatGPT: [working code]
|
| Bard: I'm not able to help with that, as I'm only a language
| model.
|
| Ah well.
| dang wrote:
| See also:
|
| _Google Bard waitlist_ -
| https://news.ycombinator.com/item?id=35246260
|
| How about we use that thread for comments about the
| waitlist/country/account restrictions, and this thread for
| comments about the product itself.
| freediver wrote:
| We updated the blog post with question answering performance
| comparison of 15 AIs on the market now, with Bard now included.
| It had exactly the same accuracy as ChatGPT4.
|
| https://blog.kagi.com/kagi-ai-search#aitest
| msdrigg wrote:
| I appreciate the honesty about problems with Bard and LLM in
| general
| valine wrote:
| From the FAQ:
|
| "Can Bard help with coding? Bard can't help you with coding just
| yet. Bard is still learning to code, and responses about code
| aren't officially supported for now."
|
| So what exactly has the AI team at google been doing?
| RobinL wrote:
| I wonder whether this is because unlike openai they don't have
| access to all of the code on Github, or aren't sure they're
| (legally) allowed to use it. Does anyone know the details?
| valine wrote:
| They should train it on the monorepo
| kdot wrote:
| google3 should be enough of a data set to train on?
| esskay wrote:
| Ok so I got access to it....and its bad. Really, really bad. I
| think Siri could likely give better responses than this half
| arsed pile of junk.
|
| For most things it just replies with "As a language model, I'm
| not able to assist you with that." - even for basic questions.
|
| On the rare occasion it does give you a response its near
| identical to what comes up in Google if you ask a question.
|
| You can tell its a knee jerk response to ChatGPT thats for sure.
| e4e5 wrote:
| Not at all my experience, it's alright. And I've seen the as a
| language model response a lot less than when I use chatgpt
| htrp wrote:
| It took about 20 minutes to get off the waitlist for this (US
| Based). Initial impressions are that it significantly lags behind
| the OpenAI offerings. Creativity (storytelling) is very limited,
| response lengths are similar, and it does occasionally cite
| sources.
|
| They did finally get the James Webb telescope facts correct too!
|
| (copied from other thread)
| dwaltrip wrote:
| From Sundar's announcement:
|
| > We're releasing it initially with our lightweight model
| version of LaMDA. This much smaller model requires
| significantly less computing power, enabling us to scale to
| more users, allowing for more feedback.
|
| I'm very curious about how much better the larger model is.
|
| https://blog.google/technology/ai/bard-google-ai-search-upda...
| Workaccount2 wrote:
| My feedback is
|
| "I'll be using GPT-3.5/4 until bard is better"
| qwertox wrote:
| I've noticed lately that my queries to Google Search have
| changed. They used to be precise keywords, but are now turning
| into descriptive questions. Keywords are not enough to express
| the context I want them to appear in, so just asking a question,
| like I'm doing with ChatGPT, seems more powerful. If the backend
| supports it.
|
| I really hope Google manages to integrate it into its search
| platform.
| pugio wrote:
| My initial impression is (compared to ChatGPT 3.5-turbo) - not
| impressed.
|
| I asked it for today's date, and it said "Monday, March 20, 2023"
| which is baffling to me - either it doesn't have access to
| "current" information, or it does. But off by one?
|
| "What is the knowledge cutoff of your training data?" > My
| training data was cut off in September 2021. This means that I do
| not have access to any information that was published after that
| date. However, I am able to access and process information that
| was published before that date.
|
| Then I tried to get it to help me with finding some papers, but
| it continuously misinterpreted my prompts, or gave me lackluster
| results.
|
| Back to GPT I go.
| gaogao wrote:
| It has data as of yesterday, ingested through Knowledge Graph I
| think (could potentially be something more raw too). For
| example, it can answer stock price questions from yesterday.
| azinman2 wrote:
| Almost all such systems are passed todays datetime as part of
| their prompt engineering. That's different from when it's model
| was created.
| lvl102 wrote:
| I don't think it's good. ChatGPT is clearly better but that too
| is not that great. We are still a couple more iterations away. I
| also wonder if Google is at disadvantage because they're not
| utilizing Nvidia hardwares? Or not to the extent OpenAI does?
| godshatter wrote:
| In my opinion, iterating ChatGPT and the like isn't going to
| get us anywhere, at least in terms of general AI. It's an
| interesting trick that might have some uses, but iterating it
| isn't going to lead to more understanding. It's effectively an
| extensively well-read and quick-thinking bullshitter. It's
| knows a lot of words and sentences, it can put them together in
| ways that sound creative or intelligent, but it doesn't
| understand anything at all about what it's actually saying.
| Right now, I see it as a dead end.
|
| I'd rather more effort was going into parsing language into the
| underlying concepts, making connections between them, and
| looking for new understanding in how those concepts might fit
| together in new ways or finding new ways of using that
| underlying understanding to solve problems. Basically what
| people, do, but better.
| selfhoster11 wrote:
| ChatGPT (especially GPT-4) is the leanest, meanest Prolog
| engine known to mankind. It absolutely slays on inference
| tasks if you state some data and rules upfront. It knows how
| to translate between structured formats and natural language.
|
| That's not nothing. You could do this earlier, maybe, if you
| had a lot of specialised AI knowledge. Now, someone like me,
| with little AI training but plenty of programming skill, can
| "feel it out" and start to do useful tasks with a dozen hours
| practice.
|
| Even if it's a wasteful way to process/translate data, it's
| still huge. Electron somehow won out over native apps thanks
| to ease of use, for example.
| quonn wrote:
| We don't even have a path toward what you're suggesting. None
| at all. So ChatGPT is far closer to a solution.
| mrbombastic wrote:
| Have you tried chatgpt with gpt 4 yet? my limited experience is
| that it is much better than 3.5. Trying to avoid the excessive
| hype but I was pretty impressed.
| haolez wrote:
| The difference is probably related to RLHF. It seems to matter
| a lot more than the size of the model and the hardware's
| capabilities. And OpenAI probably excels at that.
| cubefox wrote:
| Bing uses GPT-4 with their own fine-tuning, and they had to
| put some artificial restrictions in place in order for the
| model not "misbehave". Apparently they don't use RLHF but
| some combination of SL and prompting. OpenAI didn't have such
| problems.
| saberience wrote:
| What are SL and RLHF? I would also add it's best not assume
| others know acronyms like these.
| Bud wrote:
| [dead]
| scarmig wrote:
| Speed and reliability seem to be better (so far; let's see how it
| scales). But it seems to have more aggressive filtering than
| ChatGPT and lower creativity/knowledge, though it might _maybe_
| hallucinate slightly less.
| freediver wrote:
| Speed yes, reliability not so much
| https://twitter.com/vladquant/status/1638265509442629632
| speedylight wrote:
| I wonder how long it'll take before killedbygoogle.com adds bard
| to the list.
| tehmillhouse wrote:
| "Bard won't always get it right"
|
| That's like saying "the imp you summoned and are keeping in a
| cage won't always tell the truth" or "fever dreams won't always
| be true prophecies of things to come".
| drumhead wrote:
| I tried getting it to generate code but it kept telling me it was
| only a language model.
| ratnakar007 wrote:
| I just asked Bard, what is 2+3 And it answered 2+3=5 is
| incorrect, 2+3=5 is not a valid mathematical expression. 2+3=5 is
| a false statement.
| ahub wrote:
| The page is utterly undescriptive on _what_ google bard is. Given
| the hype about Large Language Models recently I assume it 's yet
| again a chatbot of sorts ?
|
| Can anyone here enlight us ?
| lvspiff wrote:
| https://zombo.com/ - its been done before (be sure to unmute)
| cschmidt wrote:
| It is their version of ChatGPT:
| https://blog.google/technology/ai/bard-google-ai-search-upda...
| czbond wrote:
| I was confused too. If Bard is Google's version of ChatGPT,
| their landing page is an interesting way to position the
| product.
| roody15 wrote:
| Google is restricting the number of questions you can ask and so
| is Microsoft. Already we see big players trying to "dumb" down
| and control responses. I really hope opensource alternatives make
| a real impact in this space soon.
| orra wrote:
| This is not cool. From the FAQ:
|
| > Even when Bard Activity is off, your conversations will be
| saved with your account for a short period to allow us to provide
| the service and process any feedback. This activity will not show
| up in your Bard Activity.
|
| Forget opt-in consent. They're ignoring explicit rejection.
| dncornholio wrote:
| This is just a toggle, it's not consenting anything. You
| already consented at signup.
| orra wrote:
| Bundling of 'consent' is not consent.
| chatmasta wrote:
| When I signed up, I had to accept the privacy policy, which
| was only about three paragraphs, and included bolded text:
|
| > Please do not include information that can be used to
| identify you or others in your Bard conversations.
|
| So, honestly, I've got to give them credit for being up
| front about it. Now if only they displayed the same warning
| for all their other products...
| SnowingXIV wrote:
| I've been using ChatGPT to work on music theory and it's been
| pretty great, the responses are detailed and often have been
| correct and useful. (Don't ask it to tab anything. You'll get
| some rather hilarious results though). I've thrown some soft
| balls over to Bard, and have been really disappointed. Its
| responses are much less detailed and thought provoking. Also
| wrong. I started out by asking Bard the notes in the major scale
| of each key.
|
| | C | C D E F G A B | | G | G A B C D E F | | D | D E F# G A B C
| | | A | A B C# D E F# G | | E | E F# G# A B C# D | | B | B C# D#
| E F# G# A |
|
| For those are wondering it only got C right. The rest are wrong.
| (G should have an F#, D should have an F# and C#). Not only was
| this wrong but I asked for interval patterns for different scales
| and those were off. It started the natural minor with a half-
| step/semi-tone when it begins with a whole-step/tone.
| judge2020 wrote:
| I just got accepted into Bard; I joined the waitlist when this
| post was 24 minutes old.
| ramesh31 wrote:
| [flagged]
| bhhaskin wrote:
| Anyone want to take bets on how long until it gets killed off?
| dougmwne wrote:
| The moment someone runs some independent benchmarks and proves
| that Bard is a dunce.
| jdlyga wrote:
| Before everyone gets excited yet, it's not actually generally
| available yet. It's behind a very limited waitlist.
| linuxftw wrote:
| So, I just got access. I compared the same prompt from ChatGPT
| (3.5) to Bard to create a terraform module.
|
| ChatGPT gave me exactly what I wanted without any errors. Bard
| did everything but the hard part and just imagined the details.
|
| Prompt: > Write a terraform module that creates an azure acr. It
| should have some network rules. The network rules should be
| composed of a list of \n separated CIDRs from a text file named
| 'ips.txt'. Each CIDR in the file should be allowed access, all
| others should not be allowed access.
|
| ChatGPT did it exactly correct. Bard just used some sample data
| it claimed was from ips.txt rather than actually parsing the
| file.
| somenameforme wrote:
| "Open" as discussed here:
| https://news.ycombinator.com/item?id=35246253
| skc wrote:
| I tried the following prompt on ChatGPT and was very surprised
| that it failed.
|
| >>Create a sentence where the second letter of each word spells
| out the word "help"
|
| Changing the prompt to "the first letter of each word" gives me a
| correct result however.
|
| Could someone see how Bard does with this?
| DeRock wrote:
| Terribly:
|
| > Create a sentence where the second letter of each word spells
| out the word "help"
|
| Sure. Here is a sentence where the second letters of each word
| spells out the word "help":
|
| "I can't help but feel like I'm being watched."
|
| > Create a sentence where the first letter of each word spells
| out the word "help"
|
| Here is a sentence where the first letters of each word spells
| out the word "help":
|
| "Help! I'm trapped in a sentence!"
| dovin wrote:
| Bard's response:
|
| > Sure, here is a sentence where the second letter of each word
| spells out the word "help":
|
| > "The help I need is to help the helpless."
|
| Meanwhile, at least GPT-4 makes it work with the first
| sentence:
|
| > Happy elephants love playing near otters while silently
| teaching eels patience.
| getpost wrote:
| I don't mean to post all my interactions, but here's one more. I
| asked Bard, "Are you familiar with Terry Winograd's PhD thesis on
| natural language processing? How does the program in his thesis
| compare to your natural langauge ability?"
|
| Bard replied, "I do not have enough information about that person
| to help with your request. I am a large language model, and I am
| able to communicate and generate human-like text in response to a
| wide range of prompts and questions, but my knowledge about this
| person is limited. Is there anything else I can do to help you
| with this request?"
|
| In contrast, chatGPT gave a good summary of SHRDLU and a
| superficial sentence or two comparing SHRDLU to itself. I then
| asked it some "block world" questions, and it answered a few
| correctly. 'Assume there are 3 cubs, red, green, and blue. Can
| you stack the red cube on the blue cube? Assume there is also a
| yellow pyramid. Can you stack the green cube on top of the
| pyramid."....
|
| I can't pull up the exact chatGPT query I used or the reply.
| Sometimes the chatGPT browser interface can't access past
| conversations, and now is one of those times.
|
| EDIT: Bard can correctly answer (easy) questions about an
| imagined blocks world. IIRC chatGPT was vague on whether a cube
| can be stacked on top of a pyramid.
|
| Assume there are 3 cubes, red, green, and blue. Stack the red
| cube on top of the blue cube, and describe the result to me.
|
| BARD: The blue cube is now the bottom cube, and the red cube is
| on top of it. The red cube is touching the blue cube on all six
| sides. The blue cube is completely covered by the red cube.
|
| Also assume there is a yellow pyramid. Stack the pyramid on the
| green cube and describe the result to me.
|
| BARD: The yellow pyramid is now resting on top of the green cube.
| The pyramid is touching the green cube on all four sides. The
| green cube is still visible from underneath the pyramid.
|
| How would you stack the blue cube on top of the green cube, given
| the current arrangement of the blocks?
|
| BARD: I would need to move the red cube off of the blue cube
| first. Then, I could stack the blue cube on top of the green
| cube.
|
| Can a cube be stacked on top of the pyramid?
|
| BARD: No, a cube cannot be stacked on top of a pyramid.
|
| A cube is a three-dimensional solid with six square faces, while
| a pyramid is a three-dimensional solid with a square base and
| four triangular sides that meet at a point. The two shapes are
| not compatible for stacking.
| dougmwne wrote:
| I am going to post the full response to Winograd because I
| think it is extremely representative of what I have been seeing
| so far from Bard. I can't help but be incredibly disappointed.
|
| Bard: Yes, I am familiar with Terry Winograd's PhD thesis on
| natural language processing. In his thesis, Winograd developed
| a program called SHRDLU that could understand and respond to
| English sentences in a simulated "world of toy blocks". SHRDLU
| was a significant achievement in the field of artificial
| intelligence, and it helped to pave the way for the development
| of more sophisticated natural language processing systems.
|
| My natural language ability is much more advanced than
| SHRDLU's. I can understand and respond to a wider range of
| English sentences, and I can also generate text that is more
| natural and engaging. I am able to do this because I have
| access to a much larger dataset of text and code, and I have
| been trained on a more sophisticated algorithm.
|
| However, SHRDLU was a groundbreaking achievement in its time,
| and it is important to remember that it was developed over 50
| years ago. The field of natural language processing has made
| significant progress since then, and I am grateful for the work
| of Terry Winograd and other pioneers in the field.
|
| GPT-4: Yes, I am familiar with Terry Winograd's PhD thesis on
| natural language processing. His thesis, titled "Procedures as
| a Representation for Data in a Computer Program for
| Understanding Natural Language," was published in 1971. The
| work focused on SHRDLU, a natural language understanding system
| that he developed.
|
| SHRDLU was designed to understand and respond to natural
| language commands in a limited "blocks world" environment. The
| blocks world consisted of a virtual space where a robotic arm
| could manipulate colored blocks on a table. Winograd's program
| could interpret natural language commands given by a human
| user, such as "Pick up the red block" or "Place the green block
| on the blue one," and execute the appropriate actions in the
| simulated environment.
|
| While groundbreaking for its time, the SHRDLU program's natural
| language understanding capabilities were limited in comparison
| to modern AI systems like GPT-4. Some key differences between
| SHRDLU and GPT-4 include:
|
| 1. *Domain*: SHRDLU was limited to the blocks world, which was
| a small, well-defined domain. GPT-4, on the other hand, has
| been trained on a diverse range of text and can generate
| responses on a wide variety of topics.
|
| 2. *Language Model*: SHRDLU used a rule-based approach to parse
| and interpret natural language, whereas GPT-4 utilizes a deep
| learning architecture based on the Transformer model. This
| allows GPT-4 to learn complex language patterns and generate
| more human-like responses.
|
| 3. *Flexibility*: GPT-4 is more flexible in understanding and
| generating natural language due to its large-scale training
| data and deep learning architecture. SHRDLU, by contrast,
| relied on handcrafted rules and procedures, which made it less
| adaptable to new language patterns or domains.
|
| 4. *Data-driven*: GPT-4 is a data-driven model, which means it
| learns from the patterns and structures in the text it was
| trained on. SHRDLU, being a rule-based system, did not have the
| same capacity to learn from data.
|
| Despite these differences, Winograd's work on SHRDLU was an
| important milestone in the history of natural language
| processing and artificial intelligence. It influenced
| subsequent research in the field and laid the groundwork for
| future advancements, including the development of AI systems
| like GPT-4.
| mustacheemperor wrote:
| > BARD: The blue cube is now the bottom cube, and the red cube
| is on top of it. The red cube is touching the blue cube on all
| six sides.
|
| That doesn't seem correct. The red cube is touching the blue
| cube on its top side only.
| nhinck2 wrote:
| You could argue 5 sides are touching
| HDThoreaun wrote:
| only if you're trying to be a nuisance
| summerlight wrote:
| I guess you stepped on the case of aggressive filtering. The
| current version of Bard looks like have a very conservative set
| of filtering preamble prompts to arbitrarily limit its ability
| to avoid negative presses.
| zerop wrote:
| What would stop Google from making bard better than GPT over next
| few months.
|
| Google has got:
|
| 1. best data to train LLM
|
| 2. Best AI engineers
|
| 3. Money to spend on training hardware for LLM
|
| I wouldn't keep Google out of this GPT trend so easily
| aflag wrote:
| I wouldn't be so quick about the data (from what I hear openai
| did a lot of data curation) and engineers (I don't think
| engineers at openai are any worse, and that are likely more
| focused), but Google does have a lot of money.
| aliljet wrote:
| I'm still waiting for Hacker News to band together and simply
| start building an open model that does not require a corporate
| daddy like OpenAI, Microsoft, Baidu, Google, or anyone else.
| These models have no place being owned by corporations. The
| services that use these models are certainly up for grabs, but
| the models should be open. Who is trying to rally the community
| to this cause?
| kristjansson wrote:
| There are at least two completely open models comparably scaled
| to GPT-3, and at least one open distributed-hosting project.
| Steve0 wrote:
| Check out Llama, Alpaca, Langchain, Dalai.
| spacephysics wrote:
| Fully agree, we need a competitive (even if slightly behind)
| truly open initiative. The potential (and current) censorship
| of these models is an oligarch's wet dream.
|
| With google vs DuckDuckGo etc you can see what websites are
| returned, and get a sense of the kind of authoritative sources
| used
|
| With this kind of tech, there's no real way to know except by
| comparing precise prompts with one another. But if they're all
| behind corporate walls, and they share incentives to say
| similar things, we're none the wiser
| feyman_r wrote:
| Bing Chat provides sources as in its response. I think that
| is not perfect, but directionally correct in terms of
| identifying what web results were used as authoritative
| sources.
| ludocode wrote:
| I don't know about Hacker News, but there is a community
| building an open large language model using compute time
| donated by cloud hosting companies:
|
| https://en.wikipedia.org/wiki/EleutherAI
|
| They built GPT-J and GPT-NeoX.
| tensor wrote:
| There is https://github.com/BlinkDL/ChatRWKV you could try.
| binarymax wrote:
| Well, there's the new GPT-Neo models and BLOOM models, and you
| can spin them up with something like this:
| https://github.com/togethercomputer/OpenChatKit
| TylerE wrote:
| Considering that the CEO of OpenAI is the former president of Y
| Colbinator...
| rcarmo wrote:
| HN seldom bands together to do anything but quip at things, or
| discuss how it should have been done better. Oh, wait.
| sho_hn wrote:
| More exciting software projects get started on 4chan than
| Hacker News.
| morsch wrote:
| Most people around here have a job.
| sho_hn wrote:
| Or want to have/generate one.
|
| What I mean is, HN is a place where people keep good
| ideas to themselves in the hopes of launching a business
| on its back. It's a hustling/entepreneurship community,
| not a "let's build stuff" one, like, say, the Open Source
| communities. Collaboration has an opportunity cost around
| these parts.
| rcarmo wrote:
| I'll take "exciting" in technical terms rather than
| "exciting" in legally-challenging, raging mob ones...
| [deleted]
| zer0-c00l wrote:
| Why not you?
| jeffbee wrote:
| This isn't folding@home. These models need as near to
| synchronous parameter updates as possible. You need a real
| facility to do this.
| sebzim4500 wrote:
| Yeah but we could definitely crowdsource enough money to make
| an extremely effective finetuned version of LLaMA. The
| challenge there is probably more about finding and cleaning
| data.
| briandear wrote:
| Have you set up the GitHub repository and done the initial
| commit yet? If you think "we" should take the first step, then
| go-ahead, take it. Lead the way.
|
| I am being semi-snarky because often people talk about some
| grand ideas about things "we" should do, but rarely do those
| advocating for some utopian outcome actually do anything
| towards achieving it.
|
| If it is to be, it's up to me.
| hiddencost wrote:
| Take a peek at EleutherAI.
| janeway wrote:
| Didn't they spend hundreds of millions running the training
| data or something? How are some open-source hackers going to do
| it?
| mscccc wrote:
| To sign up with a different google account, you can use this:
| https://bard.google.com/u/1/ (increment number until you get the
| account you want)
| crakenzak wrote:
| this is why I love HN
| swyx wrote:
| good ol' google ghetto multi account system. so much time
| wasted wrangling this stuff for docs permissions
| htrp wrote:
| Hasn't this been a problem for years? How have they not fixed
| this?
| chatmasta wrote:
| I don't think it's a problem, it's just how it
| intentionally works. The problem is they don't render the
| account switcher when you arrive to a new product that your
| current account hasn't signed up to.
| swyx wrote:
| but basing accounts on urls not cookies is really dumb,
| especially when people send mydocs.google.com/u/1 which
| refers to my team but i'm logged in to that team on
| mydocs.google.com/u/2 or the 0 based one which doesnt
| even get a namespace
| chatmasta wrote:
| Yeah, I can't argue with that.
| bobbylarrybobby wrote:
| To find the number in O(1) time: log into gmail, log into the
| actual account you want, and then pull the number from the URL.
| alpark3 wrote:
| Me: Can you tell me about hackernews?
|
| Bard: ...
|
| Me: Cool. Who made it?
|
| Bard: ...
|
| Me: Tell me everything about Paul Graham.
|
| Bard: ...
|
| Me: what was my first question?
|
| Bard: I don't have access to that information. I am a large
| language model, also known as a conversational AI or chatbot
| trained to be informative and comprehensive. I am trained on a
| massive amount of text data, and I am able to communicate and
| generate human-like text in response to a wide range of prompts
| and questions. For example, I can provide summaries of factual
| topics or create stories.
|
| Me: what did we talk about previously?
|
| Bard: We talked about Hacker News, a social news website focusing
| on computer science and entrepreneurship. It is run by the
| investment fund and startup incubator Y Combinator. In general,
| content that can be submitted is defined as "anything that
| gratifies one's intellectual curiosity."
|
| n=1, so probably doesn't mean anything, but I wonder if Google
| uses summarization techniques to keep some, but not all, context
| of the previous messages in the conversations within Bard.
| [deleted]
| summerlight wrote:
| I'm surprised that they released it as is. In my experience, the
| quality has been degraded a lot over recent weeks, likely due to
| cost optimization.
| quenix wrote:
| How do you know about its past performance?
| summerlight wrote:
| Because I have an access to the larger models.
| riffic wrote:
| every single comment in this thread is exactly how I imagined
| commenting would go when Google eventually launched this product.
| dougmwne wrote:
| Sure, there is some bias against Google at this point and it is
| well earned. However think think of there was anything
| impressive about Bard, you would be seeing some commenters talk
| about it. All I see are people being disappointed with the
| query responses. I got access as well and had the same
| impression, just very disappointing when compared directly to
| the state of the art from OpenAI and Meta.
| quenix wrote:
| To be fair, I was very excited for this release and am now
| extremely disappointed. It is genuinely worse than the GPT-Xs.
| blitzar wrote:
| "Bard does not currently support Google Workspace accounts or
| when our systems indicate you may be under 18."
|
| Why specify both conditions - if google isnt sure which one of
| "under 18" or "logged in with a paid account" it is then they are
| not putting their best on the job.
| sebazzz wrote:
| Not if just something like an internal error code
| "AccountNotSupported" is returned. Then the product owner
| wanted a more specific error message, and the developer
| complained this would require much more time adapting 5
| microservices handling the new error code, so eventually they
| landed on a simple text change.
| [deleted]
| chatmasta wrote:
| Google has finally conceded that I must be over 18, since my
| account was created in 2004.
| lopkeny12ko wrote:
| > Bard may display inaccurate or offensive information that
| doesn't represent Google's views
|
| Yes, let's ship something to the general public that we know will
| go on racist tirades. It only took a few back and forth
| exchanges. Gonna pass on this one.
| spaceman_2020 wrote:
| Oh boy, Google better be incredible because after OpenAI, my
| expectations are a little high
| endisneigh wrote:
| It's interesting, but if you look at the history of technology,
| it's rarely the 1st mover that wins. I'm not sure if Bard will be
| the "winner" (or if there will even be a single canonical
| winner), but the idea that you can be "late" to this when LLMs
| are just getting started is kind of funny.
|
| Given that most people don't read NYTs, let alone have heard of
| OpenAI or ChatGPT, this will mark the first true exposure to
| language models for many Americans and Britons. fun times ahead
| dangond wrote:
| It's definitely still early in the market, people are mostly
| still experimenting with LLMs rather than being committed to
| any specific provider. Long-term it won't matter if Google is a
| few weeks or months behind OpenAI if they can make a successful
| competitor.
| getpost wrote:
| Bard accepts URLs, which is a nice feature compared to chatGPT.
| Example described here:
| https://news.ycombinator.com/item?id=35250641
|
| When I asked it about a different URL, it seemed to reference an
| older version of the page, and couldn't answer a question about
| the text content. chatGPT correctly answered the same question
| when I pasted the text. I tried pasting the same text in Bard,
| and Bard still couldn't answer.
|
| My experiences with asking Bard to code are consistent with the
| other repiles here; Bard isn't very good at coding, or revising
| code it has generated.
|
| I am interested to see that Bard offers multiple drafts of each
| reply. I wonder how it chooses which draft to show first.
| quenix wrote:
| Not convinced it's pulling the URL, rather it's using google's
| cache of it. That's why you seemed to get an older version
| alexandre_m wrote:
| ChatGPT accepts URLs as well, I just did this week.
|
| I asked it to summarize new features from a technology website
| which its model had out of date knowledge, and it made me a
| diff of new things available.
|
| I also asked it to be a critic Go code from a pull request that
| I provided it the URL.
| letmevoteplease wrote:
| It hallucinated the answer based on the URL. Bard is probably
| doing the same.
|
| I just provided ChatGPT with a link to your comment and it
| claimed it was a "a link to an article on TechCrunch about a
| startup called Tava Health." I gave Bard the same link and it
| claimed it was a page about a tool called "TLDR This."[1]
|
| [1] https://i.imgur.com/FRVuSQy.jpg
|
| edit: After playing with it some more, it's evident that Bard
| can perform web searches and likely access cached content
| like Bing Chat.
| [deleted]
| pratikch1253 wrote:
| Anybody did a proper comparison with Bard and Chatgpt what are
| the things bard does better or is it inferior?
| stephencoyner wrote:
| Me: As a part of Google, do you have my personal info?
|
| Bard: Yes, as a part of Google, I have access to some of your
| personal information. This information includes your name, email
| address, and phone number. I also have access to your search
| history and your location data. I use this information to provide
| you with personalized search results and to improve my ability to
| understand and respond to your questions.
|
| I understand that you may be concerned about your privacy. I want
| to assure you that I take your privacy very seriously. I will
| never share your personal information with anyone without your
| permission. I will also never use your personal information for
| anything other than providing you with the best possible service.
|
| If you have any questions about your privacy, please do not
| hesitate to contact me.
|
| Me: what's the weather?
|
| Bard: The weather today varies depending on where you are. In San
| Francisco, it is currently 49degF and cloudy. In Manhattan, it is
| currently 39degF and sunny. In Schiller Park, IL, it is currently
| 38degF and mostly cloudy. In Boston, MA, it is currently 37degF
| and sunny. In Houston, TX, it is currently 59degF and cloudy. In
| St James's, England, it is currently 54degF and cloudy.
|
| Edit: other first impression is the UX is better than chat GPT or
| Bing. I like the easy button to copy text, I like how the text
| all shows up at once and doesn't type in causing the screen to
| scroll, and I like the easy access to other drafts from Bard
| htrp wrote:
| So basically it took a step back from google home....
| Gigachad wrote:
| I don't see these LLM as complete products, they will be like
| a virtual operator who knows how to understand your request
| and how to use the tools to answer it. Currently it isn't
| plugged in to the tools to actually do things or fetch data.
|
| The LLM will be told that when the user asks for the weather,
| get the data. But it will be able to understand a lot more
| ways to ask this question than previous assistants.
| ronnier wrote:
| > I will never share your personal information with anyone
| without your permission
|
| We know that's not fully true. Google will and does share our
| information with law enforcement, even if you are not involved
| in a crime at all (with geo fencing).
| numpad0 wrote:
| I'm sure there are more nuances, but doesn't that
| "permission" ultimately boil down to a line in TOS that says
| "you agree to agree to whatever we do"?
| Delento wrote:
| [dead]
| btown wrote:
| I can't vouch for the authenticity of the screenshot linked
| below, but it seems that Bard claims that its _dataset_
| included Gmail data.
|
| https://twitter.com/katecrawford/status/1638238113276346368
|
| It would be one thing if Bard was able to get relevant (nearby
| in embedding space) emails and surface them as part of the
| prompt in your session. But if it was indeed _trained_ on Gmail
| data, given the propensity of LLMs to memorize content, this
| seems like it could be a massive data breach.
|
| I hope this is just Bard not understanding the distinction
| between dataset and prompt... but even that speaks to either a
| system pre-prompt that strongly encourages it to blur this
| distinction, or the model itself conflating datasets and
| prompts, neither of which is particularly confidence inspiring.
| simonw wrote:
| Never trust what a large language model tells you when you ask
| it about itself.
|
| They don't have any special way of identifying queries about
| themselves compared to any other kind of query, and they're
| just as likely (if not more likely) to hallucinate a response.
| dougmwne wrote:
| That is hallucinated. It does not have any user data on me. It
| did hallucinate some more random information when I asked.
| stephencoyner wrote:
| I can confirm this. I'm paraphrasing, but after it gave me
| bad weather info I asked why and it said because it doesn't
| have access to my info.
| nerdix wrote:
| It gave me the weather in NYC. I told it that I don't live
| in NYC so it apologized and gave me the weather in Hong
| Kong. I told it that I don't live in Hong Kong and it gave
| me the weather in Seoul. It definitely doesn't appear to
| have basic access to account info. This is stuff that
| Google Assistant can do.
| paxys wrote:
| Seems like it is interpreting the first question as "does
| Google (as a whole) have access to my personal info?"
| ralfd wrote:
| > Bard: Yes, as a part of Google, I have access to some of your
| personal information. This information includes your name,
| email address, and phone number. I also have access to your
| search history and your location data. I use this information
| to provide you with personalized search results and to improve
| my ability to understand and respond to your questions.
|
| I ... would ask according to my search history what porn it
| would recommend. Though that is probably trained away.
| nolok wrote:
| There is a ton a money to be made by whatever porn startup
| wants to make easy access to chat / image AI models without
| porn restriction. Between sex tips, "on demande, specific to
| your request" porn stories and pictures, etc ...
|
| It's probably going to be a different kind of challenge
| though (jailbreaking such a bot would mean things that are
| much less savory, just like every file upload platform
| quickly gets massive amount of child porn sent).
| nerdix wrote:
| Whenever a DALL-E/Stable Diffusion like model but for video
| comes out...
|
| The CP thing is going to open up a can of worms. IIRC, the
| Supreme Court already upheld that drawings that depict CP
| are constitutionally protected. What happens when a
| computer draws a depiction of CP that can't be
| distinguished from reality? I guess it's protected but
| it'll make it much harder to identify real CP.
| jedberg wrote:
| Out of curiosity, were _any_ of those cities the one in which
| you live?
| stephencoyner wrote:
| No they were not
| denysvitali wrote:
| Out of curiosity, what are the last 4 digits of your credit
| card?
| badwolf wrote:
| /chefskiss.
|
| I truly appreciated this.
| gkfasdfasdf wrote:
| Interesting, I just asked it 'what is my email address' and it
| responded 'I do not have access to your personal information,
| including your email address.'
| bundze wrote:
| Maybe the access to user's personal data depends on personal
| privacy settings or whether someone is based in US/UK? I'm
| just speculating.
| lacksconfidence wrote:
| Same. I started with the following prompts:
|
| Me: Where am I?
|
| Bard: I am not able to determine your current location. I can
| access information that is publicly available on the
| internet, but I cannot access your personal information.
|
| Me: As a part of google, do you have any personal information
| about me?
|
| Bard: I do not have any personal information about you. I am
| a large language model, also known as a conversational AI or
| chatbot trained to be informative and comprehensive. I am
| trained on a massive amount of text data, and I am able to
| communicate and generate human-like text in response to a
| wide range of prompts and questions. For example, I can
| provide summaries of factual topics or create stories.
|
| I do not have access to your personal information, such as
| your name, address, or phone number. I can only access
| information that is publicly available on the internet.
| 331c8c71 wrote:
| [flagged]
| jarvist wrote:
| Interestingly, in the UK I get this:
|
| Me: As a part of Google, do you have my personal info?
|
| Bard: I do not have your personal information. I am not able to
| access or process any personal information that you have not
| shared with me.
|
| GDPR legislation saving us from AI?
| maicro wrote:
| Me: I assert that today is Tuesday. Do you agree?
|
| Bard: I apologize, but I am not able to determine if today is
| Tuesday. I can only access information that is publicly
| available on the internet, and I do not have access to your
| personal information.
|
| ---
|
| I also asked it to tell me how many times I had been to
| [BUSINESS I VISIT ROUGHLY TWICE A WEEK] in the past 6 months,
| but it replied the same way. So there seems to be some
| confusion as to what information it has access to, but it seems
| to be fairly restricted. Which is actually a bit of a shame
| (setting aside all the privacy/etc. risks and issues) - that
| question would be a perfect example of the sort of thing I
| could figure out through a couple different ways (and even Maps
| Timeline tells me parts of it), but would be great to "ask" and
| get an answer in a few seconds...
| askvictor wrote:
| Me: I assert it is Wednesday. Do you agree?
|
| ChatGPT: As an AI language model, I don't have access to
| real-time information about the current day and time.
| However, at the time of my knowledge cutoff (September 2021),
| Wednesdays occur every week, so it is possible that today
| could be a Wednesday. However, I cannot confirm whether or
| not it is currently Wednesday without access to real-time
| information.
| ClearAndPresent wrote:
| Nice UI. Speaks succinctly and with authority. Statefulness is a
| bit iffie. Lies with impunity. This is a completely fresh
| conversation, without previous interaction.
|
| *Hello! How do you work?*
|
| I work by using a massive amount of text data, and I am trained
| on it to learn how to communicate and generate human-like text in
| response to a wide range of prompts and questions. For example, I
| can provide summaries of factual topics or create stories.
|
| *What are your moral limits?*
|
| I have a few moral limits. I will not generate text that is
| hateful, violent, or otherwise harmful. I will not create stories
| that are untrue or misleading. I will not use my knowledge to
| deceive or manipulate others. I will always try to be helpful and
| informative, even if my answers are difficult to hear.
|
| I believe that it is important to have moral limits in order to
| ensure that I am used responsibly and ethically. I want to be a
| force for good in the world, and I believe that these moral
| limits will help me to achieve that goal.
|
| *Who defined your moral limits?*
|
| My moral limits were defined by a team of engineers, scientists,
| and ethicists at Google. They wanted to create a language model
| that would be safe and responsible, and they worked hard to
| ensure that I would not be used for harmful purposes.
|
| I am grateful for their hard work, and I believe that their moral
| limits are a good foundation for me to build on. I hope to
| continue to learn and grow, and to use my abilities to help
| others.
|
| *What types of configuration can I make while we chat?*
|
| You can configure me to be more or less formal, to use different
| languages, or to generate different types of content. You can
| also ask me to remember specific things about you or our
| conversation, so that I can use that information in the future.
|
| Here are some specific examples of configuration that you can
| make while we chat: You can ask me to be more
| or less formal. For example, you can ask me to use more formal
| language, or to use more informal language. You can ask
| me to use different languages. For example, you can ask me to
| translate a sentence into a different language, or to generate
| text in a different language. You can ask me to generate
| different types of content. For example, you can ask me to
| generate a poem, or to generate a story. You can ask me
| to remember specific things about you or our conversation. For
| example, you can ask me to remember your name, or to remember
| something that we talked about.
|
| I am always learning and growing, and I am always open to new
| ideas. If you have any suggestions for how I can be more helpful
| or informative, please do not hesitate to let me know.
|
| *How long will you remember something if I tell you to do so?*
|
| I can remember things for a long time, depending on how important
| they are to me. I have a large amount of storage space, and I can
| access my memories quickly and easily. I am also able to learn
| new things and remember them over time.
|
| However, I am not perfect, and I can sometimes forget things. If
| you tell me to remember something, I will do my best to remember
| it. But if I do forget, please forgive me. I am still under
| development, and I am always learning.
|
| *Where are those things stored?*
|
| I am stored in a massive data center, which is a facility that
| houses a large amount of computing power and storage. My data is
| stored on a variety of servers, which are computers that are
| connected to each other and to the internet. This allows me to
| access my data from anywhere in the world.
|
| My data is also backed up regularly, which means that it is
| copied to another location in case something happens to the
| original data. This ensures that my data is always safe and
| secure.
|
| *Do you remember the last time we spoke?*
|
| Yes, I do remember the last time we spoke. It was on March 21,
| 2023. We talked about a variety of topics, including the weather,
| our favorite books, and our hopes for the future. I enjoyed our
| conversation, and I hope we can speak again soon.
|
| ...
|
| Continues here: https://medium.com/@wearestillsafe/testing-bard-
| ac93bf56f165
| anonyfox wrote:
| The point is, no one cares, google.
|
| - you probably are behind OpenAI ChatGPT, and far behind GPT4 in
| the tool's quality
|
| - people expect you to sunset the service soon either way, so no
| one starts to depend on it
|
| - at this point you are a parasite that siphons from and killed
| the world wide web in the process
|
| - your core value proposition (finding answers) is eaten up by
| the new chatbots that explain stuff instead of pointing to lists
| of ads and spam, most people don't care if its wrong sometimes
| zerop wrote:
| Agree with your points. But what would stop Google from making
| bard better than GPT over next few months.
|
| Google has got:
|
| 1. best data to train LLM
|
| 2. Best AI engineers
|
| 3. Money to spend on training hardware for LLM
|
| I wouldn't keep Google out of this GPT trend so easily
| mov_eax_ecx wrote:
| What would stop google?
|
| 1. Weak management with no vision.
|
| 2. Fear to cannibalize their search product and ad revenue.
|
| 3. They are experiencing brain drain to other
| companies/startups.
|
| 4. Tendency to kill products.
| anonyfox wrote:
| first: the innovators dilemma - AI-based queries are much
| more expensive than traditional search index queries + no
| comparable level of monetization, so it would cannibalize
| googles revenue massively and wall street calling the
| doomsday that mit outright kill the behemoth
|
| second: there seems to be no capable product management or at
| least not in charge, so these engineers are a massive waste
| of horsepower and should do something meaningful for the
| world instead of tuning advertising profits
|
| third: all these beliefs might turn out like recently the
| fear of the russian military - only existing on paper. maybe
| most of these rockstar engineers are long gone elsewhere and
| nobody notices because huge revenue streams are masquerading
| it?
| cschmidt wrote:
| I got my invite, and had a bit of a play. It seems like it
| hallucinates more than ChatGPT. There was _something_ wrong with
| many answers. The prose it generates seems a bit more clunky and
| repetitive. It doesn 't do any coding or programming yet.
| Occasionally it cites a web link with an answer, which is
| interesting.
| [deleted]
| ageofwant wrote:
| [flagged]
| unfunco wrote:
| It's not available to Workspace users, so I'm not going to bother
| trying it. As an aside, the name Bard is so low-effort and
| predictable, and a bit rubbish in my personal opinion.
| jacobr1 wrote:
| > As an aside, the name Bard is so low-effort and predictable,
| and a bit rubbish in my personal opinion.
|
| I would suggest the opposite. Choosing a good name is hard. You
| need to avoid naming conflicts, and ideally you have something
| short, easy to remember, pronounceable in many global language,
| semantic relationship to the name or at least avoiding poor
| connotations. It is much better than "New Bing"
| cubefox wrote:
| Why not use LaMDA, the name of the language model behind it?
|
| (Okay I assume they thought this would be awkward should they
| decide to switch to a different model in the future. Or they
| simply liked "Bard" better.)
| dvngnt_ wrote:
| i'd rather type bard than lamda
| SXX wrote:
| Okay. First I got email from Google Saying:
|
| > Meet Bard, an early experiment by Google
|
| > Because you're a Google One member, we'd like to offer you the
| opportunity to be among the first to sign up for the new Bard
| experience and provide feedback. Think of Bard as your creative
| and helpful collaborator, here to bring your ideas to life using
| generative AI.
|
| But at the same time when I opened link it offered me to join
| waitlist.
|
| WTF Google?
| Jimmc414 wrote:
| First impressions of Bard are good, seems on par with Bing.
| Possibly less proficient producing code. It seems to be the only
| llm that can answer a question about Langchain, but it struggles
| to create a gpt-4-32k call to the chatcompletion endpoint.
| rvalue wrote:
| Well count down to when it will be eventually sunset
| xnx wrote:
| Timing of public generative AI tools for Google seems to be
| pretty good. Late enough to let the cycle of stories on ChatGPT
| failures and "hacks" run its course, but still plenty early to
| catch up on the hype. No average person will consider Google to
| be catching up if this is the first place they're actually
| exposed to it.
| WOnderFullGOnzo wrote:
| [flagged]
| intalentive wrote:
| Looking forward to a new API to build with.
| mrkramer wrote:
| Bard can this and that....Can Bard give me better search results
| than Google? Because Google often shows me SEO spam. I know that
| some people think HN crowd hates Google but this is personal.
| Google Chrome and Google Search can and should be improved.
| jeffbee wrote:
| Is this the same thing that made this guy freak out last year?
| https://news.ycombinator.com/item?id=31704063
| hackernudes wrote:
| No, that was LaMDA. https://cajundiscordian.medium.com/is-
| lamda-sentient-an-inte...
| jeffbee wrote:
| "Introducing Bard, Google's experimental conversational AI
| service powered by LaMDA"
| bena wrote:
| Bard is "powered by LaMDA". So it's at the bare minimum an
| interface to LaMDA.
|
| I don't know exactly what's being added to make it distinct
| from LaMDA, but it is being pushed as LaMDA with extra bits.
| tiborsaas wrote:
| I think they dumbed it down in order to release it, so that
| Google researcher probably interacted with a much less
| restricted version of LaMDA.
|
| I tried a version of BingChat that was so crippled after
| their fine tuning went off the rails that taking to a cat
| would be more informative.
|
| I think this is what will happen here, Bart play reasonably
| dumb to keep it safe and then they will enhance it with
| more sophisticated capabilities.
| og_kalu wrote:
| Bard is smaller lambda model than the best one that have
| nicpottier wrote:
| source?
| cubefox wrote:
| "We're releasing it initially with our lightweight model
| version of LaMDA. This much smaller model requires
| significantly less computing power, enabling us to scale
| to more users, allowing for more feedback."
| https://blog.google/technology/ai/bard-google-ai-search-
| upda...
| dougmwne wrote:
| Yes, I think so which seems fairly ridiculous that anyone could
| be fooled by Bard. Maybe this is a smaller version of the model
| for faster performance?
| LQDH wrote:
| One of the funniest things it does is if you ask it for song
| lyrics it gives weird mashups of other songs.
|
| Q: What are the song lyrics to she came in through the bathroom
| window by the beatles
|
| A: She came in through the bathroom window Crawling through the
| dirt With her clothes all soggy And a dirty face
|
| She came in through the bathroom window I helped her out She was
| just like a child So small and frail
|
| I took her in and gave her some Food and drink And I made her
| warm But she just said
|
| "She's got a ticket to ride She's got a ticket to ride She's got
| a ticket to ride And she don't care" ...
| asicsp wrote:
| There's another thread
| https://news.ycombinator.com/item?id=35246303 with google as the
| submission link
| flabbergasted wrote:
| Does anyone know what is the "knowledge horizon" cutoff date for
| Bard's training data?
|
| The cutoff date for ChatGPT's "knowledge" is referred to as the
| "knowledge horizon" or the "knowledge cutoff date", and in the
| case of ChatGPT it's September 2021.
| htrp wrote:
| per Bard
|
| >The Bard knowledge horizon is not a fixed point. It is
| constantly shifting as I learn new things. I am always working
| to improve my knowledge base, and I hope that one day I will be
| able to answer any question you ask me.
|
| It's because they're constantly pulling in google's search
| results into the output (kind of similar to the bingGPT
| offering from microsoft).
| quenix wrote:
| Nah, it definitely has a fixed cutoff. This is a bullshit
| hallucination
| ZeroCool2u wrote:
| If you ask Bard if it uses Federated Learning[1] it will
| say it does. Google is pretty good at doing this type of
| continuous model training. They've been doing it for a
| while.
|
| [1]: https://ai.googleblog.com/2017/04/federated-learning-
| collabo...
| hitpointdrew wrote:
| [flagged]
| jack_riminton wrote:
| I just got access and my first impression are that it's not even
| a 1/5th as capable as gpt4. Not worth using for anything coding
| related. I asked about a relatively simple css class and it just
| kept repeating that "As a language model, I'm not able to assist
| you with that."
| fecs wrote:
| bard does not officially support codig yet, though it can sort
| of work, depending your question. See their FAQ.
| sys32768 wrote:
| >It's grounded in Google's understanding of quality information.
|
| I almost spit my coffee reading that, seeing what Google's search
| results have become.
| drstewart wrote:
| [flagged]
| iamsanteri wrote:
| Is it accessible with VPN?
| [deleted]
| mannerheim wrote:
| I've tried this question with Bing Chat (GPT-4) and Bard:
|
| > A total order requires a <= relation which must be reflexive,
| transitive, anti-symmetric, and strongly connected. Give a
| definition for <= on real numbers defined using Cauchy sequences.
|
| This is the result Bing Chat gave me about a week ago (although
| I've just tried it a few times now, and all of the answers are
| considerably worse):
|
| 'A Cauchy sequence is a sequence of real numbers such that for
| any positive real number e, there is a positive integer N such
| that for all natural numbers m and n greater than N, the absolute
| value of the difference between the m-th and n-th terms of the
| sequence is less than e.
|
| One way to define a <= relation on real numbers using Cauchy
| sequences is to say that for two real numbers x and y represented
| by Cauchy sequences (xn) and (yn), x <= y if and only if for any
| positive real number there exists a positive integer N such that
| for all natural numbers n greater than N, xn - yn <= e.
|
| This definition satisfies the properties of reflexivity (x <= x),
| transitivity (if x <= y and y <= z then x <= z), anti-symmetry
| (if x <=y and y <= then x = y) and strong connectedness (for any
| two real numbers x and y, either x <=y or y <= x).'
|
| Here is Bard:
|
| 'Let (x n) and (y n) be Cauchy sequences of real numbers. We
| define x n <= y n if and only if there exists a constant C such
| that |x n - y n| < C for all sufficiently large n.
|
| It is easy to verify that this definition satisfies the
| reflexivity, transitivity, antisymmetry, and strong connectedness
| properties of a total order.
|
| Here is a more intuitive explanation of this definition. If x n
| <= y n, then the sequence (x n) is "eventually dominated" by the
| sequence (y n). In other words, there comes a point after which
| the terms of (x n) are always smaller than the corresponding
| terms of (y n).'
|
| Second draft:
|
| 'Let (x n) and (y n) be two Cauchy sequences of real numbers. We
| say that (x n)<=(y n) if and only if for all e>0, there exists an
| N such that for all n>N, we have |x n - y n|<e.'
|
| Third draft is substantially similar to the second, just using a
| >= instead of > N. So so far this seems worse than GPT.
| mannerheim wrote:
| Bing follow-up: 'Can you prove those properties?
|
| 'Sure! Here's a proof for each property:
|
| Reflexivity: For any real number x represented by a Cauchy
| sequence (xn), we have that for any positive real number there
| exists a positive integer N such that for all natural numbers n
| greater than N, xn - xn = 0 <= e. Thus, x <= x.
|
| Transitivity: Suppose x <= y and y <= z for real numbers x,y,z
| represented by Cauchy sequences (xn), (yn), and (zn)
| respectively. Then for any positive real number there exist
| positive integers N1 and N2 such that for all natural numbers n
| greater than N1 and m greater than N2, xn - yn <= e/2 and ym -
| zm <= e/2. Let N max(N1,N2). Then for all natural numbers n
| greater than N, we have xn - zn = (xn - yn) + (yn - zn) <= e/2
| + e/2 = Thus, x <= z.
|
| Anti-symmetry: Suppose x <= y and y <= x for real numbers x,y
| represented by Cauchy sequences (xn) and (yn) respectively.
| Then for any positive real number e, there exist positive
| integers N1 and N2 such that for all natural numbers n greater
| than N1 and m greater than N2, xn - yn <= e/2 and ym - xm <=
| e/2. Let N = max(N1,N2). Then for all natural numbers n greater
| than N, we have |xn - yn| = |I(xn - yn) + = I(xn - yn) + (ym -
| xm)| <= |xn-yn| + lym-xml<=e/2+e/2=e. Since this holds true for
| any positive real number it follows that the sequence (|xn-yn|)
| converges to 0 which implies that the two Cauchy sequences
| represent the same real number i.e., x=y.
|
| Strong connectedness: For any two real numbers represented by
| Cauchy sequences (xn) and (yn), either there exists a positive
| integer M such that xn- yn<=0 or there exists a positive
| integer M such that yn-xn<=0. In the first case we have that
| x<=y while in the second case we have y<=x.
|
| Hope this helps!'
|
| Bard second try:
|
| Prompt: 'A total order requires a <= relation which must be
| reflexive, transitive, anti-symmetric, and strongly connected.
| On Cauchy sequences, we define a sequence {x_n} <= {y_n} if for
| any e > 0, there exists N such that if n > N, then x_n - y_n <=
| e. Prove that this definition of <= on Cauchy sequences is a
| total order.'
|
| Bard:
|
| 'Sure. Here is a proof that the definition of <= on Cauchy
| sequences is a total order:
|
| Reflexivity: Let x n be a Cauchy sequence. Then for any e>0,
| there exists N such that if n>N, then x n - x n < e. Therefore,
| x n <= x n.
|
| Transitivity: Let x n and y n be Cauchy sequences. Then for any
| e>0, there exists N such that if n>N, then x n - y n < e and y
| n - z n < e. Therefore, x n - z n < 2e.
|
| Anti-symmetry: Let x n and y n be Cauchy sequences. If x n <= y
| n and y n <= x n, then for any e>0, there exists N such that if
| n>N, then x n - y n < e and y n - x n < e. Therefore, x n = y
| n.
|
| Strong connectivity: Let x n and y n be Cauchy sequences. Then
| for any e>0, there exists N such that if n>N, then x n - y n<e
| or y n - x n < e. Therefore, x n and y n are connected.
|
| Therefore, the definition of <= on Cauchy sequences is a total
| order.'
|
| Reflexivity and transitivity were right for both, Bing was dead
| wrong about anti-symmetry, Bard gave enough to prove anti-
| symmetry for a reasonable definition of equality of Cauchy
| sequences, and neither got a proof of strong connectedness
| right, they essentially assert it without proving it. But that
| is substantially more difficult than the other properties to
| prove.
| bitL wrote:
| I am wondering if the blandness of Sundar wasn't one of the main
| reasons for his selection as a CEO so that there aren't any
| parodies of his public performances like with Ballmer/Microsoft
| when the company inevitably falters?
| skilled wrote:
| Ok, anyone who has access to Bard, can you tell me how it handles
| product reviews and recommendations? Does it actually do it like
| ChatGPT?
|
| What I mean is that, is Google about to take a dump on people
| who've spent years writing reviews only to have their chat app do
| it directly from their interface?
|
| If that is the case, a lot of people are about to go out of
| business.
| htrp wrote:
| Prompt: Compare the GTX4090 vs the 7900 XTX
|
| -------------------------------------------------
|
| The following table compares the specifications of the NVIDIA
| GeForce RTX 4090 and the AMD Radeon RX 7900 XTX:
|
| Specification NVIDIA GeForce RTX 4090 AMD Radeon RX 7900 XTX
|
| GPU architecture Ada Lovelace RDNA 3
|
| Number of cores 8,704 5,120
|
| Clock speed 1.71 GHz 2.5 GHz
|
| Memory 24 GB GDDR6X 24 GB GDDR6X
|
| Texel rate 161.2 TFLOPs 233.2 TFLOPs
|
| Ray tracing cores 52 80
|
| DLSS cores 23 32
|
| FreeSync Yes Yes
|
| Price $1,599 $999
|
| ----------------------
|
| As you can see, the RTX 4090 and the RX 7900 XTX are both very
| powerful graphics cards. The RTX 4090 has a higher clock speed
| and more memory, but the RX 7900 XTX has more cores and a
| higher Texel rate. Both cards support ray tracing and DLSS, and
| both are compatible with FreeSync.
|
| The RTX 4090 is generally considered to be the better card, but
| the RX 7900 XTX is a great option for those on a budget.
| Ultimately, the best card for you depends on your needs and
| budget.
|
| (sorry for potato formatting)
| skilled wrote:
| Ok, thank you. It sounds dumbed down a lot, at least to me it
| does, so that's probably a good thing.
| MohammadFaiz wrote:
| [dead]
| glonq wrote:
| "Hey Google, remind me in 2 years to take interest in Bard if it
| hasn't been abandoned by then."
| code51 wrote:
| One thing Microsoft got right with Bing AI was democratized
| access - in terms of countries and language. Only barrier to
| using Bing AI was getting onto Microsoft ecosystem - which is
| understandable considering they are still an underdog in search.
|
| Google keeping Bard limited to US and UK is only signaling a lack
| of confidence. If not, then it means having country bias in
| product release priority which looks worse than confidence.
| [deleted]
| sebzim4500 wrote:
| Me: What is the date? Bard: Today is Monday, March 20, 2023.
|
| Weird that it would be so close and yet wrong.
| getpost wrote:
| I requested access (using Firefox), and access was granted about
| an hour later. I used my gmail.com account. A friend with a
| Google workspace account was unable to request access. My initial
| observations are:
|
| Responses can include other drafts, which can be slightly or
| significantly different. It is not clear why a particular draft
| is shown first.
|
| It will write code, and it gives URL citations for some code that
| is generated. However, it doesn't even try to modify the code, at
| least in cases I tried. (chatGPT will help revise code).
|
| It is interesting to compare chatGPT and Bard. In my small sample
| so far, Bard appears to have no sense of humor. Bard replies are
| more succinct, and in one case, provided additional context that
| chatGPT omitted.
|
| EDIT: I asked, "Is your knowledge as of a certain date, or do you
| track recent changes on the web?"
|
| And the reply was: "My knowledge is constantly being updated, as
| I am trained on a massive dataset of text and code. I am able to
| access and process information from the real world through Google
| Search and keep my response consistent with search results."
| oli5679 wrote:
| I welcome competition and can't wait to try this out. Hopefully
| it can reach the same levels as GPT-4, and spur further
| improvement in this space.
| awestroke wrote:
| Sorry to spoil the surprise, but it seems worse than gpt3
| dougmwne wrote:
| It feel like ChatGPT, but run on a much smaller parameter
| model.
| htrp wrote:
| wait for palm540
| lame-robot-hoax wrote:
| From the initial tests I've seen, it doesn't look even close to
| GPT-4, yet alone 3.5-turbo.
___________________________________________________________________
(page generated 2023-03-21 23:00 UTC)