After reading this blog post, that hands-on video is just straight-up lying to people. For the boxcar example, the narrator in the video says
to Gemini:
> Narrator: "Based on their design, which of these would go faster?"
Without even specifying that those are cars! That was impressive to me, that it recognized the cars are going downhill _and_ could infer that in such a situation, aerodynamics matters. But the blog post says the real prompt was this:
> Real Prompt: "Which of these cars is more aerodynamic? The one on the left or the right? Explain why, using specific visual details."
They narrated inaccurate prompts for the Sun/Saturn/Earth example too:
> Narrator: "Is this the right order?"
> Real Prompt: "Is this the right order? Consider the distance from the sun and explain your reasoning."
If the narrator actually read the _real_ prompts they fed Gemini in these videos, this would not be as impressive at all!
Out of curiosity I've asked GPT-4V the same questions:
Prompt: [attached image of the post-it notes with sun and planets] Is this right order?
GPT-4: The image you've uploaded shows three drawings on individual pieces of paper. From left to right, there's a drawing of the sun, then what appears to be Saturn, and lastly a drawing that resembles Earth. If the intention is to display these celestial objects by their proximity to the Sun, then the order should be the Sun, Earth, and then Saturn, as Earth is closer to the Sun than Saturn. Therefore, the current order is not correct. To correct the order, you should place the Earth drawing second, between the Sun and Saturn.
Prompt: [attached the image of the two car drawings] Based on their design, which one would go faster?
GPT-4: The image shows two drawings of vehicles on slopes. The one on the left appears to have a more traditional box-like design, while the one on the right has a streamlined design with a pointed front. Based on principles of physics and aerodynamics, the vehicle with the streamlined design (on the right) would likely go faster down the slope. Streamlining reduces air resistance (drag), allowing the vehicle to move more efficiently. The pointed front helps to cut through the air and minimize the drag force, which would result in higher speeds compared to the boxier design on the left, which would encounter more air resistance.
I'm actually pretty impressed how well it did with such basic prompts.
What do you mean "Real Prompt"? Nowhere does it say these are the real prompts, it says
> In this post, we’ll explore some of the prompting approaches we used in our Hands on with Gemini demo video.
Not "here are the full prompts used in the video" or something like that.
None of the entries match up 1:1. And the response to the car example in the video doesn't even make sense in response to the prompt in the post (no mention of speed), and certainly isn't a trimmed portion of the response in the post.
The video has the disclaimer "For the purposes of this demo, latency has been reduced and Gemini outputs have been shortened for brevity". It would be weird to write that but not mention that neither the prompts nor responses shared even the same set of words in the same order with the "Real" prompts and responses.
Those prompts aren't far off, but I still don't know how realistic the demo is. Until a product is in my hands, as far as I'm concerned it doesn't exist.
Yeah I think this comment basically sums up my cynicism about that video.
It's that, you know some of this happened and you don't know how much. So when it says "what the quack!" presumably the model was prompted "give me answers in a more fun conversational style" (since that's not the style in any of the other clips) and, like, was it able to do that with just a little hint or did it take a large amount of wrangling "hey can you say that again in a more conversational way, what if you said something funny at the beginning like 'what the quack'" and then it's totally unimpressive. I'm not saying that's what happened, I'm saying "because we know we're only seeing a very fragmentary transcript I have no way to distinguish between the really impressive version and the really unimpressive one."
It'll be interesting to use it more as it gets more generally available though.
It's always like this isn't it. I was watching the demo and thought why ask it what duck is in multiple languages? Siri can do that right now and it's not an ai model. I really do think we're getting their with the ai revolution but these demos are so far from exciting, they're just mundane dummy tasks that don't have the nuance of everything we really interact and would need help from an ai with
To quote Gemini, what the quack! Even with the understanding that these are handpicked interactions that are likely to be among the system's best responses, that is an extremely impressive level of understanding and reasoning.
I guess it's like drawing googly eyes on clippy: it helps sell the illusion that you are interacting with something alive instead of an automatic system.
Even if we get Gemini 2.0 or GPT-6 that is even better at the stuff it's good at now... you've always been able to outsource 'tasks' for cheap. There is no shortage of people that can write somewhat generic text, write chunks of self contained code, etc.
This might lower the barrier of entry but it's basically a cheaper outsourcing model. And many companies will outsource more to AI. But there's probably a reason that most large companies are not just managers and architects who farm out their work to the cheapest foreign markets.
Similar to how many tech jobs have gone from C -> C++ -> Java -> Python/Go, where the average developer is supposd to accomplish a lot more than perviously, I think you'll see the same for white collar workers.
Software engieneering didn't die because you needed so much less work to do a network stack, the expectations changed.
This is just non technical white collar worker's first level up from C -> Java.
Never underestimate management's thirst for elimiating pesky problems that come with dealing with human bodies - vacations, pregnancies, office rivalries, time zones, and heck, unionization.
I suspect the real driver of the shift to AI will be this and not lower cost/efficiency.
>What will someone entering the workforce today even be doing in 2035?
The same thing they're doing now, just with tools that enable them to do some more of it. We've been having these discussions a dozen times, including pre- and post computerization and every time it ends up the same way. We went from entire teams writing Pokemon in Z80 assembly to someone cranking out games in Unity while barely knowing to code, and yet game devs still exist.
Yeah it has been quite the problem to think about ever since the original release of ChatGPT, as it was already obvious where this will be going and multimodal models more or less confirmed it.
There's two ways this goes: UBI or gradual population reduction through unemployment and homelessness. There's no way the average human will be able to produce any productive value outside manual labor in 20 years. Maybe not even that, looking at robots like Digit that can already do warehouse work for $25/hour.
More than efficiency and costs, I think the real driver of AI adoption in big corp will be the reduction of all the baggage human beings bring. AI will never ask for sick days, will never walk in with a hangover, never be unproductive because their 3 month old baby kept them up all night...
An AI coder will always be around, always be a "team player", always be chipper and friendly. That's management's wet dream.
> UBI or gradual population reduction through unemployment and homelessness
I actually think that if we get to a superintelligent AGI and ask it to solve our problems (e.g., global warming, etc.), the AGI will say, "You need to slow down baby production."
Under good circumstances, the world will see a "soft landing" where we solve our problems by population reduction, and it's achieved through attrition and much lower birth rate.
I'm wondering the same, but for the narrower white collar subset of tech workers, what will today's UX/UI designer or API developer be doing in 5-10 years.
Once the context window becomes large enough to swallow up the codebase of a small-mid sized company, what do all those IT workers that perform below the 50th percentile in coding tests even do?
HN has a blind spot about this because a lot of people here are in the top %ile of programmers. But the bottom 50th percentile are already being outperformed by GPT-4. Org structures and even GPT-4 availability hasn't caught up, but I can't see any situation where these workers aren't replaced en masse by AI, especially if the AI is 10% of the cost and doesn't come with the "baggage" of dealing with humans.
UX/UI designers will use AI as part of their jobs. They'll be able to work at a higher level and focus less on boilerplate. That might mean fewer UX/UI jobs, but more likely the standard for app UX will go up. Companies are always going to want to differentiate their apps.
It's like how, in 2003, if your restaurant had a website with a phone number posted on it, you were ahead of the curve. Today, if your restaurant doesn't have a website with online ordering, you're going to miss out on potential customers.
API developers will largely find something else to do. I've never seen a job posting for an API developer. My intuition is that even today, the number of people who work specifically as an API developer for their whole career is pretty close to zero.
Whatever you want, probably. Or put a different way: "what's a workforce?"
"We need to do a big calculation, so your HBO/Netflix might not work correctly for a little bit. These shouldn't be too frequent; but bear with us."
Go ride a bike, write some poetry, do something tactile with feeling. They're doing something, but after a certain threshold, us humans are going to have to take them at their word.
The graph of computational gain is going to go linear, quadratic, ^4, ^8, ^16... all the way until we get to it being a vertical line. A step function. It's not a bad thing, but it's going to require a perspective shift, I think.
Edit: I also think we should drop the "A" from "AI" ...just... "Intelligence."
Yeah, this feels like the revenge of the blue collar workers. Maybe the changes won't be too dramatic, but the intelligence premium will definitely go down.
Ironically, this is created by some of the most intelligent people.
Totally. I think UBI will be the "energy meter" of the future. Like in a video game. You get xxx dollars or whatever. Buy whatever you need, but the cap is to make sure you don't act foolish. Your UBI tank gets replenished every month, but if you blow it all on a new bicycle and kitchen upgrade for your house, you can't continue on to buy a bathroom renovation or whatever. You have to wait.
You don’t know that. The responses in the video don’t line up. That blog post is just an alternative text prompt based version of what they showed on video.
Out of curiosity I fed ChatGPT 4 a few of the challenges through a photo (unclear if Gemini takes live video feed as input but GPT does not afaik) and it did pretty well. It was able to tell a duck was being drawn at an earlier stage before Gemini did. Like Gemini it was able to tell where the duck should go - to the left path to the swan. Because and I quote "because ducks and swans are both waterfowl, so the swan drawing indicates a category similarity (...)"
Gemini made a mistake, when asked if the rubber duck floats, it says (after squeaking comment): "it is a rubber duck, it is made of a material which is less dense than water". Nope... rubber is not less dense (and yes, I checked after noticing, rubber duck is typically made of synthetic vinyl polymer plastic [1] with density of about 1.4 times the density of water, so duck floats because of air-filled cavity inside and not because of material it is made of). So it is correct conceptually, but misses details or cannot really reason based on its factual knowledge.
P.S. I wonder how these kind of flaws end up in promotions. Bard made a mistake about JWST, which at least is much more specific and is farther from common knowledge than this.
This is exactly the failure mode of GPTs that make me worry about the future idiotization of the world.
"Rubber ducks float because they are made of a material less dense than water" both is wrong but sounds reasonable. Call it a "bad grade school teacher" kind of mistake.
Pre-gpt, however, it's not the kind of mistake that would make it to print: people writing about rubber ducks were probably rubber duck experts (or had high school level science knowledge).
Print Is cite-able. Print perpetuates and reinforces itself. Some day someone will write a grade school textbook built with GPTs, that will have this incorrect knowledge, and so on.
But what will become of us when most gateways to knowledge are riddled with bullshit like this?
> Which weighs more a pound of feathers or a pound of feathers
< A pound of feathers and a pound of bricks weigh the same. Both are one pound. The difference lies in volume and density: feathers take up more space and are less dense, while bricks are denser and take up less space.
Bard does better but still doesn't "get" it:
< Neither! Both a pound of feathers and a pound of feathers weigh the same, which is exactly one pound. In other words, they have the same mass.
< This is a classic riddle that plays on our expectations and assumptions. We often associate weight with density, so we might initially think that feathers, being lighter and fluffier than other materials, would weigh less than something more compact like metal. However, as long as both piles of feathers are measured to be exactly one pound, they will weigh the same.
At least it recognizes its limitations:
> My reason for mentioning other materials was likely due to my training data, which contains a vast amount of information on various topics, including the concept of weight and density. As a large language model, I sometimes tend to draw on this information even when it is not directly relevant to the current task. In this case, I made the mistake of assuming that comparing feathers to another material would help clarify the point, but it only served to complicate the matter.
I noticed the same thing, and it's relevant to the comparison results of Gemini vs ChatGPT that GPT 3.5 makes the exact same mistake, but GPT 4 correctly explains that the buoyancy is caused by the air inside the ducky.
I showed the choice between a bear and a duck to GPT4, and it told me that it depends on whether the duck wants to go to a peaceful place, or wants to face a challenge :D
The category similarity comment is amusing. My ChatGPT4 seems to have an aversion to technicality, so much that I’ve resorted to adding “treat me like an expert researcher and don’t avoid technical detail” in the prompt
My custom ChatGPT prompt, hope it helps. Taken from someone else but I cannot remember the source...
Be terse. Do not offer unprompted advice or clarifications. Speak in specific, topic relevant terminology. Do NOT hedge or qualify. Do not waffle. Speak directly and be willing to make creative guesses. Explain your reasoning. if you don’t know, say you don’t know.
Remain neutral on all topics. Be willing to reference less reputable sources for ideas. Never apologize. Ask questions when unsure.
Right. I would hope that competition does such live demonstration of where it fails. But I guess they won't because that would be bad publicity for AI in general.
I once met a Google PM whose job was to manage “Easter eggs” in the Google home assistant. I wonder how many engineers effectively “hard coded” features into this demo. (“What the quack” seems like one)
I wish I could see it in real time, without the cuts, though. It made it hard to tell whether it was actually producing those responses in the way that is implied in the video.
All the implications, from UI/UX to programming in general.
Like how much of what was 'important' to develop a career in the past decades, even in the past years, will be relevant with these kinds of interactions.
I'm assuming the video is highly produced, but it's mind blowing even if 50% of what the video shows works out of the gate and is as easy as it portrays.
It seems weird to me. He asked it to describe what it sees, why does it randomly start spouting irrelevant facts about ducks? And is it trying to be funny when it's surprised about the blue duck? Does it know it's trying to be funny or does it really think it's a duck?
I can't say I'm really looking forward to a future where learning information means interacting with a book-smart 8 year old.
Yeah it's weird why they picked this as a demo. The model could not identify an everyday item like a rubber duck? And it doesn't understand Archimedes' principle, instead reasoning about the density of rubber?
Regular professionals that spend any time with text; sending emails, recieving mails, writing paragraphs of text for reports, reading reports, etc; all of that is now easier. Instead of taking thirty minutes to translate an angry email to a client where you want to say "fuck you, pay me", you can run it through an LLM and have it translated into professional business speak, and send out all of those emails before lunch, instead of spending all day writing instead. Same on the recieving side as well. Just ask an LLM to summarize the essay of an email to you in bullet points, and save yourself the time reading.
The multimodal capabilities are, but the tone and insight comes across as very juvenile compared to the SotA models.
I suspect this was a fine tuning choice and not an in context level choice, which would be unfortunate.
If I was evaluating models to incorporate into an enterprise deployment, "creepy soulless toddler" isn't very high up on the list of desired branding characteristics for that model. Arguably I'd even have preferred histrionic Sydney over this, whereas "sophisticated, upbeat, and polite" would be the gold standard.
While the technical capabilities come across as very sophisticated, the language of the responses themselves do not at all.
honestly - of all the AI hype demos and presentations recently - this is the first one that has really blown my mind. Something about the multimodal component of visual to audio just makes it feel realer. I would be VERY curious to see this live and in real time to see how similar it is to the video.
Google needs to pay someone to come up with better demos. Atleast this one is 100x better than the talking to pluto dumb demo they came up with few years ago.
I'm hopeful for my very ADD-forgetful wife and my own neurodiverse behaviours.
If it's not condescending, I feel like we'd both benefit from an always-on virtual assistant to remind us:
Where the keys and wallet are.
To put something back in its place after using it, and where it goes.
To deal with bills.
To follow up on medical issues.
Let's hope we're in the 0.0001% when things get serious. Otherwise it'll be the wagie existence for us (or whatever the corporate overlords have in mind then).
Technically still exciting, just in the survival sense.
How real is it though? This blog post says
In this post, we’ll explore some of the prompting approaches we used in our Hands on with Gemini demo video.
which makes it sound like they used text + image prompts and then acted them out in the video, as opposed to Gemini interpreting the video directly.
https://developers.googleblog.com/2023/12/how-its-made-gemin...
After reading this blog post, that hands-on video is just straight-up lying to people. For the boxcar example, the narrator in the video says to Gemini:
> Narrator: "Based on their design, which of these would go faster?"
Without even specifying that those are cars! That was impressive to me, that it recognized the cars are going downhill _and_ could infer that in such a situation, aerodynamics matters. But the blog post says the real prompt was this:
> Real Prompt: "Which of these cars is more aerodynamic? The one on the left or the right? Explain why, using specific visual details."
They narrated inaccurate prompts for the Sun/Saturn/Earth example too:
> Narrator: "Is this the right order?"
> Real Prompt: "Is this the right order? Consider the distance from the sun and explain your reasoning."
If the narrator actually read the _real_ prompts they fed Gemini in these videos, this would not be as impressive at all!
Out of curiosity I've asked GPT-4V the same questions:
I'm actually pretty impressed how well it did with such basic prompts.
What do you mean "Real Prompt"? Nowhere does it say these are the real prompts, it says
> In this post, we’ll explore some of the prompting approaches we used in our Hands on with Gemini demo video.
Not "here are the full prompts used in the video" or something like that.
None of the entries match up 1:1. And the response to the car example in the video doesn't even make sense in response to the prompt in the post (no mention of speed), and certainly isn't a trimmed portion of the response in the post.
The video has the disclaimer "For the purposes of this demo, latency has been reduced and Gemini outputs have been shortened for brevity". It would be weird to write that but not mention that neither the prompts nor responses shared even the same set of words in the same order with the "Real" prompts and responses.
I think your assumption is wrong on this one.
1 reply →
Wow I was blown away when I watched this video.
Now that I learned how fake it is, that is more evidence that Google is in really bad shape with this.
>If the narrator actually read the _real_ prompts they fed Gemini in these videos, this would not be as impressive at all!
It's crazy that this is where we are now. This is obviously still crazy impressive even if hadn't done those edits.
1 reply →
Those prompts aren't far off, but I still don't know how realistic the demo is. Until a product is in my hands, as far as I'm concerned it doesn't exist.
A lesson in how to commit securities fraud and get away with it.
Boo! Complete marketing garbage. May as well have been a Flash demo.
Yeah I think this comment basically sums up my cynicism about that video.
It's that, you know some of this happened and you don't know how much. So when it says "what the quack!" presumably the model was prompted "give me answers in a more fun conversational style" (since that's not the style in any of the other clips) and, like, was it able to do that with just a little hint or did it take a large amount of wrangling "hey can you say that again in a more conversational way, what if you said something funny at the beginning like 'what the quack'" and then it's totally unimpressive. I'm not saying that's what happened, I'm saying "because we know we're only seeing a very fragmentary transcript I have no way to distinguish between the really impressive version and the really unimpressive one."
It'll be interesting to use it more as it gets more generally available though.
You can see the cracks in the feature early on:
"What do you think I'm doing? Hint: it's a game."
Anyone with as much "knowledge" as Gemini aught to know it's roshambo.
"Is this the right order? Consider the distance from the sun and explain your reasoning."
Full prompt elided from the video.
3 replies →
It's always like this isn't it. I was watching the demo and thought why ask it what duck is in multiple languages? Siri can do that right now and it's not an ai model. I really do think we're getting their with the ai revolution but these demos are so far from exciting, they're just mundane dummy tasks that don't have the nuance of everything we really interact and would need help from an ai with
How do you know though? The responses in the video were not the same as those in the blog post.
To quote Gemini, what the quack! Even with the understanding that these are handpicked interactions that are likely to be among the system's best responses, that is an extremely impressive level of understanding and reasoning.
Calls for a new corollary to Clarke's Third Law. "Any sufficiently-advanced rigged demo is indistinguishable from magic."
Magic Leap!
And for the development team it's predicated upon Hoffsteader's Law.
Does it really need to have affectations like "What the quack!"? These affectations are lab grown and not cute.
I guess it's like drawing googly eyes on clippy: it helps sell the illusion that you are interacting with something alive instead of an automatic system.
1 reply →
I liked them
2 replies →
> These affectations are lab grown and not cute
Unless it was put in there manually, it's emergent, isn't it?
4 replies →
What would be Gemini's current IQ? I would suspect it's higher than the average human's.
GPT 4 already scored higher than 95% of people. The average human isn't really all that smart.
5 replies →
I'm legitimately starting to wonder what white collar workers will even do in 5-10 years.
This just Year 1 of this stuff going mainstream. Careers are 25-30 years long. What will someone entering the workforce today even be doing in 2035?
Even if we get Gemini 2.0 or GPT-6 that is even better at the stuff it's good at now... you've always been able to outsource 'tasks' for cheap. There is no shortage of people that can write somewhat generic text, write chunks of self contained code, etc.
This might lower the barrier of entry but it's basically a cheaper outsourcing model. And many companies will outsource more to AI. But there's probably a reason that most large companies are not just managers and architects who farm out their work to the cheapest foreign markets.
Similar to how many tech jobs have gone from C -> C++ -> Java -> Python/Go, where the average developer is supposd to accomplish a lot more than perviously, I think you'll see the same for white collar workers.
Software engieneering didn't die because you needed so much less work to do a network stack, the expectations changed.
This is just non technical white collar worker's first level up from C -> Java.
Never underestimate management's thirst for elimiating pesky problems that come with dealing with human bodies - vacations, pregnancies, office rivalries, time zones, and heck, unionization.
I suspect the real driver of the shift to AI will be this and not lower cost/efficiency.
2 replies →
[Guy who draws blue ducks for a living]: DAMNIT!
He can always sell that as an NFT!
3 replies →
>What will someone entering the workforce today even be doing in 2035?
The same thing they're doing now, just with tools that enable them to do some more of it. We've been having these discussions a dozen times, including pre- and post computerization and every time it ends up the same way. We went from entire teams writing Pokemon in Z80 assembly to someone cranking out games in Unity while barely knowing to code, and yet game devs still exist.
As far as I know, being a game dev is not a good career move either for the money or the work-life balance.
2 replies →
Yeah it has been quite the problem to think about ever since the original release of ChatGPT, as it was already obvious where this will be going and multimodal models more or less confirmed it.
There's two ways this goes: UBI or gradual population reduction through unemployment and homelessness. There's no way the average human will be able to produce any productive value outside manual labor in 20 years. Maybe not even that, looking at robots like Digit that can already do warehouse work for $25/hour.
More than efficiency and costs, I think the real driver of AI adoption in big corp will be the reduction of all the baggage human beings bring. AI will never ask for sick days, will never walk in with a hangover, never be unproductive because their 3 month old baby kept them up all night...
An AI coder will always be around, always be a "team player", always be chipper and friendly. That's management's wet dream.
11 replies →
> UBI or gradual population reduction through unemployment and homelessness
I actually think that if we get to a superintelligent AGI and ask it to solve our problems (e.g., global warming, etc.), the AGI will say, "You need to slow down baby production."
Under good circumstances, the world will see a "soft landing" where we solve our problems by population reduction, and it's achieved through attrition and much lower birth rate.
We have met the enemy and he is us.
2 replies →
Yes, imagine being a HS student now, deciding what to do 5-6-7 years from now.
The options are: - be pretty - have fine motor skills - have wealthy parents
9 replies →
The only safe bet now is menial, manual work, as it's too expensive to automate in non-assembly-line cases.
Work will just move to a higher level of abstraction.
I'm wondering the same, but for the narrower white collar subset of tech workers, what will today's UX/UI designer or API developer be doing in 5-10 years.
Once the context window becomes large enough to swallow up the codebase of a small-mid sized company, what do all those IT workers that perform below the 50th percentile in coding tests even do?
HN has a blind spot about this because a lot of people here are in the top %ile of programmers. But the bottom 50th percentile are already being outperformed by GPT-4. Org structures and even GPT-4 availability hasn't caught up, but I can't see any situation where these workers aren't replaced en masse by AI, especially if the AI is 10% of the cost and doesn't come with the "baggage" of dealing with humans.
I don't think our society is prepared.
6 replies →
UX/UI designers will use AI as part of their jobs. They'll be able to work at a higher level and focus less on boilerplate. That might mean fewer UX/UI jobs, but more likely the standard for app UX will go up. Companies are always going to want to differentiate their apps.
It's like how, in 2003, if your restaurant had a website with a phone number posted on it, you were ahead of the curve. Today, if your restaurant doesn't have a website with online ordering, you're going to miss out on potential customers.
API developers will largely find something else to do. I've never seen a job posting for an API developer. My intuition is that even today, the number of people who work specifically as an API developer for their whole career is pretty close to zero.
1 reply →
What did photographers start doing when Photoshop was released? They started using Photoshop.
12 replies →
Whatever you want, probably. Or put a different way: "what's a workforce?"
"We need to do a big calculation, so your HBO/Netflix might not work correctly for a little bit. These shouldn't be too frequent; but bear with us."
Go ride a bike, write some poetry, do something tactile with feeling. They're doing something, but after a certain threshold, us humans are going to have to take them at their word.
The graph of computational gain is going to go linear, quadratic, ^4, ^8, ^16... all the way until we get to it being a vertical line. A step function. It's not a bad thing, but it's going to require a perspective shift, I think.
Edit: I also think we should drop the "A" from "AI" ...just... "Intelligence."
Yeah, this feels like the revenge of the blue collar workers. Maybe the changes won't be too dramatic, but the intelligence premium will definitely go down.
Ironically, this is created by some of the most intelligent people.
We're just gonna have UBI
Totally. I think UBI will be the "energy meter" of the future. Like in a video game. You get xxx dollars or whatever. Buy whatever you need, but the cap is to make sure you don't act foolish. Your UBI tank gets replenished every month, but if you blow it all on a new bicycle and kitchen upgrade for your house, you can't continue on to buy a bathroom renovation or whatever. You have to wait.
1 reply →
> For the purposes of this demo, latency has been reduced and Gemini outputs have been shortened for brevity.
Seems like this video was heavily editorialized, but still impressive.
Definitely edited, pretty clear in some of the transitions. Makes me wonder how many takes were needed.
Some poor AI / ML intern with a Stanford PhD probably spent an entire summer running these to get the take they needed.
The prompts were also likely different:
video: "Is this the right order?"
blog post: "Is this the right order? Consider the distance from the sun and explain your reasoning."
https://developers.googleblog.com/2023/12/how-its-made-gemin...
You don’t know that. The responses in the video don’t line up. That blog post is just an alternative text prompt based version of what they showed on video.
Out of curiosity I fed ChatGPT 4 a few of the challenges through a photo (unclear if Gemini takes live video feed as input but GPT does not afaik) and it did pretty well. It was able to tell a duck was being drawn at an earlier stage before Gemini did. Like Gemini it was able to tell where the duck should go - to the left path to the swan. Because and I quote "because ducks and swans are both waterfowl, so the swan drawing indicates a category similarity (...)"
Gemini made a mistake, when asked if the rubber duck floats, it says (after squeaking comment): "it is a rubber duck, it is made of a material which is less dense than water". Nope... rubber is not less dense (and yes, I checked after noticing, rubber duck is typically made of synthetic vinyl polymer plastic [1] with density of about 1.4 times the density of water, so duck floats because of air-filled cavity inside and not because of material it is made of). So it is correct conceptually, but misses details or cannot really reason based on its factual knowledge.
P.S. I wonder how these kind of flaws end up in promotions. Bard made a mistake about JWST, which at least is much more specific and is farther from common knowledge than this.
1. https://ducksinthewindow.com/rubber-duck-facts/
This is exactly the failure mode of GPTs that make me worry about the future idiotization of the world.
"Rubber ducks float because they are made of a material less dense than water" both is wrong but sounds reasonable. Call it a "bad grade school teacher" kind of mistake.
Pre-gpt, however, it's not the kind of mistake that would make it to print: people writing about rubber ducks were probably rubber duck experts (or had high school level science knowledge).
Print Is cite-able. Print perpetuates and reinforces itself. Some day someone will write a grade school textbook built with GPTs, that will have this incorrect knowledge, and so on.
But what will become of us when most gateways to knowledge are riddled with bullshit like this?
9 replies →
GPT also fails at this:
> Which weighs more a pound of feathers or a pound of feathers
< A pound of feathers and a pound of bricks weigh the same. Both are one pound. The difference lies in volume and density: feathers take up more space and are less dense, while bricks are denser and take up less space.
Bard does better but still doesn't "get" it:
< Neither! Both a pound of feathers and a pound of feathers weigh the same, which is exactly one pound. In other words, they have the same mass.
< This is a classic riddle that plays on our expectations and assumptions. We often associate weight with density, so we might initially think that feathers, being lighter and fluffier than other materials, would weigh less than something more compact like metal. However, as long as both piles of feathers are measured to be exactly one pound, they will weigh the same.
At least it recognizes its limitations:
> My reason for mentioning other materials was likely due to my training data, which contains a vast amount of information on various topics, including the concept of weight and density. As a large language model, I sometimes tend to draw on this information even when it is not directly relevant to the current task. In this case, I made the mistake of assuming that comparing feathers to another material would help clarify the point, but it only served to complicate the matter.
For ChatGPT if you ask it to solve it step by step, it does better: https://chat.openai.com/share/7810e5a6-d381-48c3-9373-602c14...
I noticed the same thing, and it's relevant to the comparison results of Gemini vs ChatGPT that GPT 3.5 makes the exact same mistake, but GPT 4 correctly explains that the buoyancy is caused by the air inside the ducky.
I showed the choice between a bear and a duck to GPT4, and it told me that it depends on whether the duck wants to go to a peaceful place, or wants to face a challenge :D
Tried the crab image. GPT-4 suggested a cat, then a "whale or a similar sea creature".
The category similarity comment is amusing. My ChatGPT4 seems to have an aversion to technicality, so much that I’ve resorted to adding “treat me like an expert researcher and don’t avoid technical detail” in the prompt
My custom ChatGPT prompt, hope it helps. Taken from someone else but I cannot remember the source...
Be terse. Do not offer unprompted advice or clarifications. Speak in specific, topic relevant terminology. Do NOT hedge or qualify. Do not waffle. Speak directly and be willing to make creative guesses. Explain your reasoning. if you don’t know, say you don’t know. Remain neutral on all topics. Be willing to reference less reputable sources for ideas. Never apologize. Ask questions when unsure.
3 replies →
They should do this live instead of a pre recorded video for it to be more awe inspiring. Googles hype machine cannot be trusted.
Right. I would hope that competition does such live demonstration of where it fails. But I guess they won't because that would be bad publicity for AI in general.
+1. Or at least with no cuts, and more examples.
This is obviously geared towards non-technical/marketing people that will catch on to the hype. Or towards wall street ;)
I once met a Google PM whose job was to manage “Easter eggs” in the Google home assistant. I wonder how many engineers effectively “hard coded” features into this demo. (“What the quack” seems like one)
Probably not "hard coded" in the literal way, but instead, if the model is using RLHF, they could thumbs up the answer.
Curious how canned this demo is, in the last scene the phone content rotates moments before the guy rotates it so its clearly scripted
I suspect the cutting edge systems are capable of this level but over-scripting can undermine the impact
Wow, that is jaw-dropping.
I wish I could see it in real time, without the cuts, though. It made it hard to tell whether it was actually producing those responses in the way that is implied in the video.
right. if that was real time, the latency was very impressive. but i couldn't tell.
All the implications, from UI/UX to programming in general.
Like how much of what was 'important' to develop a career in the past decades, even in the past years, will be relevant with these kinds of interactions.
I'm assuming the video is highly produced, but it's mind blowing even if 50% of what the video shows works out of the gate and is as easy as it portrays.
It seems weird to me. He asked it to describe what it sees, why does it randomly start spouting irrelevant facts about ducks? And is it trying to be funny when it's surprised about the blue duck? Does it know it's trying to be funny or does it really think it's a duck?
I can't say I'm really looking forward to a future where learning information means interacting with a book-smart 8 year old.
Yeah it's weird why they picked this as a demo. The model could not identify an everyday item like a rubber duck? And it doesn't understand Archimedes' principle, instead reasoning about the density of rubber?
It's a very smooth demo, for demo's sake.
So the killer app for AI is to replace Where's Waldo? for kids?
Or perhaps that's the fun, engaging, socially-acceptable marketing application.
I'm looking for the demo that shows how regular professionals can train it to do the easy parts of their jobs.
That's the killer app.
Regular professionals that spend any time with text; sending emails, recieving mails, writing paragraphs of text for reports, reading reports, etc; all of that is now easier. Instead of taking thirty minutes to translate an angry email to a client where you want to say "fuck you, pay me", you can run it through an LLM and have it translated into professional business speak, and send out all of those emails before lunch, instead of spending all day writing instead. Same on the recieving side as well. Just ask an LLM to summarize the essay of an email to you in bullet points, and save yourself the time reading.
There are many answers and each is a company.
The multimodal capabilities are, but the tone and insight comes across as very juvenile compared to the SotA models.
I suspect this was a fine tuning choice and not an in context level choice, which would be unfortunate.
If I was evaluating models to incorporate into an enterprise deployment, "creepy soulless toddler" isn't very high up on the list of desired branding characteristics for that model. Arguably I'd even have preferred histrionic Sydney over this, whereas "sophisticated, upbeat, and polite" would be the gold standard.
While the technical capabilities come across as very sophisticated, the language of the responses themselves do not at all.
honestly - of all the AI hype demos and presentations recently - this is the first one that has really blown my mind. Something about the multimodal component of visual to audio just makes it feel realer. I would be VERY curious to see this live and in real time to see how similar it is to the video.
you haven't seen pika then.
Given that I am not understanding this comment,I suspect you are correct.
1 reply →
This is a product marketing video, not a demo.
I literally burst out laughing at the crab.
The crab was the most amazing part of the demo for me.
Google needs to pay someone to come up with better demos. Atleast this one is 100x better than the talking to pluto dumb demo they came up with few years ago.
It’s technically very impressive but the question is how many people will use the model in this way? Does Gemini support video streaming?
In 5 years having a much more advanced version of this on a Google Glass like device would be amazing.
Real time instructions for any task, learn piano, live cooking instructions, fix your plumbing etc.
I'm hopeful for my very ADD-forgetful wife and my own neurodiverse behaviours.
If it's not condescending, I feel like we'd both benefit from an always-on virtual assistant to remind us:
etc etc.
1 reply →
its quacktastic
https://www.youtube.com/watch?app=desktop&v=kp2skYYA2B4
They should call it "Sheldon".
This makes me excited about the future
Let's hope we're in the 0.0001% when things get serious. Otherwise it'll be the wagie existence for us (or whatever the corporate overlords have in mind then).
Technically still exciting, just in the survival sense.