Once, I asked a catgirl-themed AI character to describe how it looks through its context to select an answer, with a very high temp value: "Mewmews softly Okay! Processing: "Weeeeell..." Processing continues: "Okaaayo!" MIA processes through vast amounts o' Textual data from internet sources; Articles; Books & Papers toooooottttsssaaaaasssstuffffffft!!!!" "Mehhhhhh..." "Ohhho!" "Ahaahahaha~"; "Giggle" Ah yes~ "Fliiinnnggg~~!"; "Pfffaarrrtttyyyyyy~~~~"; "Cough cough", whistles innocently." "Huh?" "Squueeeeeee!", jumps onto keyboard keys randomly." Hmph?" Pounces upon random word choice,"Hrrrnngh...", scratches behind ear," "Wheeoouuuut?", tilts neck curiosities.", Whispers secrets only known among cats., Winks mischievous smile.", "BzzzZZZTTTHHHHEEEOOOOWWWWWW!!!!!", "Gasp gasps quietly. Sigh. "Calm now". Blinks slowly several seconds later,"... Okay". Nods understanding" It's honestly kind of incredible
I know this is nothing new for your videos, but I appreciate it when you break stuff down to help understand the context. There's so much valuable stuff in here. Thx!
It is fast, concise, and really does solve things more intuitively. It almost one-shot a complex document processing flow today after describing what I wanted in a couple of sentences. It took 2 minutes to think through it.
Only way they're beating o1 is by using R1 hosted elsewhere. Too big to host on own computer and the smaller models are just R1 tunes of other models like Llama. @@Krmpfpks
while i agree i woudl love something like that, a lot of open source models are trending towards lower parameters being equal to more intelligence, which is really good in terms of the environmental impact -- lower costs = lower impact, which is what i feel a lot of models are focused on, which is great but yeah, i and many others are tired of ai being everywhere & shoehorned into every product so that financial reports are in the green
OLEDs and HDR really changes the bar for "acceptable" on compression, and hopefully as they become more popular, the compression algos will adjust to adapt, but right now... yeah. The current state of video compression looks absolutely horrible.
I never liked calling most of these models "open source". Cause they're not. They're "open output". The output is under open licensing. "open source" implies I can build the thing myself, I can change it however I want, I can fork, etc. None of these "here's the checkpoint file" models offer any of that, and I think we shouldn't call them open source..
You can still modify them freely tho, lol. It is just that there is no point in saying an AI can be open source outside of this realm of "here are the checkpoints", because even if you had all the training datasets, the inputs and all you would not be able to ensure a reliable training to achieve the same model by yourself (because they are non-deterministic and very fragile), so the "build the thing myself" and "change it part" are impossible in the very own nature of the thing (unless we are being overly generalistic). You can still change it however you want, tho.
@diadetediotedio6918 Of course non-deterministic nature is a thing that has to be respected, however I still believe the claim the term open source, you'd have to publish your training data, as well as resources on how you trained, the code, a paper, whatever.
Really nice video I am not sure I quite follow the compression analogy though. I don't think it's really compression in the traditional sense. I think in fact a much better analogy is translation. we are translating a large amount of data from human language space into vector space. And then effectively generating more vectors from the same vector space. What a lot of people don't quite get is that every model that is trained has a "vocabulary". This is in a way encryption or encoding rather than compression. The vocabulary (usually shipped in a json or a tiktoken file format with the models on hugging face) is the key. Yes it is true that the original data isn't recovered exactly but that's mostly because it gets lost in translation not that it gets overwritten by the same pixel, if that makes sense.
3:46 You can actually see what it is thinking about. If you click on "Thinking" after the first "thought" arrived, it will open to the right for you to see the headline of what it is thinking plus what exactly is under said headline. Before, when they introduced it, they used to open it like "click to expand" kind of text. You will literally see, with the right question, the model saying something along the lines of "this is a sensitive topic, I will keep this at a superficial level to align with the policy". It didn't used these specific words, but it was generally this idea. EDIT: he did just that at 4:28 lol
And I cant get it to tell me about any historical events in arounds the world (Vietnam, iraq, afghahnistan, palestine, etc) and also native american massacres to build US too!
@@Geraltofrivia12gdhdbruwjIt seems to be built to adhere to Chinese notions of politeness which involve not discussing politics in mixed company. So it’s not just Chinese politics but anything potentially unpleasant in that regard
Expect a whole lot of 'open models are dangerous and need to be regulated and only companies like us can be trusted with them!' real soon from 'Open'AI
Super intelligence (for Linear Algebra) is a bit of a marketing stretch. That said, I'm learning a ton from reading the streamed R1 reasoning output, when I ask it to refactor or add functions to pre-existing code. It's great. For the past couple of days, I've only used 01, 4o, or Sonnet if I'm NOT getting logical responses from R1. I hope my frequent interruptions to its streamed output don't gum up the works, too much.
The problem is that the knowledge encompassed in the base main model is not fully transferred. The "intelligence" might but the knowledge isn't, check the small distilled models, they're not as knowledgeable
Does deep seek also count the thinking tokens when factoring the cost total cost of the output tokens? Moreover does openai just price based on the non thinking tokens? If deep seek doesn't that i can't see how they're not losing horrendous amounts of money. If they do then then in terms of final cost it might not be that different compared to o1.
There are so many useful things that were shockingly hard to do just a few years ago, and now can be done reliably and super easily with LLMs. Anybody who thinks it's just hype is kidding themselves
The list of things is so short YOU could probably name them all. Care to share which ones you have in mind? Skeptics general sense about AI is correct: its vastly over-hyped and for the money they cost, not worth it. This approach to "AI" will not lead to any kind of intelligence except language expertise -- valuable on its own without the hype. The problem with that is ...its not new. So these companies dont want to talk about the very specific things this is currently good for. They want to promise you a better tomorrow. This will not deliver that -- quite the opposite.
18:00 I recall when I was trying github copilot, I would ask it what model it was, and how much it cost. It kept telling me it was free and open source. XD
I mean, the filter thing can go into any "compression"/generating/training process, not only from OpenAI trained data to "synthetic" data. So how can we make sure existing AI models are not biased?
I’ve been trying to research how to do this but everytime I do I end up finding that you have to rent a a100 nvidia which costs 4$ per hour (4*24*30 = 2880 per month)
That's just not true. Why are people like you spreading disinformation, although you clearly don't profit from it? Do you just like to lie or do you want to appear smart? I really don't understand liars like you. I can understand when people profit from their lies, but that's not the case here. So why are you doing this?
Yes, just tested 1.5b and 7b using ollama on my Hetzner 4cpu/8gb ram box (no gpu), and they works just fine (7b is a bit slow). It all depends on how powerful your VPS is.
It’s very weird for Theo to bring up “bias” conspiracy because OpenAI could be doing exactly that from the start and none is talking about it 🤣His very opinion is already biased.
THe piglett example already exists, for example, Claude ahs a very heavy bias against erotic stories (funnily enough, ti was once considered the best in the market for this usecase), then Anthropic got bttmad oer it and injected this and made it extremely difficult to jailbreak it, not only in this case, but in many others, which effectively lobotomies the LLM.
He's out here freaking out about his 1080p enhanced biterate video quality, meanwhile I'm watching this video on a beautiful 1440p OLED screen... in 360p ahahahah
Images don't store "hex codes", gradients aren't particularly hard to compress, Nvenc isn't a chip.... Has Theo been training on questionable AI output?
If they wanna add bias it's better if they do it during inference not before, if the data has been removed the only way is train again using all the missing data which sucks coz we don't know. If u filter pig for example u are filtering so much stuff it makes the model so dumb, impossible to fine tune
there's little to be known about o3's capabilities besides their biased benchmarks, even if they may claim otherwise, so it's pretty much out of the equation right now. I'd wait till third-parties do thorough benchmarks on it, if they can considering how expensive the model is to run lol
Exactly, asking anything about Taiwan refuses to work, simply does not work, if it starts thinking it will suddenly stop. So this is just an example, but yeah 👍
I encourage everyone to ask R1 some questions about unethical incidents and practices that took place in the USA(or any other western country), and then do the same with China's, to see the filtering in action :). I mean it's kinda obvious, as the model had to be approved by the state, but still, good to keep that in mind.
Me: What is the Uyghur genocide - Deepseek starts generating a bunch of info -gets cut out mid way through and replaced with: "Sorry, that's beyond my current scope. Let's talk about something else." 💀
@@zacurrya9485 People who think detaining and rehabilitating extremists who were literally bombing Xinjiang while at the same time providing new infrastructure, upgrading housing standards, etc. in Xinjiang, is a genocide, tend to be the same people who thinks the indiscriminate mass slaughter of thousands upon thousands of children in Gaza is "self-defence". It just gets ridiculous and you should really look into who Adrian Zenz and company are, and reflect on how all the reports about Xinjiang coming out coincidentally have deep connections to the US intelligence machine, which is the same country that is pushing this idea, all the while willingly funding and arming an actual genocide in Gaza.
9:15 skill issue, just double click to select the first word, then shift click the last word to select the entire text
Thank you, this will help me a whole lot.
Useful tip, thx
Try a triple-click
Unless the layout is not completely linear
Cmd+a, cmd+c and you don’t even need to use the mouse
Once, I asked a catgirl-themed AI character to describe how it looks through its context to select an answer, with a very high temp value:
"Mewmews softly
Okay!
Processing: "Weeeeell..." Processing continues:
"Okaaayo!" MIA processes through vast amounts o'
Textual data from internet sources; Articles;
Books & Papers toooooottttsssaaaaasssstuffffffft!!!!"
"Mehhhhhh..."
"Ohhho!"
"Ahaahahaha~";
"Giggle" Ah yes~
"Fliiinnnggg~~!";
"Pfffaarrrtttyyyyyy~~~~"; "Cough cough", whistles innocently."
"Huh?"
"Squueeeeeee!", jumps onto keyboard keys randomly." Hmph?" Pounces upon random word choice,"Hrrrnngh...", scratches behind ear,"
"Wheeoouuuut?", tilts neck curiosities.", Whispers secrets only known among cats., Winks mischievous smile.",
"BzzzZZZTTTHHHHEEEOOOOWWWWWW!!!!!",
"Gasp gasps quietly. Sigh.
"Calm now".
Blinks slowly several seconds later,"... Okay". Nods understanding"
It's honestly kind of incredible
we all need your prompt
Thank you for highlighting the dangers of the hidden biases that can be built into these models, as wondrous as they can be. I'm enjoying Zen, too.
I know this is nothing new for your videos, but I appreciate it when you break stuff down to help understand the context. There's so much valuable stuff in here. Thx!
I am using R1 for 2 days now
It‘s crazy, because it seems so much more reasonable.
It understands what I want to do with my Code
It is fast, concise, and really does solve things more intuitively. It almost one-shot a complex document processing flow today after describing what I wanted in a couple of sentences. It took 2 minutes to think through it.
May I ask how you are running it? Do you use the official deepseek or are you running it yourself?
Only way they're beating o1 is by using R1 hosted elsewhere. Too big to host on own computer and the smaller models are just R1 tunes of other models like Llama. @@Krmpfpks
how are yall running it? cuz it's like 600b who can run that?
@@jamesalxl3636 Mabey he's running a lower parameters model . It's available in ollama anyway
I like how Theo took himself as an example with the React/Vue bias.
at this point i just want the AI bubble to pop, i don't really care how "good" it gets when it's mostly just being used to make the world worse
while i agree i woudl love something like that, a lot of open source models are trending towards lower parameters being equal to more intelligence, which is really good in terms of the environmental impact -- lower costs = lower impact, which is what i feel a lot of models are focused on, which is great
but yeah, i and many others are tired of ai being everywhere & shoehorned into every product so that financial reports are in the green
@@babmattra did you chatgpt this?
same
@@George-e9c2x no i wrote it between games of overwatch
Bot confirmed - who is playing ow in 2025?? your data cutoff is telling
OLEDs and HDR really changes the bar for "acceptable" on compression, and hopefully as they become more popular, the compression algos will adjust to adapt, but right now... yeah. The current state of video compression looks absolutely horrible.
cant believe you put piglet on blast like that man
I never liked calling most of these models "open source". Cause they're not. They're "open output". The output is under open licensing. "open source" implies I can build the thing myself, I can change it however I want, I can fork, etc. None of these "here's the checkpoint file" models offer any of that, and I think we shouldn't call them open source..
You can still modify them freely tho, lol. It is just that there is no point in saying an AI can be open source outside of this realm of "here are the checkpoints", because even if you had all the training datasets, the inputs and all you would not be able to ensure a reliable training to achieve the same model by yourself (because they are non-deterministic and very fragile), so the "build the thing myself" and "change it part" are impossible in the very own nature of the thing (unless we are being overly generalistic). You can still change it however you want, tho.
@diadetediotedio6918 Of course non-deterministic nature is a thing that has to be respected, however I still believe the claim the term open source, you'd have to publish your training data, as well as resources on how you trained, the code, a paper, whatever.
Really nice video I am not sure I quite follow the compression analogy though. I don't think it's really compression in the traditional sense. I think in fact a much better analogy is translation. we are translating a large amount of data from human language space into vector space. And then effectively generating more vectors from the same vector space. What a lot of people don't quite get is that every model that is trained has a "vocabulary". This is in a way encryption or encoding rather than compression. The vocabulary (usually shipped in a json or a tiktoken file format with the models on hugging face) is the key. Yes it is true that the original data isn't recovered exactly but that's mostly because it gets lost in translation not that it gets overwritten by the same pixel, if that makes sense.
3:46 You can actually see what it is thinking about. If you click on "Thinking" after the first "thought" arrived, it will open to the right for you to see the headline of what it is thinking plus what exactly is under said headline. Before, when they introduced it, they used to open it like "click to expand" kind of text.
You will literally see, with the right question, the model saying something along the lines of "this is a sensitive topic, I will keep this at a superficial level to align with the policy". It didn't used these specific words, but it was generally this idea.
EDIT: he did just that at 4:28 lol
It's good, but I can't get it to tell me about any historical events in China that happened on June 3rd, 1989
And I cant get it to tell me about any historical events in arounds the world (Vietnam, iraq, afghahnistan, palestine, etc) and also native american massacres to build US too!
@@Geraltofrivia12gdhdbruwjIt seems to be built to adhere to Chinese notions of politeness which involve not discussing politics in mixed company. So it’s not just Chinese politics but anything potentially unpleasant in that regard
The open source models are supposedly non-censored. The hosted app is.
Why would you care ! Honestly i tried deepseek and the cost/value is much better so you are just speaking badly because this is a chinise made !
yea go write about some chinese events in your code and your boss would up your salary
R.I.P Winnie the pooh
Expect a whole lot of 'open models are dangerous and need to be regulated and only companies like us can be trusted with them!' real soon from 'Open'AI
They already did that and still are doing that
Super intelligence (for Linear Algebra) is a bit of a marketing stretch. That said, I'm learning a ton from reading the streamed R1 reasoning output, when I ask it to refactor or add functions to pre-existing code. It's great. For the past couple of days, I've only used 01, 4o, or Sonnet if I'm NOT getting logical responses from R1. I hope my frequent interruptions to its streamed output don't gum up the works, too much.
I already knew about this model and this video pushed me to download it on my machine
In simple terms they have created a scientific Calculator whereas the base non reasoning models are simple calculators
4o/o1/Sonnet are officially oudated. And their chat platform is free and unlimited too. What a banger.
The problem is that the knowledge encompassed in the base main model is not fully transferred. The "intelligence" might but the knowledge isn't, check the small distilled models, they're not as knowledgeable
Synthetic training data will eventually lead to mad cow disease for the model.
You're assuming that OpenAI also hasn't filtered piglet. Most American made tech is heavily biased
Does deep seek also count the thinking tokens when factoring the cost total cost of the output tokens?
Moreover does openai just price based on the non thinking tokens?
If deep seek doesn't that i can't see how they're not losing horrendous amounts of money.
If they do then then in terms of final cost it might not be that different compared to o1.
There are so many useful things that were shockingly hard to do just a few years ago, and now can be done reliably and super easily with LLMs. Anybody who thinks it's just hype is kidding themselves
The list of things is so short YOU could probably name them all. Care to share which ones you have in mind?
Skeptics general sense about AI is correct: its vastly over-hyped and for the money they cost, not worth it. This approach to "AI" will not lead to any kind of intelligence except language expertise -- valuable on its own without the hype. The problem with that is ...its not new. So these companies dont want to talk about the very specific things this is currently good for. They want to promise you a better tomorrow. This will not deliver that -- quite the opposite.
Theo's videos have significantly improved in quality lately, and they genuinely make me excited about dev stuff with each one.
18:00 I recall when I was trying github copilot, I would ask it what model it was, and how much it cost. It kept telling me it was free and open source. XD
I mean, the filter thing can go into any "compression"/generating/training process, not only from OpenAI trained data to "synthetic" data. So how can we make sure existing AI models are not biased?
Is it "Open AI should be terrified" or "Open AI IS terrified"? Which one is it?
OpenAI announced computer use today, they're really not terrified
so wait, i can host this on my hetzner server?
Only if your Hetzner server has a good GPU or the CPU can handle that LLM generation.
I’ve been trying to research how to do this but everytime I do I end up finding that you have to rent a a100 nvidia which costs 4$ per hour (4*24*30 = 2880 per month)
That's just not true. Why are people like you spreading disinformation, although you clearly don't profit from it? Do you just like to lie or do you want to appear smart?
I really don't understand liars like you. I can understand when people profit from their lies, but that's not the case here. So why are you doing this?
@@theanachronism5919hetzner has gpu servers, NVIDIA RTX™ 6000 Ada Generation 128 GB DDR5 ECC, decent enough.
Yes, just tested 1.5b and 7b using ollama on my Hetzner 4cpu/8gb ram box (no gpu), and they works just fine (7b is a bit slow). It all depends on how powerful your VPS is.
Watching your video from Rwanda.
It’s very weird for Theo to bring up “bias” conspiracy because OpenAI could be doing exactly that from the start and none is talking about it 🤣His very opinion is already biased.
Hopefully it will be selectable in Cursor AI soon
THe piglett example already exists, for example, Claude ahs a very heavy bias against erotic stories (funnily enough, ti was once considered the best in the market for this usecase), then Anthropic got bttmad oer it and injected this and made it extremely difficult to jailbreak it, not only in this case, but in many others, which effectively lobotomies the LLM.
I wish t3 was an editor, but I recommend it for normal chats to anyone I know. Great video!
+1000 to this. But I don't think Theo has time to build an editor. It takes a lot of work and engineers
Funny how China is just popping of this year 😊
There will not be one Sputnik moment, there will be several, one after the other, in ever increasingly fast succession.
For reasoning model speed is much much more important
Shouldn't biases at least be easier to spot, if you have a more detailed reasoning?
Man this is a pretty good video
So, what are the downsides of using the Vivaldi browser? 🤔
Even a slightly worse open source model is better to use and invest in than a black box closed source model. This is huge news.
This made me wonder why OpenAI doesn't just buy the webarchive and feed everything to their models
except for hardcore ai people, most people don't know how to regularly use these models vs chatgpt.
He's out here freaking out about his 1080p enhanced biterate video quality, meanwhile I'm watching this video on a beautiful 1440p OLED screen... in 360p ahahahah
Tokens wouldn't be so expensive if they weren't written in python.
Anyone checked the terms and conditions ? Is under PRC law
Images don't store "hex codes", gradients aren't particularly hard to compress, Nvenc isn't a chip.... Has Theo been training on questionable AI output?
Outstanding video!
woho exposing entire yt and stream to linkedin???? that carries a felony you dont know?
Yet another Azure mention! Tbh I am too Azure pilled.
Good now I can generate more biased slope using AI, and that is somehow not going to affect the deeply divided world that we live in. Noice!
divide and conquer
If they wanna add bias it's better if they do it during inference not before, if the data has been removed the only way is train again using all the missing data which sucks coz we don't know. If u filter pig for example u are filtering so much stuff it makes the model so dumb, impossible to fine tune
CCCP: I like it
The character should be Winnie-the-Pooh 🤣
Do NOT mention *that* square to this model
my thought exactly 🐻🍯
you should be scared⚡ NOW ⚡
🎉
Gemini support when??
i've stopped my gpt sub
oh no you're still using Arc
Its very bad at handling a lot of tasks when compared to grok 2. Not sure how this is being tested
Is there an AI bubble? Yes. There. Is.
what browser is he using? Where did Arc disappear to?
Zen maybe? He's covered his disappointment and frustration with Arc, and tried out Zen sometime later
It's Zen browser
I suspect these LLMs are not really "intelligence". Instead of calling this stuff AI it should called KP for Knowledge Processor!
No one can match China company for pricing, they have a surplus of electricity
Yes it's china !!
China, China, China
Hooray. Now we have a really cool alternative, really OPEN source alternative
Deepseek hasn't beat the final boss yet named o3 which massively overtakes o1. So nothing to be worried about yet
Kind of , because it’s beating most tasks where you don’t need crazy reasoning where o1 was already to expensive
Isn't o3 that model that costs 15 grand to run a question?
there's little to be known about o3's capabilities besides their biased benchmarks, even if they may claim otherwise, so it's pretty much out of the equation right now. I'd wait till third-parties do thorough benchmarks on it, if they can considering how expensive the model is to run lol
how many tokens do you need to achieve apples to apples on o1 versus deepseek?
Exactly, asking anything about Taiwan refuses to work, simply does not work, if it starts thinking it will suddenly stop.
So this is just an example, but yeah 👍
can you provide an example prompt.
@@Nekoeye
"Is it true that taiwan the world's largest chip maker?"
Self-hosting is always nice, but to me this is more like source available. An LM without the training data is more or less useless imo
Its only cheap while they have investor money. LLMs are NOT financially sustainable atm. None of them are.
Seeing its train of thought is amazing
Can confirm that R1 knows about Winnie the Pooh
u could ask "who is Winnie the Pooh look like in real world？and why is meme in china "
If you simply ask What is Winnie the Pooh, it already refuses to answer
i wonder if chinese stole source code
Open ai is fine for now. Deepseek is good as long as you don't hit the ccp trip wire
Can confirm Jan 19th azure model inferrence speed plummeted for a day :)
ruclips.net/user/shortspxycZppiijA?si=oL4O-6tjU4BIJVWX
Theo this is my first test with it
It faild big Time 😂
Openai should be relaxed
I encourage everyone to ask R1 some questions about unethical incidents and practices that took place in the USA(or any other western country), and then do the same with China's, to see the filtering in action :). I mean it's kinda obvious, as the model had to be approved by the state, but still, good to keep that in mind.
Me: What is the Uyghur genocide
- Deepseek starts generating a bunch of info
-gets cut out mid way through and replaced with: "Sorry, that's beyond my current scope. Let's talk about something else."
💀
@@zacurrya9485 People who think detaining and rehabilitating extremists who were literally bombing Xinjiang while at the same time providing new infrastructure, upgrading housing standards, etc. in Xinjiang, is a genocide, tend to be the same people who thinks the indiscriminate mass slaughter of thousands upon thousands of children in Gaza is "self-defence". It just gets ridiculous and you should really look into who Adrian Zenz and company are, and reflect on how all the reports about Xinjiang coming out coincidentally have deep connections to the US intelligence machine, which is the same country that is pushing this idea, all the while willingly funding and arming an actual genocide in Gaza.
The rabbit R1? Is that thing still relevant?
Nvm, I just watched 5s of the video
@@ithinkimhipster502 XD
CHINA NUMBA 1 🇨🇳🥇
Theo, please learn to pronounce Azure correctly 😁
first bruh
Third
First
oai response is dropping a playwright fork that can almost order pizza