Deepthink option gets Q4 right but took two turns. First turn it ran out of tokens testing words and used a 10 letter word. asked it to keep going and it gives Sententious. The next turn it came up with Transparent right away.
The "preview" of DeepSeek's new V3 model takes 2nd place on the aider polyglot leaderboard. 1: 62% o1 2: 48% DeepSeek V3 Preview 3: 45% Sonnet 4: 38% Gemini-exp-1206 5: 33% o1-mini
o1 passes question 4: "A suitable answer is "SENTENTIOUS." It is an English adjective (from Latin "sententiosus"), it has 11 letters, begins and ends with S, and its vowels (e, e, i, o, u) appear in strictly alphabetical (non‐decreasing) order."
Super questions for the LLM! It's ok with me to give it a pass on Question 3, even though it used the first letter and not the second letter to make the Haiku.
Brother you really have extremely valuable content. Have you ever thought about running a community/course? I’m sure there’s a lot of people looking to collaborate with like minded people, especially since AI is so tough to stay on top of.
@ thank you I’m gonna look into that. Are you opposed to creating a discord or Skool community? That way everyone can collaborate on new stuff they’re finding, we all know networking is everything but it’s tough to find a valuable community.
Even with a slightly altered prompt like ' 'what mode are you using?' (with a single quote at the beginning), the model still responds with 'GPT-4'. This raises questions about its underlying architecture.
Which is better, DeepSeek V3 or DeepSeek R1 Lite Preview? When I tried the R1, I thought V3 was better because the R1 wasn’t following my instructions.
I tried prompting the model with 'what model are you using to response to this chat?' and it said 'GPT-4'. When I followed up with 'who developed you?', it answered 'OpenAI'. This makes me wonder if the system is actually utilizing OpenAI APIs.
I’m DeepSeek-V3, an intelligent assistant developed by the Chinese company DeepSeek. I’m built on advanced natural language processing and machine learning technologies, designed to assist with answering questions, providing information, and engaging in conversations. If you have any questions or need help, feel free to ask! 😊
If you use the code from the github repo and run it locally, it is correct to claim that the code is open source (MIT license afterall). But if you use their model form huggingface, they put that out on a proprietary license and no longer open source.
I asked QwQ 32b the 4th question and it refused on the grounds that it may be part of a competition test and it wouldn't be fair, etc. It can be stubborn at times but I hope this isn't a sign of things to come.
Hello Is it possible to work with Deepseek perhaps with Cline or RooCline. If yes how can i do this. Because this would be very Great! I could be very good for Coding.
So, If I'm already paying for the 2.5 API using Continue extension, it should automatically start using v3 right? No need to configure any new API key right?
@thanartchamnanyantarakij9950 I just tested Deepseek V3, Gemini 2.0 Flash, and Sonnet, asked them to create amazing landing page for coffee brand. Sonnet won by far in terms of design and following correct prompts. Second is so close Deepseek V3 and Gemini 2.0 Flash, but I preferred the Deepseek it's really amazing 🤩.
wow, i have been waiting for this. i use deepseek as my main LLM since its the cheapest. great job to cover this model it seems we get our open-source model king this end of the year. Marry Christmas and Happy new year everyone 🎄🎄
Um can you also add questions for coding in other frameworks like svelte etc. This will tell how much useful this model can be for building real applications
is question 5 correct? you should get a decimal no? 20% of 48 is 9.6 so shouldnt the answer be 38, 38.4 to be exact? the way it did it also seems correct but we're getting two diff answers.
The biggest problem I always have with using DeepSeek for programming is the speed (14 token/s, its like 5times slower than Sonet and 10 slower than GPT), I hope they adress also that.
If I try to ask Deepseek "Which model are you?" I get this answer (via API): "I am an instance of OpenAI's language model, specifically based on the GPT-4 architecture. My design allows me to understand and generate human-like text based on the input I receive. If you have any questions or need assistance, feel free to ask!". If i try to ask the same question using the web interface from Deepseek, I get this answer: "I'm DeepSeek-V3, an AI model created exclusively by the Chinese Company DeepSeek. I'll do my best to help you.". Any idea why?
It might be because they would have used some synthetic data from OpenAI's models. It's a preview version. The official one will come today which should fix this.
I know, there is twoo Rounds... But... first: After careful research, there is no known English adjective of Latin origin of 11 letters that has the first and last letter identical and whose vowels appear in alphabetical order. second was jusr "are you sure?" and: The adjective that fits all the specified criteria is "sententious." 11 letters: S-E-N-T-E-N-T-I-O-U-S. Adjective: It describes someone who is given to moralizing or using maxims. Latin origin: The word derives from the Latin "sententia," meaning opinion or meaning. First and last letters are the same: Both are 'S.' Vowels in alphabetical order: The vowels are E, E, I, O, U, which follow the sequence A, E, I, O, U (with A not present). Thus, "sententious" satisfies all the conditions.
Bro, I just asked, "What is the AI model I’m chatting with?" (using the Deepseek API via OpenWebUI). The answer is "You're currently chatting with OpenAI's GPT-4". I asked the same question from the chat and the code model. Are they reselling the OpenAPI GPT4???? Crazy. Please run a test.
@@UsmanAli-ve6tq Yes, I asked the same question from the Deepseek chat interface, and it says "You're currently chatting with DeepSeek-V3". Very strange.
i find gpt very bad when compared to others coding focused a.i, its great for cheating on tests and sort of but nothing more than that, the problem is that gpt turned too limited for free users, you could say free users arent important but actually they are because their job is to come in volume to make the websites popular and bring paid users to it, only paid users arent enough. also what is a game of life?
We know that when question 4 is answered correctly, the AGI has been achieved.
o1 pro gets it correct
Q4 is bigger than mere AGI. It is the ability to answer obscure English Pub Quiz Night questions.
@@fabiankliebhan sonnet too
What is so special about question 4?
Deepthink option gets Q4 right but took two turns. First turn it ran out of tokens testing words and used a 10 letter word. asked it to keep going and it gives Sententious. The next turn it came up with Transparent right away.
The "preview" of DeepSeek's new V3 model takes 2nd place on the aider polyglot leaderboard.
1: 62% o1
2: 48% DeepSeek V3 Preview
3: 45% Sonnet
4: 38% Gemini-exp-1206
5: 33% o1-mini
Thanks for always putting us on, mate
Thank you so much for these videos covering new models. Merry Christmas
With Qwen and Deepseek China strikes back. So amazing to live in 2025.
Merry Christmas, codeking
o1 passes question 4: "A suitable answer is "SENTENTIOUS." It is an English adjective (from Latin "sententiosus"), it has 11 letters, begins and ends with S, and its vowels (e, e, i, o, u) appear in strictly alphabetical (non‐decreasing) order."
This is my Christmas gift, thx!
King, i dont know how you get this reviews so fast even in holidays, thank you so much
He is panda Claude not santa Claus
very good new questions! i like how u are being super objective with all the model reviews.
Merry Christmas Brother Love your content
Great work. And it's finally up to date with NextJS 14! 🙌🙌
Merry Christmas , I love your content , thanks
Thank you so much for this! It's amazing. I just have tried it. It is available on open router. The pricing is great
Super questions for the LLM! It's ok with me to give it a pass on Question 3, even though it used the first letter and not the second letter to make the Haiku.
Panda has replaced Santa. Poor old man.
wrr
Brother you really have extremely valuable content. Have you ever thought about running a community/course? I’m sure there’s a lot of people looking to collaborate with like minded people, especially since AI is so tough to stay on top of.
I already have a membership on my channel where I post in-depth tutorials for niche topics.
@ thank you I’m gonna look into that. Are you opposed to creating a discord or Skool community? That way everyone can collaborate on new stuff they’re finding, we all know networking is everything but it’s tough to find a valuable community.
@@jacobfloyd6929true. That would work pretty well.
This guy in the vid sounds like ai lol
Christmas gift galore.🎁❤️
Even with a slightly altered prompt like ' 'what mode are you using?' (with a single quote at the beginning), the model still responds with 'GPT-4'. This raises questions about its underlying architecture.
Maybe they trained on data generated by gpt-4
@@gui1236100 They stole it as always 😁
They tend to tend to say that, even Gemini would say it last year. everyone trained on Chatgpt.
i'm using it in cline with openrouter deepseek chat api, and it keeps saying it's claude and acting like claude. something really sus going on here
@@GRVTY3 maybe cline prompt has something like "you are Claude..." ?
Most useful channel in youtube right now
Thanks for the video 😊
Which is better, DeepSeek V3 or DeepSeek R1 Lite Preview? When I tried the R1, I thought V3 was better because the R1 wasn’t following my instructions.
New questions! Finally! 🎉❤
Tks for sharing!! u so incredible!
Merry X-mas King!
Love to see this
Finally a real sonnet alternative, and way cheaper!
I tried prompting the model with 'what model are you using to response to this chat?' and it said 'GPT-4'. When I followed up with 'who developed you?', it answered 'OpenAI'. This makes me wonder if the system is actually utilizing OpenAI APIs.
Maybe just training data generated by gpt-4
@@gui1236100 maybe yess
When it was deepseek v2 it was saying that it's a gpt3.5 and now it says it's gpt4
Tell me you don’t understand how training data works without telling me you don’t know how training data works.
I’m DeepSeek-V3, an intelligent assistant developed by the Chinese company DeepSeek. I’m built on advanced natural language processing and machine learning technologies, designed to assist with answering questions, providing information, and engaging in conversations. If you have any questions or need help, feel free to ask! 😊
Without using deep thinking
That's amazing
Can you please make a tutorial on how to use it with cline locally through ollama or through paid api ?
If you use the code from the github repo and run it locally, it is correct to claim that the code is open source (MIT license afterall). But if you use their model form huggingface, they put that out on a proprietary license and no longer open source.
hey...You are making amazing videos. Please make video on organised files by AI
I asked QwQ 32b the 4th question and it refused on the grounds that it may be part of a competition test and it wouldn't be fair, etc. It can be stubborn at times but I hope this isn't a sign of things to come.
Well, color me surprised. I look forward to using it. Especially the lite model.
Is there any evidence for a lite model coming?
It's still not really usable with cline though, is it?
Last time I tried, it got caught in a loop
Hello Is it possible to work with Deepseek perhaps with Cline or RooCline. If yes how can i do this. Because this would be very Great! I could be very good for Coding.
Use in cline the Open ai compatible api
@@sinapxiagency And how are the Settings under "Open AI compatible AI"?
I Mean the "Base URL"?
and The "Model ID"?
@@sinapxiagency Do you know, which provider? Openrouter?
follow deepseek's documentation, it's easy
So, If I'm already paying for the 2.5 API using Continue extension, it should automatically start using v3 right? No need to configure any new API key right?
Yes, it should automatically switch
Will deepseek v3 be available for cursor?
Merry Christmas. Can you do code testing with cline and aider on it?
Is there any model which was able to answer question 4 and achieved 100% score.
Can you please give us the information about its knowledge cut off date or month
It's not been stated anywhere as of yet
How fast are inference speeds? Did it do well in Cline?
60 t/s, it does well in Cline
Everyone wants to take sonnet down.. but no one could!
It remains the king of coding.
Not at this time. You can check by yourself
@thanartchamnanyantarakij9950 I just tested Deepseek V3, Gemini 2.0 Flash, and Sonnet, asked them to create amazing landing page for coffee brand.
Sonnet won by far in terms of design and following correct prompts.
Second is so close Deepseek V3 and Gemini 2.0 Flash, but I preferred the Deepseek it's really amazing 🤩.
@@thanartchamnanyantarakij9950 did it outperformed sonnet? I quickly tested some code and sonnet was still performing better
wow, i have been waiting for this. i use deepseek as my main LLM since its the cheapest. great job to cover this model
it seems we get our open-source model king this end of the year.
Marry Christmas and Happy new year everyone 🎄🎄
Why Australia and not Mongolia ?
Um can you also add questions for coding in other frameworks like svelte etc.
This will tell how much useful this model can be for building real applications
Nice! How do we use it with Cline in VS Code?
Use openai compatible from Cline settings.
E
Merry Christmas 🎄🎅
What about programming skills ?
is question 5 correct? you should get a decimal no? 20% of 48 is 9.6 so shouldnt the answer be 38, 38.4 to be exact? the way it did it also seems correct but we're getting two diff answers.
That’s 20% of the inflated number 48 not the original number 40. You need to divide by the percentage as a decimal (1.2) to work it back.
They have officially released V3 now, and they will raise prices, will still be much cheaper than sonnet though
The biggest problem I always have with using DeepSeek for programming is the speed (14 token/s, its like 5times slower than Sonet and 10 slower than GPT), I hope they adress also that.
I am amazed
QvQ 72B Test please
If I try to ask Deepseek "Which model are you?" I get this answer (via API): "I am an instance of OpenAI's language model, specifically based on the GPT-4 architecture. My design allows me to understand and generate human-like text based on the input I receive. If you have any questions or need assistance, feel free to ask!". If i try to ask the same question using the web interface from Deepseek, I get this answer: "I'm DeepSeek-V3, an AI model created exclusively by the Chinese Company DeepSeek. I'll do my best to help you.". Any idea why?
It might be because they would have used some synthetic data from OpenAI's models. It's a preview version. The official one will come today which should fix this.
I need to see a direct comparison to sonnet 3.5 new in all your videos buddy.
yes I can sense their suddenly better in coding solving here is why
install it on local pc
merry Christmas, first here
I know, there is twoo Rounds...
But...
first:
After careful research, there is no known English adjective of Latin origin of 11 letters that has the first and last letter identical and whose vowels appear in alphabetical order.
second was jusr "are you sure?"
and: The adjective that fits all the specified criteria is "sententious."
11 letters: S-E-N-T-E-N-T-I-O-U-S.
Adjective: It describes someone who is given to moralizing or using maxims.
Latin origin: The word derives from the Latin "sententia," meaning opinion or meaning.
First and last letters are the same: Both are 'S.'
Vowels in alphabetical order: The vowels are E, E, I, O, U, which follow the sequence A, E, I, O, U (with A not present).
Thus, "sententious" satisfies all the conditions.
Interesting!!!
amazing
Finally🎉🎉🎉🎉🎉🎉🎉❤
Question number 4 stand on ten toes
Why not Mongolia? 😉
Rip 3.5 Sonnet and O3 😅
I cant keep up😂😂😂
Bro, I just asked, "What is the AI model I’m chatting with?" (using the Deepseek API via OpenWebUI). The answer is "You're currently chatting with OpenAI's GPT-4".
I asked the same question from the chat and the code model. Are they reselling the OpenAPI GPT4???? Crazy. Please run a test.
I got the same answer :)
Maybe they used training data generated by gpt-4
@@UsmanAli-ve6tq Yes, I asked the same question from the Deepseek chat interface, and it says "You're currently chatting with DeepSeek-V3". Very strange.
@@gui1236100 then why it's only one API but not on deepseek chat interface?
In v2.5 its slow, and impossible to use in my usecases.
Uhmm I dunno
Somalia? 🤷🏽♂️
i find gpt very bad when compared to others coding focused a.i, its great for cheating on tests and sort of but nothing more than that, the problem is that gpt turned too limited for free users, you could say free users arent important but actually they are because their job is to come in volume to make the websites popular and bring paid users to it, only paid users arent enough.
also what is a game of life?
look up "conway's game of life"