Thank you! Bret Victor's work is so inspiring.

Interesting four points!

Excellent

What Is cca? What is this is this cyber security or networking or maths?

so it's basically for RAG apps?

How did you get spectogram in what appears to be Audacity?

ran the demo myself a few months ago and it worked. now I get this. > Entering new AgentExecutor chain... --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-10-2d2d4f1a7f7a> in <cell line: 1>() ----> 1 agent_executor.invoke({ 2 "input": "Create a plot of the number of full time employees at the 3 tech companies with the highest market cap in the United States in 2024.", 3 }) 32 frames /usr/local/lib/python3.10/dist-packages/langchain_core/tools/base.py in args(self) 444 @property 445 def args(self) -> dict: --> 446 return self.get_input_schema().model_json_schema()["properties"] 447 448 @property AttributeError: type object 'TavilySearchInput' has no attribute 'model_json_schema'

A love supreme~ A love supreme~ A love supreme

Excelente explicación, y métricas para medir el esfuerzo de entrenamiento de GPT3 tks

Amazing Jalal, best material I've seen so far describing this matter. Keep up the great work old friend😊

THE FUCK THEY'VE DONE WITH THE MUSIC????

pls hire me.

finally found the video, if you haven't watched then this is the one .

this is amazing. One thing I didn't understand is the matrix, how it is generated and used in the processing to return the probability (how "the" turns into a big array of inputs)

Great example thanks Jay 😃

Very helpfull video, very well explained

Great video, and perhaps just as important, great selection of albums

Sir how can I execute multiple code shell at a time in jupytor

thank you for saying that bit about word2vec being outdated. a coworker was lobbying to use it for one of our projects and this helped nip that in the bud.

Thank you Sir for sharing ..your explanation is always different ..from transformer architecture i am following you..great

@Jay, Thank you for the explanation. I found the Colab link is not working, Can you share the updated link, please?

GRADIUS!!

why input token sh, ank is not a complete word but the output token redemption is a complete word. Are they part of the same vocabulary? Meaning vocabulary = list of all complete words + all fragmentations of each word?

Can you explain the mathematics model behind prompt? I found no mathematics model to explain prompt, just guideline to say you should write prompt as if you are talking to a human being

/

Rlhf makes those models much better so does directional stimulus context.

semplicemente f a n t a s t i c o

if i want to use Gato how do I go about that?🤔

Hello all, I am comming from the future (4 years after the video has been released), and I hope I am not late XD I love the way you teach <3, it is amazing so keep it up ! I have just one thing to ask : Can we have the code for the language_model class in 26:16 so that we can follow along and code on the fly please ? Thank you

Very practical and useful information. Thanks!

Very cool. Glad someone else has had the idea and actually implemented it.

u look like gaurav taneja aka flying beast

Thank you so much! This is really useful for drawing framework figures for research papers!

You are awesome Jay Keep up the good work

Thank you. Not related but I really want to know, what font are you using in your blog poster?

Thanks for sharing, looking for more valuable content like this

Excellent explanation, Thanks!

Does the agent use an LLM to determine the steps? Can you cover these internal details?

Thank you so much for your contribution, i really appreciate it.

is this supposed to be an ad or no?

Excelente!!!

Amazing! I am concentrating on LangChain these days.

😮

Thank you!

Wonderful walkthrough! 😍

Can Tools work only with Langchain? If not, a more general example would be nice..

2024, still a great reference to Transformers. Million thanks for the amazing work!

would be better if you could explain the code line by line instead of just mentioning briefly what they are doing. Great video otherwise. I learn alot from your videos.

thank you Jay for this beautiful explanation

Hi Jay, great video. What if the user wants to also provide his/her own data and ask questions related to that, which might also require outside world knowledge (this web search as a tool might still be useful)?