Couldn't appreciate more the "watch it happen right here, make it super simple, really easy to learn" lemma, this will make u go far
@yagomj5066
28 күн бұрын
Maybe instead of zooming out and in, keeping a zoom in would be a pro
@LearnByBuildingAI
13 күн бұрын
check check! thanks!
@wadejohnson4542
19 күн бұрын
Looking forward to the upcoming DSPy videos in the series. Much appreciated. Thank you.
@LearnByBuildingAI
13 күн бұрын
More to come!
@HerroEverynyan
14 күн бұрын
Fantastic tutorial! Thanks so much!
@LearnByBuildingAI
13 күн бұрын
You're very welcome!
@ClintSearchEngineer
27 күн бұрын
I appreciate what you are doing here, with the grug angle.. Smart, grug smart.
@LearnByBuildingAI
13 күн бұрын
grug not smart, grug just learn hard lesson when grug walk into wall many times
@MecchaKakkoi
Ай бұрын
Great walk-through. Subscriber no. 42 here 😄
@LearnByBuildingAI
Ай бұрын
Thank you! Everyone starts somewhere, hope I get some momentum. I appreciate your support!!!
@seanbergman8927
Ай бұрын
Nice example! Enjoyed your walk through. I’m wanting to dive into DSPy. Starting to work on a training dataset for my application. Looking forward to more videos from you!
@LearnByBuildingAI
Ай бұрын
That's great work! Awesome to see that you're already applying it!
@brianjones7656
Ай бұрын
Great stuff - thanks!
@LearnByBuildingAI
Ай бұрын
Thanks Brian. It's the first - let's keep it moving forward :)
@AmberEvans-ui8el
Ай бұрын
Good vid - hope you post the notebook soon.
@LearnByBuildingAI
Ай бұрын
Notebook is here: github.com/bllchmbrs/learnbybuilding.ai/blob/main/dspy-grug-text/dspy-gentle-intro-part-1.ipynb Please star the Repo too!
@user-wr4yl7tx3w
13 күн бұрын
what if you don't have the ground truth, can you still use dspy? generally, isn't the ground truth hard to come by?
@LearnByBuildingAI
13 күн бұрын
No! It's not, at least, it shouldn't be. It doesn't need to be perfect, but you've got to collect data all of the time when you're using these systems. The goal is to curate a dataset that you're deeming "ground truth". It may not be perfect but it's just supposed to be "good enough". You can start with raw LLMs, but ground truth (in some sense) is what you should be moving towards!
@user-wr4yl7tx3w
13 күн бұрын
won't dspy approach result in costing us more in terms of openai token usage, given how it tries to optimize?
@LearnByBuildingAI
13 күн бұрын
Yes, but no. 1. Yes, because 'training' / 'optimization' is more expensive because you're optimizing. 2. No because you can use a much cheaper model to run your inference. For instance, you 'train' haiku to be better. Haiku from Anthropic is sooo much cheaper than GPT4 or Opus. If you're doing a lot of inference, you're going to save money.
@Slimshady68356
Ай бұрын
Nice explanation , Just subscribed
@LearnByBuildingAI
Ай бұрын
Thanks for the sub!
@PoGGiE06
22 күн бұрын
Very helpful video, thanks! New subscriber here. One minor niggle: always helpful to have a link to the code/.ipynb!
@LearnByBuildingAI
13 күн бұрын
KZitem doesn't let me post links yet because the channel is new. All notebooks are here: github.com/bllchmbrs/learnbybuilding.ai and here :learnbybuilding.ai/
Пікірлер: 26