Great! Thanks

It's a great video, but I still haven't figured out how to apply it... Do you need to use their work to evaluate the model, see what types of questions it is wrong on, and, for example, tune it to improve it for them, or how? Can anyone clarify?

It did not find a Fourier transformation! It (being the training computation) found a solution that could be described by a Fourier transformation.

Yea i cant find the code for this. Could you please tell us where this is?

I really love how to teach and talk! It's relaxing to watch your tutorials... It almost feels like you are the Bob Ross of Transformers programming haha

There AI is a bit of a copycat. Not much of a thinker. It's not really a copy as it's rewritten. But yeah they have some problems and more compute isn't going to fix it. I think they need to improve their neural nets architecture. And a bunch of other things.

Omg ❤

This is basically AI amplification. You exponentially refine the AI with AI. Now that they are doing the X^N trick where X is intelligence, the core question will be if the X is > 1 or < 1.

They're being open again ? I didn't expect this...

using my limited understanding: the main problem seems to be the fuzziness of human language. why not let the systems develop their own precise data-/command language that it uses to interact -to its agents, internal communication-? normalizing the input to a precise perception of the situation/context? we receive visual (looking, reading), audible, ..) -IOW- sensual information and translate it into meta information. watching a real time situation vs reading a description ends up in our perception very similar. Seeing a tiger jumping out of the bushes or reading about it requires naturally different actions. but there is a preprocessing, context establishing prior to our processing. all this, translating the input and building a context would remove a lot of noise and ambiguity. this, translated to a meta language that is the only channel that will feed to the process, may enhance already in the input phase objectivity and precision. missing context, safety, .. may be requested/verified already in the translation phase before it ever reaches the generation process. it may reduce the sample- and parameter-count of the system significantly -as a result of the normalization in the pre-processing phase-. Critiques?

News agencies are the last thing I'd trust to deliver trustworthy data.

Grasshopper here for class and leaving first comment. Thanks for the great videos!

This is very good introduction and enjoy the contents even I have implemented my Q-Learning by myself around 30 years ago.

MS cares about you... Joke of the year

Google fears perplexity, it's so, so much better. Its wrapper around a bunch of LLM's and a step by step. logic approach is better than the base models.

LoL, now that google search results often start with hallucinations, now we pay to have ai able to access actual search results. A golden age... ;-D

I think a good method of grokking would be to train on data compressed by synonyms

"forbes article" -aka someones blogpost on their forbes "site"

great insights, thank you

Great series, really enjoyed it.

I was about to ask if this video was sponsored by Microsoft 🤦‍♂ thank you for the translation 😉 , did not occur to me, honestly 🤦‍♂

😂 Thank you

Thank you for such a detailed explanation. Really enjoyed it 🚀. But is this Q* somewhat relevant to the one from OpenAI that people have been talking about 🧐?

I had this error when executing it : TypeError: Missing required arguments; Expected either ('model' and 'prompt') or ('model', 'prompt' and 'stream') arguments to be given

Thanks for the great content! Where can I find the link to your colab notebook (including your extra comments)?

Gemma 2 27B (Q4_K_M) got it zero shot: ** User: Stanford provides a financial aid to families with low income. They pay 90% of their official fees. If a poor family with 6 children will send all children to Stanford, at what time will they have enough money, received from Stanford, to send the 7th child to Stanford, if they have no money at all?? ** Ellama: This is a bit of a trick question! Here's why: + *Financial aid is need-based:* If a family has no income, it's unlikely they would receive 90% coverage from Stanford's financial aid program. *The problem with the scenario:* The question assumes the family has to rely solely on Stanford's financial aid for their 7th child's education. This is a common misconception - financial aid often doesn't cover 100% of costs, and it's based on financial need. A family with no income would likely find it impossible to attend Stanford without some form of outside funding or support. Let me know if you'd like to explore a different scenario with realistic income constraints!

My Claude 3.5 Sonnet answered like this for your prompt: ------------------------- Let's approach this step-by-step, using the given facts and rules to determine if Alice is wozz. Step 1: Fact - Alice is feg Step 2: Fact - Alice is tess Step 3: Rule - If feg and tess, then rabe Since Alice is both feg and tess, we can conclude that Alice is rabe Step 4: Rule - If rabe, then thoxe Since we concluded Alice is rabe, we can now conclude Alice is thoxe Step 5: Rule - If thoxe, then vepe Since we concluded Alice is thoxe, we can now conclude Alice is vepe Step 6: Fact - Alice is tess (we already knew this, but we're restating it for the next step) Step 7: Rule - If tess and vepe, then nup Since Alice is both tess and vepe, we can conclude that Alice is nup Step 8: Fact - Alice is ag Step 9: Fact - Alice is vide Step 10: Rule - If nup and ag and vide, then duve Since Alice is nup, ag, and vide, we can conclude that Alice is duve (Note: We already knew Alice is duve from the facts, but this confirms it through the rules) Step 11: Rule - If fum, then wozz However, we don't have any information about Alice being fum Conclusion: Based on the given facts and rules, we cannot conclude that Alice is wozz. There's no rule or chain of rules that leads us from the facts we know about Alice to the conclusion that she is wozz. Therefore, the answer to the query "Is Alice wozz?" is: We don't know. We cannot conclude that Alice is wozz based on the given information.

Superb video :) Very clear and concise explanation. Thank you.

Hello, thanks a lot for the awesome explanation! SBERTS don’t receive the attention they need. One question though, where do cross-encoders come to play here then? Is it a sentence embedding model with an output layer that produces a score between 0 and 1?

Yay! 😎🤖