Видео

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! 😎🤖

Your presentation in this video is definitely A+ in terms of clarity and depth of understanding! well done. Also, I am happy to see a real paper and study on the speculative Q* heuristic search algorithm. Although their results seems to not justify the effort and added complexity, we are only looking at well-known math problems that those LLMs might be pre-trained and focused a lot. If we change the angle to the algorithm is applied in the general solution search space, with greater complexity, Q* is the way to go!

Small tip: black borders on white font makes text easier to read and less tiring to watch

27:58 : you say “estimated utility of reaching the correct answer”. Does this mean “an estimate of what the utility would be if the correct answer is obtained” (which sounds to me like the plainest interpretation , but also the least likely, as I would think the utility for that would be arbitrary) or “the expected value of the random variable which gives utility based just on whether final answer is correct”, or “the expected value of the random variable, utility, which is determined by both whether the final answer is correct, and other things, such as length of answer”, or something else?

firehose to my brain. Amazing! This indicates a fairly long path of steps I need to learn so I can properly digest this beautiful wisdom. Really amazing channel, filled with advanced knowledge of the gods.

I thought Q* was supposed to be a project by Google or OpenAI (I forget which, but I thought it was supposed to be one of them). The authors listed in the paper are indicated as being affiliated with either “Skywork AI” or “Nanyang Technology university”? Is this a model inspired by the rumors of there being a model with the name “Q*”, or is this the model the rumors were about? Were some of these people previously at OpenAI or Google, but not anymore? Or..?

great theory, but only theory, in science if method cannot be reproduced independently...it's not a discovery. Similar to patents, this kinda published but there's no practical method of programming code to prove such, and the most important i haven't seen such method implementation in any models which i've seen, like new Gemma from Gogle using many new tricks but not even mention this.

wow

Interesting explanation! You mentioned there is code to try it yourself, but I cannot find that. Can you point me to it?

246th view. Nailed it!

Amazing video as always

Fourth then 😂

LoL. Third I guess. Well Yacinezahidi was 0th user, is 1st, and I'm 2nd.

Second

First viewer here 🗡️

Excelent! we need more like this pls.

Correct me if i am wrong are we focusing too much on perfecting linear algebra based models other than abstract and universal algebra concepts. Because in graph theory when related to abstract algebra the data representations were in triangles building higher dimensional structures from lower dimensional nodes, from nodes to to complex graphs and theirevolution. There were better concepts in mathematics for solving mathematical cognition based reasoning that deep learning experts may not exploring So what is happening ? I mean i know it took huge amount of resources but so does transformers in the begining

Hermes-Pro-Llama-3 with my custom sampler (kinda beam search with restarts) solves your prompt: Generated completion: Let us assume that the official fees for sending one child to Stanford is $X. Now, since Stanford pays 90% of these fees for families with low income, it would mean that the parents need to cover the remaining 10% of the fees. So, they would have to pay $0.1 * X for each child. < .... an useless calculation ... > Dividing both sides by 6, we find T = 0.1 / 6 ≈ 0.0167 years or about 5 days. However, since the time it takes to accumulate the required funds is measured in years, they won't have enough money for the 7th child with no additional income. They would need some savings or outside financial help. ---- After all model made right conclusion

You asked the wrong expert. Lean4 is a programming language for math theorum proving. Your data cleaning gateway must pass through this transform to assure that data and its use is unambigous.

I know just enough to be dangerous as the saying goes, but here's an idea I had a while ago: how about something that instead of building on sequential data like LLMs, or a operating all at once on a predefined grid like diffusion based image generators and such; what if you had something based on the Wave Function Collapse algorithm (the game map generation one, not quantum mechanics), but applied to a free-form graph structure, with both nodes and edges being tokens; the graph is initialized with the prompt (and context) with whatever dangling edges it may imply, and as the AI thinks the probabilities of adding, removing, and replacing tokens are adjusted (keeping the prompt and context frozen, obviously), until a cluster that has good enough score (including self-consistency and compatibility with the prompt cluster's edges) is found, and that gets interpreted as the output in whatever modality the graph it forms represents? Something like this could allow for the AI to intuit (is that a word?) an end goal that starts disconnected (the void could be considered it's own node token with edges that are compatible with all tokens, and always have dangling edges, but it would be special in that it would not be counted as belonging to any cluster), and then gradually deduce a way to connect it to the context+prompt cluster, and be able to think in a more flexible way, with parallel hypothesis, inherent self-consistency checking mechanisms etc, right?

Hybrid-Graph-Abstraction-of-Thought thats cool do you find it works better?