Firstname Lastname

takeraparterer

AI & ML interests

None yet

Recent Activity

upvoted an article 1 day ago
replied to TuringsSolutions's post 4 days ago
replied to their post 5 days ago

Organizations

takeraparterer's activity

replied to TuringsSolutions's post 4 days ago
replied to their post 5 days ago
replied to TuringsSolutions's post 5 days ago
view reply

image.png
that's a FFN, which is only a small part of an LLM

reacted to TuringsSolutions's post with ๐Ÿ˜” 5 days ago
view post
Post
438
What if I told you that LLM models do not simply predict the next token in a sequence but instead utilize an emergent structural pattern-based system to comprehend language and concepts? I created a graph-based optimizer that not only works, but it also actually beats Adam, like very badly. I prove it thoroughly using SMOL LLM models. The secret? The graph is not what you think it is, humans. Code, full explanation, and more in this video. The Rhizome Optimizer is MIT licensed. I have completed my research. I fully understand now.

https://youtu.be/OMCRRueMhdI
  • 6 replies
ยท
replied to TuringsSolutions's post 14 days ago
view reply

has threatened violence in subtle ways

๐Ÿ˜ญ๐Ÿ˜ญ๐Ÿ˜ญ๐Ÿ˜ญ๐Ÿ˜ญ๐Ÿ˜ญ

replied to TuringsSolutions's post 14 days ago
view reply

very intriguing. looking into this ๐Ÿ‘€๐Ÿ‘€๐Ÿ‘€

replied to TuringsSolutions's post 14 days ago
reacted to TuringsSolutions's post with ๐Ÿ˜” 14 days ago
view post
Post
3939
Are you familiar with the difference between discrete learning and predictive learning? This distinction is exactly why LLM models are not designed to perform and execute function calls, they are not the right shape for it. LLM models are prediction machines. Function calling requires discrete learning machines. Fortunately, you can easily couple an LLM model with a discrete learning algorithm. It is beyond easy to do, you simply need to know the math to do it. Want to dive deeper into this subject? Check out this video.

https://youtu.be/wBRem2p8iPM
  • 8 replies
ยท
replied to TuringsSolutions's post 14 days ago
replied to TuringsSolutions's post 19 days ago
view reply

why the hostility? I'm asking a question

replied to TuringsSolutions's post 19 days ago
replied to TuringsSolutions's post 19 days ago
replied to lippytm's post 24 days ago
view reply

this is one of the websites of all time

reacted to lippytm's post with ๐Ÿ‘€๐Ÿš€๐Ÿš€ 25 days ago
view post
Post
1350
Hello Universes of Time Machine Builders. Financing Time Machines Traveling Throughout Eternal Time Rewriting Historical History Retroactively. Robotics Robots for no manual labor so the Human race can leave the planet retroactively. The Old Testament โ€œHitchhikers Guide Throughout the Galaxyโ€, and the New Testament being โ€œHitchhikers Guides Throughout the Universes of Time Machine Buildersโ€. Teaching & Training everyone & the Robotics Robots to become better programmers & blockchain developers. Smart Contracts Earn while you Learn to become better programmers & Blockchain developers. And making a lot of money Financing leaving the planet retroactively.
  • 2 replies
ยท
reacted to nroggendorff's post with ๐Ÿ˜” 25 days ago
view post
Post
3300
@echo off
echo hello world
pause

ยท
reacted to TuringsSolutions's post with ๐Ÿ˜” about 1 month ago
view post
Post
1378
Ever wondered how neural networks actually work under the hood?

In my latest video, I break down the core mathematical concepts behind neural networks in a way that's easy for IT professionals to understand. We'll explore:

- Neurons as logic gates
- Weighted sums and activation functions
- Gradient descent and backpropagation

No complex equations or jargon, just clear explanations and helpful visuals!

โžก๏ธ Watch now and unlock the mysteries of neural networks: https://youtu.be/L5_I1ZHoGnM
reacted to TuringsSolutions's post with ๐Ÿ˜” about 1 month ago
view post
Post
2101
Transformers are not all we need, that is being proven repeatedly now as more alternative frameworks emerge. Another such framework is Kolmogorov Arnold Network based Transformers. I break down exactly how these differ from Perceptron based Transformers and give you the link to my Colab where I create a model based on the research paper that absolutely destroys a standard Transformers based model. Check out the video here: https://www.youtube.com/watch?v=Sw0euxNZCc4
replied to TuringsSolutions's post about 1 month ago
view reply

alright. A suggestion, add some kind of admin badge so you can be distinguished from a normal user