HNHacker News
TopNewBestAskShowJobs

DevarshRanpara

155 karma · joined February 18, 2020

submissionscomments
DevarshRanpara··on The Model Is the Easy Half
Explanation is pretty solid and in depth!
DevarshRanpara··on Words Are a Byproduct of Consciousness. For LLMs, It's Backwards
Humans figured out how to hunt animals by making spears from stone by their own, it was not programmed, and that is the main thing which makes us different, humans can go against their instinct, why they do it? Because of consciousness. Can LLM (Or any Model) produce something without training it on data? (Not saying you are wrong, just pasting my thoughts, your thinking which says video can also train a model is an interesting way to look!)
DevarshRanpara··on Words Are a Byproduct of Consciousness. For LLMs, It's Backwards
You are 100% right, I am still exploring (and also learning from all these comments). I have just started to explore these things now. Thank you for understanding author's mindset.
DevarshRanpara··on Words Are a Byproduct of Consciousness. For LLMs, It's Backwards
I want to add one thing, Please think about how animals perceive world? They don't have language, but they are conscious for sure.
DevarshRanpara··on Words Are a Byproduct of Consciousness. For LLMs, It's Backwards
how animals perceive world? They don't have language, but they are conscious for sure.
DevarshRanpara··on Words Are a Byproduct of Consciousness. For LLMs, It's Backwards
Stop for one second and ask yourself a simple question. Where do your words come from?

When you speak, what comes first, the idea or the word? Do you first feel a thought inside you, and only after that go searching for the right word to wrap around it? I think we all do. The word is never the start. The word is just the skin. The idea, the consciousness, is the thing sitting under it.

DevarshRanpara··on The Smallest Brain You Can Build: A Perceptron in Python
Hey, I am sorry if you felt that way, I watched https://www.youtube.com/watch?v=l-9ALe3U-Fg and got inspiration, I found your content to be similar to that video as well. I don't understand these concepts as deeply as you can, but I have tried to make it simple and toy like. I have to say, you have really good content, if I use any of your resources in my future blogs, surely I will give acknowledgement to you or any other creator!
DevarshRanpara··on The Smallest Brain You Can Build: A Perceptron in Python
Please throw them here, I like to play around with questions, simplify them, and will try to write next part of this!
DevarshRanpara··on The Smallest Brain You Can Build: A Perceptron in Python
My next article would be on multi dimensional problem statements.
DevarshRanpara··on The Smallest Brain You Can Build: A Perceptron in Python
Yeah, I will try to make more of these, I like to lean things from core, and I like to keep everything as simple as possible.
DevarshRanpara··on The Smallest Brain You Can Build: A Perceptron in Python
I can't agree more with you, It took me many days to understand the "By we need bias?" I know maths, I know programming, but why was not clear. I love 3blue1brown.
DevarshRanpara··on The Smallest Brain You Can Build: A Perceptron in Python
True, there can be simpler versions compared to perceptron, just like you made. I have learned something new from that, Thanks for sharing.
DevarshRanpara··on The Smallest Brain You Can Build: A Perceptron in Python
Thank you, I will try to make more demo on other concepts.
DevarshRanpara··on The Smallest Brain You Can Build: A Perceptron in Python
This fast AI course looks soo good man! Definitely I will start learning soon. Thank you!
DevarshRanpara··on Show HN: Mtb – An MCP sanity checker for vibe coding
Much needed tool in those days, people are using AI like zombies, making random stuff.