I am sad to say that this is another AI generated (which in itself is fine) tutorial that uses claude-speak and the voice model used has extremely weird way of speaking which makes it really hard to follow, and understand.
And just opening the first video ("One neuron can act like an if-statement") shows that this hasn't been proof-watched, as you get two branches, each with "x1" on it but then you sum them not multiply (i.e the weights are not explained at all there).
Sad because the topic is super useful.
Edit: the audio levels are different between the videos too.
Hi! thanks for the feedback, I agree the voice model can use some improvements.
Regarding "shows that this hasn't been proof-watched, as you get two branches, each with "x1" on it but then you sum them not multiply (i.e the weights are not explained at all there)." I did proof watch them a few times, the weights on that first example are deliberately set to 1 to simplify the explanation since my goal with this series is about the high level intuition and not about the exact math behind it (which I assume a good chunk of viewers have either already seen elsewhere or can easily find with a quick search, so that part didn't feel as valuable/differentiated).
> the topic is super useful.
I agree! and I do appreciate this feedback so I can keep making (or well, prompting and polishing into existance) better content each time.
Hi atrus! I agree these could certainly have more polish, my goal with it was to share some of the intuition that has helped me personally to understand why LLMs have the chops to be so effective in the realm of text (and other domains ofc, but this one focuses on text/language processing)
9 comments
[ 0.29 ms ] story [ 11.0 ms ] threadAnd just opening the first video ("One neuron can act like an if-statement") shows that this hasn't been proof-watched, as you get two branches, each with "x1" on it but then you sum them not multiply (i.e the weights are not explained at all there).
Sad because the topic is super useful.
Edit: the audio levels are different between the videos too.
Regarding "shows that this hasn't been proof-watched, as you get two branches, each with "x1" on it but then you sum them not multiply (i.e the weights are not explained at all there)." I did proof watch them a few times, the weights on that first example are deliberately set to 1 to simplify the explanation since my goal with this series is about the high level intuition and not about the exact math behind it (which I assume a good chunk of viewers have either already seen elsewhere or can easily find with a quick search, so that part didn't feel as valuable/differentiated).
> the topic is super useful. I agree! and I do appreciate this feedback so I can keep making (or well, prompting and polishing into existance) better content each time.
Without the polish, why would I pay you for your tutorials when I already pay Anthropic and can ask claude to make the same level of quality?
AI has raised the bar for effort and viability, and this isn't going to meet it.
But this is AI-slop? Pangram gives 100% AI for anything I've checked