Sebastian Raschka
speaker
1,024 appearances
1 recordings
1 series
first heard Feb 2026
last heard 1 Feb
Sebastian Raschka’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 1 in all, peaking in Feb 2026 with 1.
Appearances
But these explanations, they help the model with the accuracy.
They're also interesting.
A lot of papers showing what the model explains does not necessarily have to be correct, or maybe it's even unrelated to the answer.
But for some reason, it still helps the model.
Like this is the fact that it is
explaining.
And I think it's also, again, I don't want to anthropomorphize these LLMs, but it's kind of like how we humans operate, right?
If there's a complex math problem, let's say in a math class, you usually have a notepaper and you do it step by step.
You cross out things.
And the model also self-corrects.
And that was, I think, the aha moment in the R1 paper.
They called it aha moment because the model itself recognized it made a mistake and then said, ah, I did something wrong and so let me try.
And I think that's just so cool that
this falls out of just giving it the correct answer and having it figure out how to do it that it kind of does in a sense what a human would do although lms don't think like humans it's kind of like an interesting coincidence and the other nice side effect is it's great for us humans often to see these steps it builds trust but also we learn we can double check things
I can give you also a hands-on example.
I was training the Gwent 3 base model with RLVR on Math 500.
The base model had an accuracy of about 15%.
Just 50 steps, like in a few minutes with RLVR, the model went from 15% to 50% accuracy.
And you can't tell me it's learning anything fundamentally about math.
Exactly.
Showing 441–460 of 1,024 · page 23 of 52
← Previous
Next →