Hacker News new | ask | show | jobs
by qsera 114 days ago
>No, it's not equivalent to nested if statements.

It is. If you control the randomness involved, the output of a model is completely deterministic. Which means that it can be represented by a huge lookup table.

Anything that can be represented by a lookup table can be expressed as an `if then else` statement.
2 comments
fc417fc802 113 days ago
By that logic sin(x) is equivalent to a lookup table. Yeah, you can approximate it that way. But doing so at any reasonable level of precision will quickly become an exercise in the absurd. Neural networks are far worse, consisting of stacks of massive linear combinations fed into nonlinear functions.

Regardless, it remains irrelevant to the subject at hand. You're going off on a tangent rather than admit your initial claim was wrong.

link
qsera 113 days ago
>By that logic sin(x) is equivalent to a lookup table

NO!

`sin(x)` is continuous, so the domain is infinite.

But an LLM model is not a continuous function, and thus the domain of a LLM model is finite (set of all possible tokens). So using a lookup table for a model behavior would be exact and not an approximation. So it can indeed be represented by an if statement of finite size.

Hence proved!

If you don't understand something in what I wrote, I can clarify if you tell me where you have trouble following.

link
basch 113 days ago
That’s not true in practice thought https://sulbhajain.medium.com/why-llms-arent-truly-determini...
link
fc417fc802 113 days ago
Even if it were true he would still be wrong. I wish HN had some mechanic to evict these sorts of troll accounts that attempt to score rhetorical points rather than honestly learning about a subject. The usual vote and flag mechanics don't work here because there's no singular and overt violation of the guidelines taking place.
link
qsera 113 days ago
that is why I said

>If you control the randomness involved

link
basch 111 days ago
Which you essentially cannot do

It is inherently randomized

link
qsera 111 days ago
But isn't the link shared by that comment doing exactly that

https://sulbhajain.medium.com/why-llms-arent-truly-determini...

>The Thinking Machines research team showed it’s possible to fix this. They built batch-invariant kernels for RMSNorm, matrix multiplication, and attention, integrating them into the open-source inference engine vLLM.

>The outcome: 1,000 identical prompts, 1,000 identical outputs. Perfect reproducibility.

??

link