HackerTrans
TopNewTrendsCommentsPastAskShowJobs

qeternity

no profile record

comments

qeternity
·25 วันที่ผ่านมา·discuss
There is a huge amount of vendor financing available for this exact reason.

Hetzner presumably have been making use of this for years already.

It's far more likely they simply began raising prices and realized the market would tolerate it.
qeternity
·เดือนที่แล้ว·discuss
I think it very much is worth it!

But the point was that quality didn't magically increase.
qeternity
·เดือนที่แล้ว·discuss
It's not better quality: 59.3% vs 59.4% fp16 on AIME 25
qeternity
·เดือนที่แล้ว·discuss
> Venture capitalists & private investors are sucking all of the possible growth and future upside from these companies and then dumping them on retail investors when there's nothing left.

A lot of the money that is deployed by VCs comes from pension funds and asset managers that ultimately manage money for the average Joe.
qeternity
·3 เดือนที่ผ่านมา·discuss
I haven't read TFA yet but a common technique is speculative decoding where a fast draft model will generate X tokens, which are then verified by the larger target model. The target model may accept some Y <= X tokens but the speedup comes from the fact that this can be done in parallel as a prefill operation due to the nature of transformers.

So let's say a draft model generates 5 tokens, all 5 of these can be verified in parallel with a single forward pass of the target model. The target model may only accept the first 4 tokens (or whatever) but as long as the 5 forward passes of the draft model + 1 prefill of the target model is faster than 4 forward passes of the target, you will have a speedup while maintaining the exact output distribution as the target.
qeternity
·3 เดือนที่ผ่านมา·discuss
> They paid a billion dollars for a vibe coded mess just for the opportunity to associate themselves with the hype.

Lol no they didn't. It wasn't even an acquihire. They just hired Peter.

Maybe they are paying him incredibly well, but not a billion dollars well.
qeternity
·3 เดือนที่ผ่านมา·discuss
> It's not any company, its Meta and the channels they administrate come with a set of responsibilities and principles

Sorry, which laws stipulate these special responsibilities and principles?
qeternity
·3 เดือนที่ผ่านมา·discuss
> or if the model might actually have emitted the formatting tokens that indicate a user message.

These tokens are almost universally used as stop tokens which causes generation to stop and return control to the user.

If you didn't do this, the model would happily continue generating user + assistant pairs w/o any human input.
qeternity
·3 เดือนที่ผ่านมา·discuss
This does not solve the problem at all, it's just another bandaid that hopefully reduces the likelihood.
qeternity
·4 เดือนที่ผ่านมา·discuss
Yes, it is written for a specific audience.

That is not a reason for snark.

As other commenters have noted, it’s well written.
qeternity
·4 เดือนที่ผ่านมา·discuss
Yes, lots of things can create indeterminism. But nothing is inherent.
qeternity
·4 เดือนที่ผ่านมา·discuss
Yes, lots of things can create indeterminism. But nothing is inherent.
qeternity
·4 เดือนที่ผ่านมา·discuss
> LLMs are inherently non-deterministic.

This isn't true, and certainly not inherently so.

Changes to input leading to changes in output does not violate determinism.
qeternity
·4 เดือนที่ผ่านมา·discuss
> With prompt caching, verbose context that gets reused is basically free.

But it's not. It might be discounted cost-wise, however it will still degrade attention and make generation slower/more computationally expensive even if you have a long prefix you can reuse during prefill.
qeternity
·5 เดือนที่ผ่านมา·discuss
> Tradition warrants a negotiation phase when one party wishes to change the terms of an agreement, or becomes cognizant that the counterparty may wish to do the same.

They didn't change the agreement. One party violated it, and the other party withdrew as a result.

This is so vanilla. But people will moan because they want subsidized tokens.
qeternity
·5 เดือนที่ผ่านมา·discuss
Number of parameters is at least a proxy for model capability.

You can achieve incredible tok/dollar or tok/sec with Qwen3 0.6b.

It just won't be very good for most use cases.
qeternity
·5 เดือนที่ผ่านมา·discuss
I would guess you haven't done this in practice. Yes, of course inference is memory bound at low batch sizes. This is why we run larger batch sizes!

Also there does not exist any batch size > 1 where per-request throughput is equal to bs=1. Doing any batching at all will slow all intra-batch requests down.
qeternity
·5 เดือนที่ผ่านมา·discuss
Yes this article is full of misunderstanding. The main explanation of bottleneck is wrong: it’s the model weights which dominate memory bandwidth (and hence why batching multiple requests in a single pass increases total throughput). If copying user tokens was the bottle neck, batching would not achieve any speed up.

When an author is confused about something so elementary, I can’t trust anything else they write.
qeternity
·5 เดือนที่ผ่านมา·discuss
Sure, and again, she should do something else then.

She isn't entitled to have a large family and work whatever job she finds fulfilling.
qeternity
·5 เดือนที่ผ่านมา·discuss
If you have any understanding of history, it's naive not to.