Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Hy4 preview

tencent.com

Post reply on HN
Print view View original

211–220 of 261 posts

Re: Hy4 preview

#211

Post by mirekrusin »

LtWorf wrote: post #77
mirekrusin wrote: post #37

Earlier quoted context omitted.

You can open source dataset without all the details how it was assembled. Models are lossy compressed datasets you can pick up and amend (fine tune / continue training / alter) according to license they were released under. Hy4 is released under OSI approved Apache License 2.0.

So windows is open source because the binaries are a lossy compression of the original source?

You can't take windows binaries and continue development on them.

Model weight release is a snapshot/checkpoint you can take and resume training on new data, producing new model.

You don't need original training history to modify it further.

Re: Hy4 preview

#212

Post by algoth1 »

jamienk wrote: post #129

Genuine Q about word optimization/token density: If we create a stripped-down vocabulary with greater token density to use less resources and to resolve ambiguities earlier in the semantic process, aren't we creating NEWSPEAK and dragging along the worst aspects of it? The ambiguity and multi-valence of words is what creates more connections between words, increases the directionality of associations, and expands the…

It's my understanding that the llm is not literally thinking those words, they are just the conversion of the matrix multiplication results (numbers) into the tokens. So the matrix is "multiplying" concepts and directions to come up with the final answer - which produces a somewhat readable reasoning trace. As far as the llm is concerned the reasoning trace could be random (to us) symbols. In fact, the reasoning traces are not necessarily optimized for readability as much as they are an emergent property of the way a reasoning model is trained

Re: Hy4 preview

#213

Post by andai »

dakolli wrote: post #95
andai wrote: post #69

Earlier quoted context omitted.

Wait, what does that number mean? I thought it always uses the cache price when the prefix matches.

When the prefix matches a request sent to the same Providor. The thing is the TTL is different for each provider, some cache for 5 minutes some cache for 1hr. Its ideal to only use one provider per agent session / and per model with the best cache hit % if you care about costs.

But before 5m the hit rate is 100%, and after it's 0%? Why is there a probability?

Is there some stochastic process that takes place during those 5 minutes that determines whether or not you get the discount?

Re: Hy4 preview

#214

Post by dakolli »

RussianCow wrote: post #164
dakolli wrote: post #117

Earlier quoted context omitted.

I know what they're saying. Why would openrouter calculate it thay way lol. They obviously dont. Think for a sec, they arent idiots.

How else would you expect them to calculate it?

Do you really think they're docking points because cache invalidation due to provider switching? Seriously llms are frying ya'lls brain.

Re: Hy4 preview

#215

Post by jamienk »

algoth1 wrote: post #212
jamienk wrote: post #129

Genuine Q about word optimization/token density: If we create a stripped-down vocabulary with greater token density to use less resources and to resolve ambiguities earlier in the semantic process, aren't we creating NEWSPEAK and dragging along the worst aspects of it? The ambiguity and multi-valence of words is what creates more connections between words, increases the directionality of associations, and expands the…

It's my understanding that the llm is not literally thinking those words, they are just the conversion of the matrix multiplication results (numbers) into the tokens. So the matrix is "multiplying" concepts and directions to come up with the final answer - which produces a somewhat readable reasoning trace. As far as the llm is concerned the reasoning trace could be random (to us) symbols. In fact, the reasoning trac…

This is different from the final output? I thought all traversals of the chain of language are through these mathematical means.

You could tokenize the word "good" to resolve to only represent 'the opposite of "bad"' and to exclude "as opposed to evil", demanding that this second meaning will be reserved only for the new token "double-minus evil". You've therefore forced the words to be more univalent with no overlapping tangled associations. This, it could be argued, makes thing clearer, makes things take fewer hops to go from token to token, makes the path be straighter. In English the terms conflate and wobble back-and-forth, hide each other's meanings, only to pop up again unexpectedly, sometimes confusingly, or rhetorically, metaphorically, or ambushing us manipulatively. But these "swerves" are not only de-optimizations, they are the flow of poetry, the drama of masks, etc etc etc.

Re: Hy4 preview

#216

Post by eli »

redox99 wrote: post #74
minimaxir wrote: post #2

Hy4 apparently has ludicrous traction on OpenRouter already ( https://openrouter.ai/tencent/hy4-preview ), with trillions of tokens processed in a couple days: more than GLM 5.3 in a week. That said, it's relatively cheap with a 5% cache cost when everyone is still doing 10%/20% cache costs, so Hy4 may be more compelling.

It's very likely tencent games those stats, buying their own tokens.

Openrouter tracks what apps are using the model and the top ones for hy4 are all different coding harnesses.

I guess it could be fake but seems more likely people are just trying it out. Hy3 was a very strong and underrated model.

Re: Hy4 preview

#217

Post by Gravityloss »

dotancohen wrote: post #177
beefsack wrote: post #91

Earlier quoted context omitted.

I can't help but imagine agents using caveman speak sometimes start behaving in a stereotypically caveman manner, even if it's subtle. Is there a chance the agent does less reasoning because of it?

Caveman invented fire, the wheel, domesticated wild plants and animals, organised society, survived the Toba catastrophe, cooked food, and was having sex ages before you and me. Don't write him off as stupid.

And I wonder how they actually spoke. Since there was no visual communications medium except for cave art. (Some of which is very excellent. Try drawing 3d curved horns in perspective.) So people would have used verbal communication more. Also no written word. So one would expect there to be quite a lot of oral tradition. Like people reciting poem form epics.

If we assume the time is before farming, population density would have been low and limiting culture. Hunter-gatherers might have travelled a lot more than farmers with a homestead though.

Re: Hy4 preview

#218

Post by dominotw »

dakolli wrote: post #32
martinald wrote: post #7

Earlier quoted context omitted.

I wrote about this a couple of weeks ago. It's actually often the biggest cost and it tends to be hidden away on most platforms! https://martinalderson.com/posts/watch-out-for-cache-read-co... Btw I still haven't came across any decent model that is Seems like a bit of an opportunity for someone to take - drop cache read costs significantly.

That's because Deepseek invented the paradigm of prompt caching, they are the SOTA when it comes these techniques. Despite them open sourcing all their research, nobody beats them. edit: I do wish openrouter would let you sort providers by Cache Hit % and Cache cost. These are the only things that matter to me at this point when choosing a provider.

> open sourcing all their research,

is this true?

Re: Hy4 preview

#219

Post by Aboutplants »

simonw wrote: post #44

> [...] Let's maybe add a helmet? It could improve riding theme, but may obscure head. Maybe a small cycling cap or helmet? The user didn't ask; can add red helmet? Might be cute. But pelican with big beak; a helmet might obscure. Better maybe no. > Maybe add sunglasses? no. > Maybe add water? no. https://tools.simonwillison.net/markdown-svg-renderer#url=ht...

Halfway through it states “Let's mentally compose SVG.”

Is this a common thing? I’ve never seen it before, the “mentally compose”

Re: Hy4 preview

#220

Post by knollimar »

nextaccountic wrote: post #156
hgoel wrote: post #78

Earlier quoted context omitted.

Scientific physics simulations - even the frontier models just engage in rationalization of obviously unphysical results instead of understanding the system. They have the rote knowledge but fail to apply it unless their hand is held through the process.

Today's models can just write code to run the simulation instead

They choose not to unless you beg them, and of course they double down on not running it once they suggest reasoning qbout it is sufficient.
Post reply on HN