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

DSpark: Speculative decoding accelerates LLM inference [pdf]

github.com

Post reply on HN
Print view View original

141–150 of 393 posts

Re: DSpark: Speculative decoding accelerates LLM inference [pdf]

#141

Post by nicce »

flipped wrote: post #103
LeBit wrote: post #92

Earlier quoted context omitted.

True. But at some point you got to close your eyes and take a step forward. It’s like with VPN providers. Is Mullvad actually collaborating with law enforcement? They very well could be. It is a calculated risk. Is DeepInfra actually logging and training or selling the logs? They could be.

Mullvad has proved it doesn't collect. It's laughable to even suggest it. They have been raided multiple times, tons of audits, does bleeding edge research on privacy preserving tech, donates to GOS, etc etc. You don't see this kind of VPN company at all because none exists.

With Mullvad the threat space is also different. Most of the data is end-to-end encrypted anyway with proven methods. With LLMs you can't do that yet.

Re: DSpark: Speculative decoding accelerates LLM inference [pdf]

#142

Post by wqaatwt »

theturtletalks wrote: post #83
intended wrote: post #80

Earlier quoted context omitted.

The world runs on incentives. Altruism/Self-serving are down stream of that. Wikipedia is altruistic, and serves humanity quite well.

Open-source is also altruistic. If DeepSeek does become self-serving once they get the top spot, it doesn’t take away from the altruistic contributions that they made towards open models.

> Open-source is also altruistic

Contributing to it might not necessarily be. Most open source development is funded by large companies after all and from their perspective it can function as a cost saving measure. Allowing them to focus on their core products and removing the possibility of their rivals from getting a competitive advantage due to having a superior low level stack under their product.

Which is why open source is so successful in areas where software is a cost-center but mostly failed for consumer products (since spending resources on them would actually be altruistic unlike e.g. Linux kernel development)

Re: DSpark: Speculative decoding accelerates LLM inference [pdf]

#143

Post by Dibby053 »

brookst wrote: post #114
theturtletalks wrote: post #83

Earlier quoted context omitted.

Open-source is also altruistic. If DeepSeek does become self-serving once they get the top spot, it doesn’t take away from the altruistic contributions that they made towards open models.

And ultimately the motivation for those contributions just doesn’t matter, except to those who like to anthropomorphize company and argue about their souls.

People who donated to OpenAI in its early years might disagree on that.

Re: DSpark: Speculative decoding accelerates LLM inference [pdf]

#144

Post by c7b »

lwansbrough wrote: post #20
tomalaci wrote: post #16

Earlier quoted context omitted.

Probably because American AI companies are on the hook for quite a lot of investment money. I think they are trying to find the magical moat to justify their valuation. Revealing optimizations similar to these would pretty much reduce their competitive position.

Chinese labs are also still behind, so they’re incentivized to collaborate and have no reason to do it in private. I suspect their tune will change if they ever take the lead..

The question is also what game they're playing. Deepseek came out of a hedge fund. I think it's no coincidence that their publications tend to have a large impact on AI stock prices.

Destroying the growth story of overvalued stocks is an interesting investment strategy. It's not even new. Shortsellers understandably get terrible rep from execs, but their actions are more often in the public interest than you'd think. Normally it's exposing fraud, but here we get the really fortunate side benefit of what could eventually amount to the most significant contribution to the general software community since Linux.

Re: DSpark: Speculative decoding accelerates LLM inference [pdf]

#145

Post by wqaatwt »

breezybottom wrote: post #108
roenxi wrote: post #54

Earlier quoted context omitted.

It's a standard take since it is how markets tend to work. They aren't powered by altruism, it is a big system for turning greed into good results. We don't have all this stuff because people suddenly woke up one morning and decided to be nice.

Yes but there's more to the world than markets.

On aggregate mainly because humans often tend to behave “irrationally” due to various reasons though

Re: DSpark: Speculative decoding accelerates LLM inference [pdf]

#147

Post by kelipso »

brookst wrote: post #114
theturtletalks wrote: post #83

Earlier quoted context omitted.

Open-source is also altruistic. If DeepSeek does become self-serving once they get the top spot, it doesn’t take away from the altruistic contributions that they made towards open models.

And ultimately the motivation for those contributions just doesn’t matter, except to those who like to anthropomorphize company and argue about their souls.

Or if they want to do anything close to predicting what they will do in the future, like curious and interested humans tend to want to do.

Re: DSpark: Speculative decoding accelerates LLM inference [pdf]

#148

Post by wqaatwt »

woctordho wrote: post #105
lelanthran wrote: post #70

Earlier quoted context omitted.

I don't understand what is interesting about it: it's the default. Markets don't run on altruism.

And humans don't run on markets.

Mostly they kind of do since we do live in an utopian society of unlimited abundance. Extremely few people can afford to (or want to) spend a very large number of working hours without ever getting anything directly in return for it.

Re: DSpark: Speculative decoding accelerates LLM inference [pdf]

#149

Post by Alifatisk »

StizzurpXDD wrote: post #146

DeepSeek is, as I feel currently, the sole AI company which is actually trying to innovate rather than top mere benchmarks. Others like OpenAI, Anthropic and Google are mostly just competeing with each rather than keep innovating around the clock.

> DeepSeek is, as I feel currently, the sole AI company which is actually trying to innovate rather than top mere benchmarks.

I'd also include the other Chinese labs like Moonshot (behind Kimi) and Z.ai (behind GLM). They are innovating and continue openly sharing their research to the public. I believe the founder of Moonshot even shared 40 minute video on Twitter where he goes through techniques that powers Kimi.

Re: DSpark: Speculative decoding accelerates LLM inference [pdf]

#150

Post by nmfisher »

baxtr wrote: post #85
tomalaci wrote: post #16

Earlier quoted context omitted.

Probably because American AI companies are on the hook for quite a lot of investment money. I think they are trying to find the magical moat to justify their valuation. Revealing optimizations similar to these would pretty much reduce their competitive position.

Who is financing DeepSeek and what are they expecting in return?

Until recently, DeepSeek were self-financed (it was a spin-out from a hedge fund). They just raised ~50million RMB (US$7bn), and according to media [0] (which admittedly can be unreliable), the lead investors were:

1) The CEO himself 2) Tencent 3) CALT (the battery company) 4) NetEase (internet/media company) 5) JD.com (ecommerce) 6) Chinese investment firms

What are they expecting in return? I'd say the same thing that all those investors in OpenAI and Anthropic are expecting - profit.

[0] https://finance.sina.com.cn/stock/vcpe/2026-06-11/doc-iniazi...

Post reply on HN