CryptoTrigger

Freedom and Liberty. @chutes_ai full-port

[Chutes @chutes_ai]

The paper, if you want the math: https://t.co/YlwB3vIAHM

[Chutes @chutes_ai]

Most of the work inside an AI model is multiplying numbers. Parallax stores most of its weights as -1, 0 or 1, and at least half of those are zero, which a GPU can skip.

On one RTX 5090 that’s the difference between 209 teraflops and 3,352. Part of the jump is the card’s 4-bit mode, and skipping the zeros doubles it again. Those are the chip’s rated speeds, not measured ones.

It’s a big part of how one card hit almost 18,000 tokens a second.

[CryptoTrigger @CryptoTrigger1]

The @chutes_ai exit of 9000 $TAO today of course sucks but the reality of $dTAO is for people like me who have collected months of APY, we have more than offset this drawdown with interest.

Whales will come as easily as they leave. There’s never been as good a time to buy as now

[CryptoTrigger @CryptoTrigger1]

@opentensor @chutes_ai Truly groundbreaking. We’re sidestepping where others are blindly stepping forward

[CryptoTrigger @CryptoTrigger1]

How is this not the most vital and crucial vector of attack in the expansion of AI?

It is.

You can get in on securing the future at near all time low prices right now. This single subnet is multi-billions

@chutes_ai $TAO $dTAO

[Openτensor Foundaτion @opentensor]

Bittensor’s @chutes_ai trained Parallax 8B across hundreds of consumer GPUs around the world.

Now their latest preview shows it handling 256 AI requests simultaneously on a single gaming GPU.

The future of AI compute won't be confined to giant data centers.

[CryptoTrigger @CryptoTrigger1]

@const_reborn Dems were given this as a mandate by voters who think being anti AI is protecting their furry artist friends commission. Congrats you signed your future away

[CryptoTrigger @CryptoTrigger1]

@chutes_ai Parallax mentioned 🪂

[Chutes @chutes_ai]

How is it this fast? A small model, 4-bit math for the expert layers, and a fixed-size cache for most of the attention.

The Parallax paper: https://t.co/YlwB3vIAHM

[Chutes @chutes_ai]

Parallax runs at almost 18,000 tokens a second on a single RTX 5090.

That’s one consumer GPU answering 256 requests at once, on a vLLM fork that we put together.

The more one card can serve, the cheaper each answer gets 💪

[CoinAsia @CoinAsia_io]

NEWS: Tencent, whose Weixin and WeChat platforms reach 1.439 billion monthly users, has selected Chutes, a Bittensor subnet, as a launch partner for its new flagship AI model, Hy4.

The partnership puts @opentensor's decentralized AI infrastructure alongside one of the world's largest technology ecosystems.

Chutes offers competitive inference pricing at $0.525 per million input tokens and $1.5625 per million output tokens. This collaboration could bring greater visibility to decentralized AI networks and highlight their growing role in supporting large scale AI applications.

[CryptoTrigger @CryptoTrigger1]

@RadoTsc Would be good to see important info channeled through the main @chutes_ai X account. Spooks whales when there’s Discord chatter and no one really knows what’s happening

[Lex Tensor @Lex_Tensor]

@RadoTsc They clarified they won't be participating as a miner for this purpose, so no miner emissions will be directed to this. To my understanding, they believe they can fund this with revenue (which targets to exceed any costs related to it).

[Chutes @chutes_ai]

GLM 5.2 Fast is live on Chutes.

https://t.co/g2XkceWw7X's GLM 5.2, for chat and agents where the reply is on the clock. 1M-token context, 128K max output.

Here's what GLM 5.2 is good at, on https://t.co/g2XkceWw7X's published scores: 81.0 on Terminal-Bench 2.1, four points behind Opus 4.8 at 85.0, and 62.1 on SWE-bench Pro, up from GLM 5.1's 58.4. https://t.co/g2XkceWw7X built it for long-horizon tasks.

Base URL https://t.co/AwJu7ktgOt, model zai-org/GLM-5.2-Fast, same key as every other model ofc.

$2.45 per million input tokens, $7.70 out.

[CryptoTrigger @CryptoTrigger1]

@decentralized_1 @chutes_ai @lium_io Can’t disagree too much with that

[CryptoTrigger @CryptoTrigger1]

.@chutes_ai has a real engagement issue. The latest weekly newsletter is sitting on 30 likes and 2k views. This is the longstanding biggest subnet, now #2. @lium_io is getting 3-500 likes and >20k views regularly.

Chutes team, a revamping of comms wouldn’t go a miss

$TAO $dTAO

[CryptoTrigger @CryptoTrigger1]

@decentralized_1 @chutes_ai @lium_io If we set aside the pretty grim alpha token price performance, imo there’s no excuse for a subnet the size of @chutes_ai to be getting as little engagement as they do. They do amazing work but have problems promoting it effectively

[CryptoTrigger @CryptoTrigger1]

@Pedro0674615039 @chutes_ai @lium_io Yup their account is very robotic, feel like AI generated scheduled tweets. Could use more interactivity, the “we have added this model” tweets have lost the attention of the masses

[CryptoTrigger @CryptoTrigger1]

@Lex_Tensor @chutes_ai @lium_io Yeah fully agreed. Parallax is one of the most fascinating and incredible (if they pull it off) things in the space and I feel they could lean into it more. If @chutes_ai matched lium on the front-facing side it would only benefit all of $TAO

[CryptoTrigger @CryptoTrigger1]

.@BitcoinNews is sharing $TAO news because they know Bittensor is the ‘Bitcoin of AI’. Yes I know cliche term, but it’s the only project ideologically aligned with Bitcoin and technologically, and ethically, aligned with the values of deAI. $TAO is the solution to many problems

[CryptoTrigger @CryptoTrigger1]

@ThinkingUSD @inversebrah @tradingview 80% of the problem is this shit