Yi Cui

onekq

24 20 1

AI & ML interests

Benchmark, Code Generation Model

Recent Activity

repliedto their post about 2 hours ago

I added ASD-STE100 to global claude.md

posted an update 1 day ago

I added ASD-STE100 to global claude.md

posted an update 10 days ago

What do you plan to use Muse for?

View all activity

Organizations

replied to their post about 2 hours ago

I transformed a wordy repo:

Size

Words: 115,559 → 124,979 (+8.2%)
Sentences: 4,795 → 10,983 (+129%)

Sentence length

Average words per sentence: 24.1 → 11.4 (−53%)
90th-percentile words per sentence: 46 → 20 (−57%)
Longest sentence: 175 → 62 words (−65%)
Sentences over 20 words: 53.1% → 8.0% (−85%)
Sentences over 25 words: 41.6% → 2.5% (−94%
Sentences over 40 words: 15.8% → 0.2% (−99%)

Paragraphs

Paragraphs with more than 6 sentences: 1.2%

Readability

Flesch reading ease: 54.1 → 72.5 (+18 points)
Flesch-Kincaid grade: 11.7 → 6.0 (−5.7 grad

Vocabulary and grammar

Unique words: 7,233 → 5,796 (−20%)
Passive voice per 1k words: 8.5 → 5.7 (−33%
Complex tenses per 1k words: 1.5 → 0.5 (−66%)
"-ing" words per 1k words: 26.9 → 12.2 (−55

Punctuation

Semicolons per 1k words: 9.8 → 0.9 (−91%)
Em dashes per 1k words: 8.9 → 0.1 (−99%)

posted an update 1 day ago

Post

I added ASD-STE100 to global claude.md

3 replies

posted an update 10 days ago

Post

What do you plan to use Muse for?

replied to their post 10 days ago

Can't fine-tune or prompt engineer this model so you have to accept its accuracy as is. Add other harnesses if the accuracy is not as good

replied to their post 12 days ago

Really no idea. Just wait for the open source ones to come out

posted an update 14 days ago

Post

3194

My takes on Jev

1. Very likely a small model. You can certainly pretrain, but I would grab an existing base model, say Qwen 3 class

2. The new RL method is a breakthrough, classification doesn't need to align with human preferences

3. The new output is an overstatement. It's just a new LM head. Of course autoregressive decoding can be used for classification: it takes just a few tokens to express the output. Think twice: are you sure classification doesn't need few-shot, CoT, or reasoning? All of these depend on auto-regressiveness

4. It carves out a market already existing, which is now served by oversized LLMs (hence overpaid), e.g. LLM as judge, labeling

5. Jevons effect will kick in, promoting more modeling efforts for small budget teams. It might even accelerate RSI

7 replies

posted an update 16 days ago

Post

Not your weights, not your products.

This doesn't feel true at the beginning, but suddenly becomes true after PMF

1 reply

replied to their post 21 days ago

🤣

posted an update 21 days ago

Post

4486

I turned off subagents in Claude Code. Am I a minority?

5 replies

posted an update about 1 month ago

Post

1508

CoT: 💬💬💬💬
Astra: 🧠🧠🧠💬

replied to their post about 1 month ago

Really appreciate everyone's knowledge sharing and critique here.

Isn't this a gloomy picture that no frontier model can be run on the edge? Smaller models are for workflows and automations.

We are all used to conversing with a frontier model and let it run things on your device. A weaker model will degrade your current experience hence no adoption.

replied to their post about 1 month ago

Wow! thx for all the works here. I wish more people can see the methodology.

My Mac is only 16GB 😅 We need to find one of those people above who have big budget
https://www.ebay.com/itm/257712960417

posted an update about 1 month ago

Post

1003

My take on device-side inference: it's all about high bandwidth memory (thinking about it, this holds for the cloud too).

MacBooks enjoy incidental capacity of apple silicon, but per-device RAM is too low (16 to 24GB), only sufficient for a decent SLM. 512GB is the highest you can go (Kimi K2*). Counting MLX downloads of Kimi K2* on Huggingface, I estimate the user base to be <25K.

On the other hand, the newly debuted DGX station (Nvidia) has 748GB, which can fit in the latest Kimi, DS, and Qwen. Also the quantization options of CUDA is way better than MLX.

For high-end inferencing, I place my bet on workstations over Macs.

7 replies

posted an update about 1 month ago

Post

167

My biggest takeaway from Ben Thompson interview is the legacy of this round of "bubble".

For railroad, it was the track, and dot com, fiber. Compared to these two, GPUs depreciate too fast.

The answer is power plants.

posted an update about 1 month ago

Post

122

NVidia?!

posted an update about 1 month ago

Post

2014

Back of the envelope calculation: Ox Alpha has been out for a week with 130K users and 7T tokens burned.

Method 1: Assuming Ox Alpha is the GLM 5.3 class, it has roughly the same active param count as DeepSeek V4 Pro (~40B vs 49B), derive the cost by the floor price DS has ever published.

Method 2: Assuming the users are concentrated within an 8-hour working window each day, derive number of H800 nodes needed (~700 nodes at $2/GPU-hour).

In both methods, I assume 90/10 IO split and 60% cache hit. Both methods come to $2M.

I think the ROI is awesome: (1) publicity and (2) data harvesting.

1 reply

replied to their post about 1 month ago

Whoever this is, they give away so much compute for a model launch

replied to their post about 1 month ago

Most likely

replied to their post about 1 month ago

Lots of SLMs, like the 27b one from Qwen

posted an update about 1 month ago

Post

2492

My guess on Ox Alpha -> GLM

27 replies

Yi Cui

AI & ML interests

Recent Activity

Organizations

onekq's activity