YaqiZHANG @Alphatu4 in MENA｜Engineer ➡️Author&Founder&Writer | |NerdDiplomat🤗 | Author of 2 Books |Speaker of @pku1898 @penn @ApacheCon
Joined February 2022
- Tweets 4,747
- Following 1,338
- Followers 2,967
- Likes 4,795
863 Photos and videos
Love fun projects like this lol
Jan 14
Had Claude Code build a little plugin that visualizes the work Claude Code is doing as agents working in an office, with agents doing work and passing information to each other. New subagents are hired, they acquire skills, and they turn in completed work. Fun start.
4
5
63
6,158
❤️
14 Nov 2025
all my life I've just wanted Cline to be associated with Nous Research
1
2
19
6,437
Alphatu🐇 retweeted
15 Nov 2025
Join Tsinghua’s LIVE for more info on the advanced programs in industrial engineering and Engineering Management. Learn more about the admission process, which focuses on innovative research such as human factors and system engineering!
x.com/i/broadcasts/1lDxLBjQR…
3
3
10
1,979
We are also now working closely with cline to make Hermes even stronger in Cline with direct work on training and optimizing built around their coding harness!
Check out Hermes 4 70b & 405b models from Nous Research. Now available for you through both the Nous Research and Cline providers.
(Nous Research brand booklet linked below)
4
6
103
10,521
Alphatu🐇 retweeted
5 Jan 2024
First Milestone📌
Thai language🇹🇭 RAG integration with @llama_index, @weaviate_io, and #SeaLLM on Float16.cloud.
This blog (or notebook) demonstrate how to manage a non-English language RAG system without OpenAI🔥
HuggingFace and OpenAI-like
blog.float16.cloud/thai-rag-…
3
7
25
16,679
Alphatu🐇 retweeted
10 Apr 2025
"Follow the gradient" That's great.
We are learning so much from open source, shipping, screwing up and figuring it out.
Plans are good, reality is better
10 Apr 2025
I have never seen it expressed exactly like that, but I wholeheartedly endorse it:
Feedback beats planning.
My plea at Meta was “No grand plans, follow the gradient of user value”.
15
62
829
67,063
❤️
A big milestone for Hermes.
We did a lot of work to make a frontier level openmodel that does not dictate what expression you can elicit from the model.
Super strong at math, coding, STEM, and creativity.
Model Weights: huggingface.co/collections/N…
Check it out 👇
3
460
Alphatu🐇 retweeted
1 Sep 2025
Anecdotally, I’ve found the people most vocal and showy about grinding hard (9-9-6) tend to have less throughput than a garden variety workaholic.
I suspect this is because they’ve internalized endurance pace all the time. And loose the ability to sprint when needed.
65
58
1,770
536,340
Alphatu🐇 retweeted
29 Jul 2025
Crazy week!
@moritzthuening ported his project from Wormhole to Blackhole with 1-line of code change.
@OnDemandai has a killer agentic workflow available in the cloud and on-prem for @tenstorrent users
@gokoyeb continues to expand TT offerings
🥹 it’s a beautiful thing
3
4
22
4,579
🏆Always the No.1 @teknium
20 Jul 2025
Congrats to our post training team who worked on the Hermes 3's dataset - @teknium, @nullvaluetensor, and outside contributor @intrstllrninja - on creating the now #1 Trending dataset on HuggingFace!
1
1
2
420
Alphatu🐇 retweeted
24 Jul 2025
Another image -> 3D -> v2v (wan 2.1) render. The quality you can get is awesome. And because it's 3D mid workflow you can do arbitrary camera position / movement etc.
Still 10 hour rendering time 🤡
31
8
168
15,199
We are honored to have you here sharing your expertise with us. Everyone has been delighted.🙏
@jimkxa
@DavidBennett__
#riscv
1
1
3
173
Alphatu🐇 retweeted
25 Jul 2025
The Psyche office hours is beginning in 20 minutes in our Discord - discord.gg/nousresearch
See you there!
22 Jul 2025
Join the team behind the decentralized training projects Psyche and DisTrO for an office hours session in Nous Research's discord - Thursday evening, 6PM PST
Discord Link: discord.gg/NousResearch
5
8
91
27,898