atemoya (@atemoyacoding) header
atemoya (@atemoyacoding) profile picture

無名プログラマー。最近はAIとかMLなんかを作ってるらしいですよ。 バイブコーディングをメインにしています。(ご理解のほどお願い致します) 多分フォロバする(しばらくは) DMについて 基本的に既読にはしますが技術的や質問等のDM以外は応答し兼ねます。申し訳ないですがご了承ください。

Github, Hugging Face, Zenn, X
Joined August 2026
Photo by atemoya (@atemoyacoding)Photo by atemoya (@atemoyacoding)Photo by atemoya (@atemoyacoding)Photo by atemoya (@atemoyacoding)Photo by atemoya (@atemoyacoding)Photo by atemoya (@atemoyacoding)Photo by atemoya (@atemoyacoding)Photo by atemoya (@atemoyacoding)Photo by atemoya (@atemoyacoding)Photo by atemoya (@atemoyacoding)
好きな絵を1枚入れたら、デスクトップに住みはじめました。 目で追って、撫でると反応して、話しかけると答える相棒アプリ「Castor」を正式リリースしました。MacとWindows(Preview版)に対応。 無料・オープンソースです。誰かの机の上に、ひとりでも増えたら嬉しいです。 castor.arils.jp
v1.0.0の正式リリースが終わりました。 新機能は ・ダウンローダーでの容易な導入、アップデート ・一部の修正(GitHubには記載済み) ・UIの刷新 です。
1
27
4
162
22,223
Introducing MAI Code 2 and Code 2 Flash. Code 2 brings frontier price-performance for everyday enterprise coding tasks. Code 2 Flash brings affordable and high-quality coding for routine work at scale. Try both today in GitHub Copilot.
45
105
42
1,027
69,166
atemoya retweeted
GPT-6.2 Astra—a frontier model built for your hardest projects. It sets new highs on evals across professional work and scientific research at less than a third of the cost per task of GPT‑6 Astra. You’ll see the difference in things like slideshows, websites, and 3D designs.
207
368
411
4,989
1,064,221
atemoya retweeted
Some of you have been asking very politely. Some of you have just been asking. GPT-6.2 Astra and Sol are now available. Super efficient and built to perform where it counts—the real world. openai.com/index/introducing…
2,165
3,549
3,604
35,047
8,781,845
Interactive 3D Scene Built with Three.js
1
1
26
5,135
#SenseNova-Loop-9B is officially here — now #OpenSource! Just 9B parameters, competitive with Qwen3.8-27B across multiple benchmarks. 🔹 Big gains over Preview: NL2Repo 19.91 → 41.36; AutomationBench 14.33 → 36.67; GAIA 37.86 → 69.90 🔹 Loop + mHC: 32 unique layers, 56 layer executions 🔹 Day-0 4-bit AWQ weights (~4.9GB), with VRAM needs as low as ~9 GiB at 64K context 🔹 Up to 512K context, with text and image inputs See what a 9B model can build: animated posters, interactive websites and 3D scenes. 💻 GitHub: github.com/OpenSenseNova/Sen… 🤗 HF: huggingface.co/collections/s… 👾 Discord: discord.com/invite/BuTXPHmQu…
47
155
70
1,239
112,262
I was the opening act for a family of ducks. Thank you, Berlin. What a GTC. Europe is building its AI ecosystem and economy, from AI factories to agents to robots. DSX POD: Vera Rubin modular factories built, cabled and tested in the factory, then delivered ready to produce intelligence. Agents: models, harnesses, sandboxes, knowledge and tools. NVIDIA Agent Toolkit brings the pieces together so companies control what their agents know, access and do.  NVIDIA OpenShell enhances safety. Physical AI: new customers across AI-RAN, robotaxis and robotics. Personal AI: after four years building with Microsoft, RTX Spark brings personal agents to the Windows PC. Thank you to President @EmmanuelMacron, Prime Minister @andyburnham and Chancellor @bundeskanzler for hosting me. Great to celebrate Sferical One with Sweden’s technology leaders. And thank you to President @TokayevKZ for the warm welcome. And to our partners and NVIDIA teams: thank you for making it happen. The keynote is here: youtu.be/rF1EsryCAwc
Microducks on stage for Jensen Huang’s famous keynote! We couldn’t be prouder of our little ones. 🥹
4,981
912
257
13,881
10,327,898
Over the past week, I’ve been overwhelmed by the love and support of friends, industry colleagues, and people I've never met. Thank you to everyone who has shown kindness to my family and me. It means the world to me. I came to the United States 53 years ago, and becoming an American citizen is one of the greatest gifts and proudest moments of my life. NVIDIA has been my life’s work. Building it into the company it is today alongside my colleagues has been a privilege and an honor. Nowhere but in America could a company like NVIDIA be possible. I love our country, and I love NVIDIA. I did not live up to the standards expected of everyone at NVIDIA, and I have made serious mistakes in my personal life. I created problems for the Board that I deeply regret. I own my mistakes completely, and I am committed to cooperating with the Board’s independent investigation. Since my departure, I’ve seen an outpouring of calls from NVIDIA’s employees, investors, business partners, and customers for me to return as CEO. Many continue to reach out to me directly as the company navigates complex technology, market, competitive, and geopolitical dynamics. NVIDIA is a once-in-a-generation company. If the Board of Directors decides that my return is in the best interest of our shareholders, our employees, the company, and America, I would be honored to answer these calls and return as CEO. Thank you again to everyone who has shared their good wishes. I am profoundly humbled by your support. To my family: I love you, and I will spend the rest of my life being worthy of yours. Jensen
58,173
118,748
24,069
1,132,811
52,978,014
2
4
78
12,899
⚡Meet Hy4 flash, the cheapest model for everyday productivity. Matches Claude Haiku 5.5 (high) on daily work (human blind tests), yet 18x task cost reduction. API pricing (per 1M tokens): $0.003 cached · $0.070 input · $0.281 output. 🔗:hy.tencent.ai/research/hy4-f…
219
248
227
2,791
799,161
atemoya retweeted
Token efficiency and cost: Qwen4-Max outperforms Qwen3.8-Max with fewer tokens. On Work360, token usage drops by approximately 24% (Xhigh) and 35% (High); on Terminal-Bench 4.0, by about 48% and 49%. In our Work360 evaluation, the average cost per task drops from $4.43 to $1.67.
15
27
16
740
125,263
atemoya retweeted
📢 Meet Qwen4-Max, your new AI teammate for work, creativity, and discovery! Qwen4-Max is built on a new MoE architecture with native vision and a 1M-token context window. Highlights: - Outperforms Qwen3.8-Max with up to ~50% fewer tokens, while average cost per task drops over 60% in our internal evaluation. - Advances real-world productivity through greater proficiency with professional tools, stronger long-horizon execution, and higher-quality deliverables. - Handles real tasks, including 3D modeling, game development, manufacturing, finance, law, healthcare, and frontier scientific discovery. - $1.5/M tokens for input, $4.5/M tokens for output, and $0.075/M tokens for implicit caching — all lower than Qwen3.8-Max, with implicit caching down by 70%. The API is live on QwenCloud. You can also try Qwen4-Max on Qwen Studio, QwenWork and Qoder. Start building today! 🚀 - Blog: qwen.ai/blog?id=qwen4-max - API: qwencloud.com/models/qwen4-m… - Token Plan: qwencloud.com/pricing/token-… More to come! The open weights of smaller Qwen4 models will be released. Stay tuned. 👀
830
1,598
1,284
14,821
2,466,889
Transformerだ…… Embeddingが全部1で出力がtoks という単語に固定されててAttentionとかFFNの重みが全部ゼロなだけだから……(世間一般ではベンチマークという)
5
274
4688円もかからずに作りました ちなみに実験せず、最初からこの完成形を作るのにかかる推定額は約300円です。 300円で9Bに近づけたから満足、だけどこれで終わってたら面白くないのでまだまだやります!
35B の MoE を、MoE のまま 9.4B に削りました(−73%)。 Qwen3.5-35B-A3B のエキスパートを1つずつ違う幅で残し、約1500万トークンの LoRA で回復。AIME 2026 は 20.7/30(Qwen3.5-9B は 22.3)。 研究プレビュー Astrantia を公開します🧵 (English is below)
1
10
838
300円、22時間で作れるはず 研究時間で数週間かかりましたが......
96
学習結果をまとめたGitHubは近頃出します! 今月末までに弱点をなるべく対策したモデルも出す予定なので応援してもらえると助かります! ベンチマークも日本語もあまり良い方ではないですが、今後改善していきます!今はあくまで普通に学習するのと少し似た性能を大きなモデルから継承する研究です。
146
4bit化ができたので共有します。性能はだいぶ落ちやすいと思うので余裕があればFP16をお勧めします! huggingface.co/Takenoko12345…
Replying to @atemoyacoding
4bit量子化したものも近いうちに出します!
1
160
学習結果をまとめたGitHubは近頃出します! 今月末までに弱点をなるべく対策したモデルも出す予定なので応援してもらえると助かります! ベンチマークも日本語もあまり良い方ではないですが、今後改善していきます!今はあくまで普通に学習するのと少し似た性能を大きなモデルから継承する研究です。
35B の MoE を、MoE のまま 9.4B に削りました(−73%)。 Qwen3.5-35B-A3B のエキスパートを1つずつ違う幅で残し、約1500万トークンの LoRA で回復。AIME 2026 は 20.7/30(Qwen3.5-9B は 22.3)。 研究プレビュー Astrantia を公開します🧵 (English is below)
1
1
2
503
4bit量子化したものも近いうちに出します!
1
213
日本語に弱い問題に対処するため、DSHのプロキシを開発しました。MITライセンス(モデルはPLaMo 3.0なのでそっちのライセンスに従ってください)です。 デフォルトモデルとして入れたPLaMo 3.0に感謝します。 GitHub: github.com/atemoyacode-sudo/…
35B の MoE を、MoE のまま 9.4B に削りました(−73%)。 Qwen3.5-35B-A3B のエキスパートを1つずつ違う幅で残し、約1500万トークンの LoRA で回復。AIME 2026 は 20.7/30(Qwen3.5-9B は 22.3)。 研究プレビュー Astrantia を公開します🧵 (English is below)
2
24
1,175
35B の MoE を、MoE のまま 9.4B に削りました(−73%)。 Qwen3.5-35B-A3B のエキスパートを1つずつ違う幅で残し、約1500万トークンの LoRA で回復。AIME 2026 は 20.7/30(Qwen3.5-9B は 22.3)。 研究プレビュー Astrantia を公開します🧵 (English is below)
4
22
1
157
9,279
Hugging Face:huggingface.co/Takenoko12345… (非公式の派生モデル) 補足、性能が高いわけではなく、自由なウェイトで作り変えるのにほとんど学習を使わずにできるという研究です。(今後なるべく元のウェイトの性能を引き継ぐ研究もするので応援して欲しいです!フォロー等をしていただけると喜びます)
2
1
11
826