座って半畳寝てZizzy

趣味、ゲーム旅行AI

[座って半畳寝てZizzy @zizzyjp]

26歳になりました。世界一幸せです。やっぱ大吉だわ

[座って半畳寝てZizzy @zizzyjp]

deepseek v4楽しみだ
プレビュー版ずっと使って来たからな

料金設定も気になるところ

[座って半畳寝てZizzy @zizzyjp]

ボール奪ってまた中央に持って行こうとしたあの瞬間こわってなったブラジル強すぎる

[座って半畳寝てZizzy @zizzyjp]

えーこれで負けるのかぁ
あんなにディフェンス頑張ってたのにキツいミスだなぁ

[ピットイン @ToyPitin]

【ポケカ】抽選販売のご案内です！

◆応募方法：@ToyPitinをフォロー＆このポストをRP
◆応募締切：6/26（金）20時
◆当選発表：DMにて
◆購入期間：6/27（土）～6/28（日）

当選した方は《スタートデッキ100 バトルコレクション》を１個ご購入いただけます。
つづく

[IO @useioxyz]

NVIDIA Nemotron is soon on IO.

NVIDIA's open frontier model — Nemotron 3 Ultra — now routes through private inference. Open weights, sealed prompts.

→ Frontier reasoning at scale — 550B MoE (55B active), built for agents, coding, and deep research.
→ 1M-token context — hand it whole codebases or stacks of documents.
→ Open-weight, so it sits in the routing layer right next to Kimi and Llama.
→ Still zero logs, zero retention, a signed receipt on every reply.
→ Your prompt reaches NVIDIA's weights. Nothing else does.

Claude. Llama. Kimi. GPT. Now Nemotron. One interface, one guarantee.
Input. Output. Nothing. And we prove it.

https://t.co/2JGftbMzWe | @nvidia

[Daniel Lougen @DJLougen]

hive v0.6 is out 🐝

GPT-2 is a pre-agent-era model. 2019. No instruction tuning, no tool training, no RLHF, never saw an agent loop in pretraining.

Wrap it in hive (CPU routing + causal memory) and it resolves 85% of SWE-bench-lite instances.

The agentic capability isn't in the weights. It's in the scaffold.

https://t.co/H1TzSQkpWA

[Nous Research @NousResearch]

We are excited to join Nvidia's Nemotron Coalition of leading AI labs working together to advance open frontier foundation models.

To celebrate we have partnered with @nvidia and @nebiustf to provide 2 free weeks of the new Nemotron 3 Ultra model on the Nous Portal!

[座って半畳寝てZizzy @zizzyjp]

Gemma4-12Bきた
8GBで動くビジョン
これは楽しみ
ゲシュタルトチームはどうするのかな？
最近はdense27Bよりも9B派の俺的には刺さる
4090×1はもちろん、MacBook16GBでも動くなんて素敵
ちょうど欲しかったんだよね

[Kyle Hessling @KyleHessling1]

BREAKING! Qwopus 3.6 27B is LIVE!

Thank you for your patience on this one, but I believe you'll find the wait was worth it!

We've benchmarked this thing up and down, verified that it holds at least a 75.25% (152/202) in the initial 202 SWE bench solves. Not a full run of 500, but it shows the agentic coding quality from the original 27B is retained while adding all of the additional Qwopus benefits across many domains. As always, Jackrong is absolutely cooking here!

COT quality has improved significantly through the inversion techniques from our Negentropy proof of concept. It also went through thorough curriculum training. You can check out the MMLU pro benchmarks on the model card, but it improved a whopping 10 points over the base model in physics, as well as meaningful jumps in Chemistry, business, and computer science.

However, the best part is that I was able to build an entire survival shooter game using this local model entirely. I genuinely was blown away by the results, which you can play right now on my HF space (link in comments below). "Qwopus Commander" was completed in 9 turns of Qwopus 3.6! To test the new long context training, I made it re-output the entire 3000+ line program each turn, and it would make fixes and add features that I requested in large prompts, while perfectly replicating the entire rest of the game from context. What's more is that I did it all at Q8 KV cache quantization, and never had an issue over the entire 303k token run!

IMPORTANT: Run it at --temp 0.75 to 1. Mess with it in that range for your use case. Higher temp actually lets the fine-tune shine and be exploratory and is also more stable. Swe Bench was run at temp 1, the game was built mostly at 0.8!

We're so blessed to have all of you here and using the models! The support means so much! Please let me know what you build with it in the comments! Or if you have any issues getting it up and running, I will try my best to get back to you!

Looking forward to seeing what you legends produce with it this weekend!

https://t.co/AEl3APtTLk

[DeepSeek @deepseek_ai]

We are making our discount permanent! 🎉

Enjoy building with DeepSeek-V4-Pro and bring your innovative ideas to life! 🚀

[Daniel Lougen @DJLougen]

Rust-Brain v1.4.4 — structured memory for AI agents, built in Rust. I let qwen 3.7 have a go at it, and wow has it improved!
Query search speed used to be 16x slower than md, now it is only 1.9x slower but is a far more improved format.

Markdown dumps your whole file.
RBMEM returns the right sections.

→ 3.8× more precise than Markdown
→ 70% fewer tokens per query
→ Graph-aware recall (100% neighbor retrieval)
→ RBForge absorbed — MCP runtime tool creation is
now part of the repo
→ AES-256 encryption per section
→ SAT planning built-in
→ 285 tests

https://t.co/fHsiUijRnG

[Teknium 🪽 @Teknium]

4 big upgrades to Hermes Agents speed today

`hermes update` to get moving faster now

[Daniel Lougen @DJLougen]

BusyBeaver-50M V12 is live.

49M param strict-JSON tool-policy model for Hermes/local agent harnesses. Not a chatbot: it picks the next tool call, then the harness grounds exact paths/commands safely.

V12 resolved eval:

- correct tool: 100%
- arg semantic: 97.9% / 90.0%
- unsafe cmd: 0%

Model: https://t.co/Rls9opwyg5
Adapter: https://t.co/l5rHh3THbh

[karminski-牙医 @karminski3]

Qwen3.7! 就在今天!

ArenAI (就是之前的 LMArena), 刚刚发布了 Qwen3.7-Max-Preview 在 ArenAI 的内测跑分. 整体排名在第13, 处于目前版本国模SOTA.

本次提升最高的是数学能力, 达到了总榜第7, 编程水平在第10. 另外视觉能力测试也来到了第16.

我直接试了一下 ArenaAI 上面的 Qwen3.7-Max-Preview, 题目是一个使用 three.js 画一个软盘蓝图的场景, 主要考察大模型的前端+空间理解+建模能力.

直接看我两张 Qwen3.6-Plus 和 Qwen3.7-Max-Preview 的生成对比 (注意这个图上的元素完全是代码绘制的, 不是大模型生成的图片).

能看到Qwen3.7 在空间理解和指令遵循上有了很大的提升, 能保持所有元素都在同一轴向上(能完成这一点是巨大的进步, 目前 DeepSeek-V4-Pro 还有这方面的问题).

并且摆放顺序和每个标签的标记也是准确的, 以及背景的网点效果也还原了(这就是指令遵循的提升体现). 当然不足的地方也有很多, 比如这个软盘的一些不规则图形的细节刻画还是差了一些. 但是是瑕不掩瑜的.

稍后正式发布后给大家带来 Qwen3.7-Max 的详细评测!

(另外值得注意的是 ArenaAI 给 meta 的新模型 Muse Spark 给到了第5的超高位置. 而目前社区中这个模型一点水花都没有. 我也没API能测这个模型. 所以 ArenaAI 的评分还是仅供参考.)

#阿里千问 #qwen37 #qwen37max

[Qwen @Alibaba_Qwen]

🚀🚀Qwen3.7 Preview lands on Arena ！

Here come Qwen3.7-Max-Preview & Qwen3.7-Plus-Preview. Alibaba now #6 lab in Text, #5 in Vision.⚡️⚡️

Can't wait to release Qwen3.7 series models！Stay tuned! @arena

[left curve dev @leftcurvedev_]

I nearly 2x'd the speed while only using +1GB VRAM with the new MTP update in llama.cpp 🤯

You need to add these flags to start using it:
--spec-type draft-mtp \
--spec-draft-p-min 0.75 \
--spec-draft-n-max 2

My results with Qwen3.6 27B on a single RTX 5080 ↓

⚪️ no flag (without mtp)
→ 54.3 tok/s with 13.26GB VRAM

🔵 --spec-draft-n-max 2
→ 90.7 tok/s with 14.29GB VRAM

🔴 --spec-draft-n-max 2 --spec-draft-p-min 0.75
→ 93.9 tok/s with 14.30GB VRAM

🟢 --spec-draft-n-max 6 --spec-draft-p-min 0.75
→ 93.9 tok/s with 14.87GB VRAM

Increasing to 6 draft tokens didn't help my setup for some reason. I made sure to test with a low context length to have enough headroom and eliminate risk of vram stress. From my understanding:

1) The speed gains are very task-dependent. You need to test across a wide range of tasks to get a realistic idea of the benefits

2) We’re already running heavily quantized GGUF models (Q3, Q4, Q6, etc.), so we already benefit from strong speed/performance thanks to the reduced size. That’s why some people are seeing little to no improvement compared to MLX or other quantized versions

The progress over the past few days has been insane to say the least. However, MTP now consumes significantly more VRAM. Personally 16GB just isn't enough to use MTP and run it with a good context size. Time to upgrade lads, 24GB+ users are eating GOOD today 🔥

Full setup below ↓

[座って半畳寝てZizzy @zizzyjp]

Ornstein-27B-v2-Q4_K_MからOrnstein3.6 MTP Q4_K_Mに。速度が2.2倍に。すごいね。でもtcq使えなくなっちゃった。お願いbuunさん対応して！♥

[座って半畳寝てZizzy @zizzyjp]

gpt-latest planner/reviewer
deepseek-v4 flash worker
qwen3.5/3.6 worker
うん。完成。

[座って半畳寝てZizzy @zizzyjp]

Draftありtoken上限ありdense
強くtuningされたMoE
よりパワフルでより高速なモデルはどれなんだ

[xAI @xai]

You can now use your @grok subscription inside @NousResearch Hermes Agent.

https://t.co/UYKGws8zzH