Dimaz Arno (@dimazarno) header
Dimaz Arno (@dimazarno) profile picture
Indonesia
Joined August 2008
Photo by Dimaz Arno (@dimazarno)Photo by Dimaz Arno (@dimazarno)Photo by Dimaz Arno (@dimazarno)Photo by Dimaz Arno (@dimazarno)Photo by Dimaz Arno (@dimazarno)Photo by Dimaz Arno (@dimazarno)Photo by Dimaz Arno (@dimazarno)Photo by Dimaz Arno (@dimazarno)Photo by Dimaz Arno (@dimazarno)Photo by Dimaz Arno (@dimazarno)
We're already seeing a growing number of PHP2Shell (CVE-2026-109618) exploitation attempts hitting our servers. Looks like automated scanners are getting busy. Meanwhile, we're collecting their payloads for our own security research. Thanks for the free payload! 😂
1
196
Just tried this. ~371 tok/s at c=4 on my dual Sparks, and prefill jumped to 4,000+ tok/s too. Really nice update @vr8vr8.
Qwen3.8-Flash-Next tp=2‼️ DS4.1-Flash looked like a miracle running at 200+ now we have similar speed for Qwen3.8 locally 177tok/s‼️ 🚀 Peak c=1 @ 177 tok/s 📊 Average c=1 @ 93 tok/s 🏭 Peak c=64 @ 1,174 tok/s ⚙️ Prefill 3,939 tok/s 💻 TTFT 0.36s ⚡️ github.com/myllmbox/qwen38-f…
2
196
Updated 🏎️💨💨
44
Dimaz Arno retweeted
Qwen3.8-Flash-Next Who's actually the winner on one DGX Spark? 🤔 My LLM Box (vLLM, NVFP4) vs TensorFold (MLX 4-bit) 🚀 c=1 -> difference: ~5 % ⚙️ c=16 -> difference: ~23 % 📊 Quality -> 6.5 vs 0 Total: 87 % vs 68 % 🏆 👉 myllmbox.com/ More models coming soon 🥳
7
5
2
57
10,576
This is getting interesting. Can’t wait to try this very soon 🔥 Huge thanks to @ashxhart and the @MiaAI_lab team!
- GLM 5.3 Flash EXL3 - 2x DGX Sparks - TensorFold - 4 concurrent prose streams Pay attention to tok/s and TTFT on each stream. Buttery smooth experience!
2
144
Updated! 126 tok/s, 98ms TTFT on dual DGX Sparks. Up from 115 tok/s. Thanks @vr8vr8!
Qwen3.8-Flash-Next just got better. With a release of 0.30.0 @vllm_project it was possible to get a punch of extra ~10% compared to v3 and around ~15-20% compared to v2. c=1 -> 121 token/s❗️ c=64 -> 883 token/s❗️ ⚡️github.com/bilikaz/qwen38-fl…
1
1
1
3
1,430
Built a simple project manager for OpenCode. Nothing fancy, just project switching and file browsing. I got tired of opening multiple terminals just to work on different projects. This keeps things simple and does exactly what I need.
1
116
Been running @vr8vr8's Qwen3.8 Flash Next cluster recipe on our dual DGX Sparks for a week now. No issues so far. Really enjoying it! Thanks for sharing!
1
130
Menarik untuk dicoba ini Prof @onnowpurbo
🚀 Meet MiniCPM5-2B, a 2B-parameter language model bringing high intelligence density to the edge, now open source! It ranks #1 among open-source models under 4B parameters on the @ArtificialAnlys Intelligence Index, with a score of 23. It also scores 20 on the Agentic Index, bringing an early form of general-purpose agent capability to the edge. Across 34 benchmarks, MiniCPM5-2B achieves an average score of 53.9, covering coding, math, long-context understanding, tool use, and agentic tasks. And this release goes beyond the model itself. We’re opening up the data, training recipes, and RL stack behind MiniCPM5-2B. 🤗 Hugging Face: huggingface.co/openbmb/MiniC… 💻 GitHub: github.com/OpenBMB/MiniCPM Modelscope: modelscope.cn/models/OpenBMB… Web: openbmb.cn/
1
2,029
Jadi banyak yang mimisan ya?
62
Sebelum ada internet = Informasi tertutup Setelah ada internet = Informasi terbuka Setelah ada internet + AI = Informasi tertutup
50
Tadi ada duel sengit Pak Aolia membuat AI, Pak @dimazarno ngehack AI 🤣🤣🤣 Sang empunya pun tersenyum @onnowpurbo Kalau mau diajarin ayok kuliah di @ittstangsel sebelum tutup, tanggal 30 September 2025. registrasi.itts.ac.id Terima kasih yang sudah datang
4
17
2,311
Dimaz Arno retweeted
just unlocked the deepest vault of n8n automations on the internet - and you can get them for free. I had my VA scrape and sort every useful n8n repo on the internet by hand.. and I'm now sitting on a clean, categorized directory of 1500+ workflows inside the vault you'll find: – RAG analysis & AI research flows – lead scoring and CRM updates, fully automated – inventory management flows – content repurposing schedulers – Airtable/Notion/GPT mega-integrations all plug-and-play want access to the repo + organized vault? Like + comment “REPO” + repost (must be following so I can DM you)
1,570
683
17
1,900
174,710
Bersama dosen utama bidang cybersecurity Bapak @dimazarno dan dukungan Full oleh Rektor @onnowpurbo , @ittstangsel Insya Allah akan mengadakan CTF (capture the flag) 2025. Dulu sangat keras sekali dan sengit, nilai tipis, keren lah no debat. are you ready guys?
1
3
14
1,350
Dimaz Arno retweeted
Wawancara masuk Kuliah @ittstangsel , anak Desa di ruang Komunitas digital desa Bulakan ingin kuliah Dan mengejar cita-cita di bidang IT @onnowpurbo , senangnya @ittstangsel memberikan kemerdekaan kuliah Dari mana saja bahkan Dari daerah sekalipun ...
2
5
2
21
5,348
Apply to attend #PHTalks in Jakarta, Indonesia 🇮🇩 🗓 July 23 — free in-person event 🔗 phtalks.ptsecurity.com/jakar… CFP open until July 4. Attendee registration open until July 11. I’m reaching out to offensive and defensive security people — red/blue teams, SOC, DFIR, vuln, and bug bounty researchers across Indonesia and the region. Know people? Let me know.
7
33
11
60
11,522
How MCP work:
This quoted post is unavailable.
1
252
Workshop OFFLINE Migrasi IPv4 ke IPv6
1
3
15
1,289
Cursor and Windsurf GPT 4.1 > Claude Sonnet 3.7 Source: Trust me
110
5
1
6
1,261