@GPTWare

🇨🇦 Obsessed with all things Ai Agents, Loops, LLMs, Fine-Tuning https://xitter.cf/t.co/9thyt19bL5 - Entrepreneur. Builder.

 Canada
GPTWare.com
Joined May 2026
  • Tweets1.8K
  • Following428
  • Followers373
283Media
Agentic orchestration and agentic workflow creation are by far the most important and valuable skills you can have right now.
McKinsey & Company
@McKinseyMay 29
Agentic orchestration layers allow AI agents, enterprise systems, and data connections to work together across functions. As cognitive bottlenecks shrink, that allows decision-making to speed up, coordination to improve and new operating models to form. mck.co/4fJb564
Diagram showing the agentic orchestration layer directing workflows between enterprise context, agents, and data connections.

ALT Diagram showing the agentic orchestration layer directing workflows between enterprise context, agents, and data connections.

2
12
2,163
Prefill numbers...
22
Credits
26
Here it is... xitter.cf/GPTWare/status/2113601…
GPTware
@GPTWare2h
DeepSeek-V4.1-Flash-1017 on 1× RTX PRO 6000 Blackwell + 2× GB10, using QMesh AFD-TP3 + DSpark: Full NVFP4 Quant ⚡ 119.78 tok/s peak single-request (code) ⚡ 200.24 tok/s peak at 8 concurrent requests 2M context window.
4
Here it is... xitter.cf/GPTWare/status/2113601…
GPTware
@GPTWare2h
DeepSeek-V4.1-Flash-1017 on 1× RTX PRO 6000 Blackwell + 2× GB10, using QMesh AFD-TP3 + DSpark: Full NVFP4 Quant ⚡ 119.78 tok/s peak single-request (code) ⚡ 200.24 tok/s peak at 8 concurrent requests 2M context window.
4
Still work to do on it. The goal with QMesh is to combine fast RTX processors with Sparks to host larger models faster than on sparks alone. Here's the setup...
1
1
2
112
DeepSeek-V4.1-Flash-1017 on 1× RTX PRO 6000 Blackwell + 2× GB10, using QMesh AFD-TP3 + DSpark: Full NVFP4 Quant ⚡ 119.78 tok/s peak single-request (code) ⚡ 200.24 tok/s peak at 8 concurrent requests 2M context window.
3
3
6
233
LMAO
Theo - t3.gg
@theoOct 22
Caring a lot about harnesses rn feels similar to caring about tabs vs spaces
46
GPTware retweeted
Tim Pan@mediastorm_enOct 22
My iPhone Duo video went viral, so I'm giving away 100 iPhones on X 😛
52,524
48,443
3,935
78,801
1,928,258
Where is Anthropic's Tibo? Can we get a reset? @AnthropicAI
45
GPTware retweeted
Engy@engyaiOct 22
DeepSeek-V4.1-Flash Pricing engy will update DeepSeek-V4.1-Flash pricing to 20% of DeepSeek's official rates. Official: $0.15 / $0.60 engy (Current): $0.04 / $0.08 engy (New): $0.03 / $0.12 Changes: Input -25% · Output +50% · Both 80% below official rates
10
19
5
286
21,641
Forget DGX Station... i need a DGX POD. How much?
NVIDIA
@nvidiaOct 22
Replying to @nvidia
Read the news ⬇️ nvidianews.nvidia.com/news/n…

NVIDIA Introduces DSX POD AI Factories to Accelerate Europe’s Infrastructure Deployment

NVIDIA today introduced DSX POD, a reference design for complete NVIDIA Vera Rubin AI factories built by partners inside modular containers, integrated and validated before delivery.

nvidianews.nvidia.com
49

No more items