Hunyuan Hy4 Flash + WorkBuddy: faster, cheaper, and it writes Three.js
The fast variant of Tencent's Hy4 does an 8-minute physics demo and Three.js 3D, using about a fifth of the tokens DeepSeek V4.1 Flash needs.
11 résultats · “DeepSeek”
Open-source agent framework — everything is a plugin
“Open-source agent framework where everything is a plugin.”
DeepSeek's multi-task super agent that splits and handles multiple tasks at once.
“Multi-task super agent that splits and handles several tasks at once”
Latest DeepSeek — V4.1 with a Flash variant
“Flash hits 300 tokens/sec on real tasks — feels instant”
DeepSeek's open 485B-parameter Flash variant of V4.1.
“Way too fast”
The fast variant of Tencent's Hy4 does an 8-minute physics demo and Three.js 3D, using about a fifth of the tokens DeepSeek V4.1 Flash needs.
I was working on a document ingestion pipeline for an AI-powered financial research system when I encountered an interesting problem. A PDF converted successful
Model tested - Models : DeepSeek V4.1 Flash and Qwen3.8-Flash, head to head both run through omp / opencode-go - Use case : coding - a real feature on my hackat
Models tested - Model A : Qwen3.8 Flash qwen3.8-flash , run through oh-my-pi omp , thinking level medium - Model B : DeepSeek V4.1 Flash deepseek-v4.1-flash , r
1. Summary I uploaded profile photos of my face to five AI tools and asked each one the same questions about facial features, visagism impressions, and phenotyp
I Spent 400M Tokens Testing Kimi K3.1 — the Open-Source King Still Needs Work Last weekend Kimi K3.1 Pro dropped, and honestly I was hyped. The last K3 I touche
The receipts June–September Month Cost Tokens API requests --- --- --- --- June $112.78 3.68B 9,637 July $22.49 517M 2,069 August $15.11 155M 998 September $47.