Recent Model Releases Highlight Kimi K3 and DeepSeek V4 with Its Own Harness
casper_hansen_ · x · 2026-08-14
The author reviewed the recent flurry of model releases, highlighting Kimi K3 as the standout. Qwen3.8 Max remains reliably effective, and DeepSeek V4 is finally fully out with its own official inference harness. They note that a solid harness is now half the battle in a model release.
Related event: Chinese AI Labs Unleash a Month-Long Wave of Models, Nearing the Frontier(6 posts)→
More from Models
- Qwen2.5-72B Leads Among Similar-Sized Models — solyarisoftware · 2026-08-15
- Harvey and Applied Compute train legal-specific model with SOTA accuracy at fraction of cost — rhythmrg · 2026-08-15
- Pestle 27B Ternary: first medical ternary model, Apache 2.0 — Individual-Dot5488 · 2026-08-15
- Frontier model prices drop across the board, open and closed source, making agents cheaper — markjeffrey · 2026-08-15
- RedNote AI lab's TEMPO RL method: 16B MoE scores >30% on ARC-AGI 3 — GregKamradt · 2026-08-15
- Orion-16B passes 100B tokens, largest LLM pretrained with decentralized compute — const_reborn · 2026-08-15