Jev + deepseek v4 flash is a great combination. I reconstructed my project
Jev + deepseek v4 flash is a great combination. I reconstructed my project, a bunch of intent recognition things, using Jev. The effect is very good, very fast, and very economical. Coupled with the speed of DeepSeek V4 Flash, it is so fast.
A model that beats GPT on some benchmarks is running on my desk right now.
Nobody is covering it. If you have two Sparks and you are not checking out Qwen3.8-Flash, you are missing out. Tools at 128k context, the lane where most local models die: 89.7 tok/s, zero XML leakage.
DeepSeek released V4.1 Flash on Sept 10, and it is a real step up.
The model can now understand images natively, it holds a million tokens of context, and the weights are MIT licensed. Read the full breakdown:
When I was reborn, I used AI to farm in Shenzhen, testing my scores and harvest! This time, the land doesn’t accept AI’s illusions!
We took the world's 7 top AIs, GPT-6 Astra/CodeX, Claude/Cowork, Gemini, Grok, DeepSeek, Doubao, and WorkBuddy, from the cloud and threw them into the vegetable field for three months of rigorous evaluation!
You have reached the end of the archive
All of deepseek