Guys burning 3B+ tokens of MiniMax M2.7 on Gonka when DeepSeek v4 Flash is readily available
Anthropic Doesn't Think You Can Be Trusted, China is closing the gap, SpaceXAI Leaps Ahead, and DEF CON
0:00 Intro 2:56 Claude Watermarks 15:04 Meta + Muse 48:48 GLM-5.3 55:15 Qwen + DeepSeek 1:08:48 Grok 4.6 + Bot 1:20:15 Gavin vs Dario 1:43:44 DEFCON 2:15:35 Viewer Q&A
In case people were wondering how fast this setup can get, "fast enough for my needs"
Below are 3 different prompts (w/ some caching) at low, high, and max reasoning on DeepSeek V4 Flash (0731) i used opencode as my harness on my mac mini and it uses the dgx sparks as the
Quickly get started with DeepSeek Harness, install, configure AI models, bring plugins, set access level and more.
Let's install it with a single command and send your first prompt
You have reached the end of the archive
All of deepseek