State of Local AI
TheAhmadOsman breaks down how quickly models are getting smaller and better, why local AI matters for open source, and why owning your compute is increasingly important Timestamps: 0:00 - Why local AI matters for open source 03:55 - How AI is moving onto
Releasing Your Own Jev
Post-train a 4B/8B/27B judge on your agent's traces. It beats Jev. 79.7% agreement with human labels vs Jev's 66.3% Beats DeepSeek-V4.1-Flash (763B) by 14 points 0.13s per step on a single GPU Completely open source: recipe, data, training, evals
Top-5 Best Value #LLM Models of the Day at UTC-16
| Model | #AAII | Price | | GLM 5.3 Flash | 42 | $0.07 | | GLM 5.3 | 45 | $0.33 | | DeepSeek V4.1 Flash | 40 | $0.10 | | Claude Sonnet 5.5 | 56 | $3.06 | | MiMo-V2.6-Pro | 46 | $0.32 |
This is f**king insane
Deepseek just open sourced its entire agent runtime 240k+ github stars in about 6 weeks. built on one idea: everything is a plugin. → model adapter → tool registry → session log → sandbox → interface → the agent loop itself all swappable. no
You have reached the end of the archive
All of deepseek