all w/ apache 2.0 licensed codebase – time to go build things!
@reach_vb
-
Build Devin-Like AI Agents in Three Lines Code
By
–
smolagents – build your own Devin like agents in 3 lines of code with search!
-
OpenAI’s Packaging and Deployment Moat Exceeds Competition
By
–
The moat is in packaging + deployment – this is where OAI by far exceeds by miles, with Anthropic coming second. Loads of work to do to get there for open source, 2025 will be critical!
-
Qwen 2.5 0.5B: The Sweet Spot for Efficient Language Models
By
–
Qwen 2.5 0.5B is the sweet spot, but you do you
-
DGX B200: High-Risk AI Hardware Investment for Early Twenties
By
–
If you’re a guy in your early 20s, buy a DGX B200. Go into debt if you have to, in fact, you must go in debt to realise it’s true potential. This is the way!
-
Cascading LLM Calls Improve Performance Efficiently
By
–
Or just any other LLM even a smol one does a great job at it – cascading to two calls helps quite a bit!
-
Open Science Catching Up: Respect for Sam and OpenAI
By
–
hey hey – it's banter, I have massive respect for Sam & OAI and look up to both. At the same time I love how Open Science is finally catching up. If my tweets bother you, feel free to mute/ block!
-
Teams Building Publicly: Qwen DeepSeek Share Detailed Scientific Reports
By
–
100% agreed – similarly, we should also applaud teams (like Qwen, DeepSeek) out here building in public, sharing extremely detailed scientific reports with the mission bringing the whole community closer to the frontier. Massive respect for all!
-
Dense vs Mixture of Experts: Technical Insights and Public Sources
By
–
Very interesting, are there any more intuition on dense vs MoE? Also hate to be that guy.. but is there a public source for this (to test okay if not)
-
Open Source Winning Through Distribution Not Model Weights
By
–
open source is already winning – the most is not in weights, but distribution