Agent Engineering with Pydantic + Graphs https://
latent.space/p/pydantic with @samuelcolvin
! We've heard from @jxnlco 3 years running that @Pydantic Is All We Need, and this is even more true today with the launch of Pydantic AI! With a little @marimo_io love at the end 🙂
OPEN SOURCE
-
Pydantic AI: Agent Engineering with Graphs and Tools
By
–
-
DeepSeek-R1 RL Training Simplicity Versus Process Reward Models
By
–
From an open-research point of view, probably the greatest thing about DeepSeek–R1 is how its RL training technique appears so straightforward and simple in comparison to the cumbersome approaches people were starting to think necessary for learning reasoning like Process Reward
-
Open-Source AI Advocacy at Paris AI Summit 2026
By
–
I'll travel to Paris next week for the AI Summit to represent the open-source AI community. I'll try to push world leaders & big tech CEOs to recognize that open science and open-source AI are critical for distributing power, creating value, and reducing risks in AI.
-
Keras Community Meeting Tomorrow at 11am PT
By
–
The Keras team will be doing a community meeting on Friday morning (tomorrow) at 11am PT. it's a public Meet call, anyone can join. You'll get updates on what's new in Keras, what will land next, and you'll be able to ask any question you have.
-
Hugging Face reaches 200 employees driving open-source AI
By
–
Love catching up with the whole @huggingface team today! We're 200, moving stock markets with open-source releases, getting mentioned by presidents & trying to help the community make the whole world more open and collaborative, all of this while having fun. Let's go!
-
Ace++ ComfyUI Plugin for Advanced Face Swapping and Object Replacement
By
–
highlight = Ace++ for comfyui in terms of faceswapping and objective rpelacement
-
Chinese Hedge Fund Open Source OS Model Disrupts AI Market
By
–
That’s the irony, duh. The best OS model came from a Chinese hedge fund. The operative words here being ‘open source.’ That API already being built upon by hundreds of thousands of developers. (97% cheaper than Open AI’s.)
-
Groq’s New Deepseek R1 Distill Llama 70B Endpoint 6x Faster
By
–
Deepseek R1 Distill Llama 70B fun continues. Our new endpoint is now 6x faster than our previous offering. Thanks @ArtificialAnlys for the update.
-
Hyperbolic hosts Llama 3 405B Base in bf16 precision
By
–
afaik Hyperbolic is the only place that hosts my <3 Llama 3 405B Base, and in bf16 precision. So thank you 🙂