More teams are rethinking cloud-hosted LLMs.
agent.cpp provides minimal, high-performance building blocks for agents in C++, built directly around the llama.cpp ecosystem.
Designed for running agents locally on your own hardware.
Repo: link.mozilla.ai/agent-cpp
Guardrails are vital for AI safety, but hard to choose. Each has its own logic & definition of unsafe.
That's why we built any-guardrail, a unified interface to test and switch guardrails seamlessly, making AI safer, more reliable, and easier to build.
Read our post: blog.mozilla.ai/introducing-...
Working with multiple platforms & LLMs, but some models only appear on certain providers?
Try any-llm Model Finder! See connected providers via API keys & search models across all of them. It's built on top of our any-llm library.
Check out our repo and GIF: github.com/mozilla-ai/a...
ESPAÑA LLEVA SIN LUZ QUINCE MINUTOS.
AHORA IMAGINAD GAZA, QUE LLEVA SIN LUZ AÑO Y MEDIO.
Las prisiones españolas usan un #algoritmo sin actualizar desde 1993 que es decisivo para determinar permisos de salida.
Además de que, 200 resoluciones en 2024 citan el resultado de este algoritmo para denegar u otorgar permisos, tiene algún que otro sesgo.
Aquí, nuestra última investigación👇
Meet Any-Agent, a Python library that lets you build and switch across agent frameworks.
Try it: github.com/mozilla-ai/a...
We built it because we were struggling. Now we’re sharing.
🔹 Unified interface
🔹 Logging with OpenInference
🔹 Built-in eval
Blog: blog.mozilla.ai/introducing-...
New report from @greenpeaceeastasia.bsky.social and
@digiconomist.bsky.social finds that AI companies like Nvidia are threatening climate progress
Climate pollution from AI computer chip production increased by *over 350%* in just one year
(That's before they're even used!)
Tariffs xkcd.com/3073
Announcing a new event initiative: Feminist AI LAN Party! Katharine and I did a pilot event last year and we're now taking it to @pyconde.bsky.social.
We've also open-sourced event kits to make it easy to host your own, including:
💣 hacking LLMs
📑 data development
✂️ zine making
feministai.party
You can now register at www.eventbrite.com/e/dair-prese...
⏰Friday April 11 9am-12pm PDT | 12pm-3pm EDT | 6pm-9pm CEST | 7pm-10pm EAT
I have being recently working with different agent frameworks and I couldn't agree more with the ideas in the paper.
I haven't found yet a practical use case where I would personally prefer to use an agentic pattern over a code-defined workflow, where some (managed) calls to LLMs can still happen.
MANIFESTACIÓN HISTÓRICA POR TIERRA Y MAR
Galicia ha hablado: no quiere una nueva fábrica de celulosa ni está dispuesta a que se malgaste el dinero público en proyectos sin licencia social y tan agresivos con su naturaleza, su forma de vida y su cultura.
¡No a la megafábrica de celulosa!
ALTRI NON!
Israeli forces have killed Hossam Shabat with a targeted airstrike while he was driving his car in Beit Lahiya. Shabat, who was 23 years old, had become well-known for his reports from northern Gaza amid Israel’s total siege on the region.
Dozens more pregnant and postpartum women have died in Texas hospitals since the state banned abortion, our analysis shows.
As the maternal mortality rate dropped nationally, it rose in Texas by 33%.
I am happy to have a debate on my views on a general level beyond my personal experience and this particular situation, I didn't realize that is what was happening here.
I was taking about myself in a thread that points directly to me personally and professionally. I apologize for my over-defensiveness, it has been a long weekend.
I was doing a task that was time consuming and happened to have the expertise to improve parts of it with automation. I used this hammer myself and got the opportunity to be paid for polishing for public release.
> You go in and do what you want.
I have been in OSM way before this project.
It is true I do what I want to some extend, as any other OSM contributor, always trying to follow the existing policies in the community.
I have been manually mapping swimming pools and other features for years.
Do you think it is possible that sometimes you might perceive it that way but the thinking behind is different?
Given the different reactions, I am sure it is not you misreading it but me making a very poor choice and not including further explanation of the intended message 😅
(I think) I do understand why people from other communities like HN are mad at.
Long time ago I realized that if I follow the path of open source AI my steps will be carefully analyzed and questioned.
I know I have made mistakes with this project and I am trying to amend them and improve.
I created community.openstreetmap.org/t/about-mapp... to gather insights from the community mainly affected by this.
I do believe it also applies to Wikipedia.
People are training LLMs with Wikipedia data, and that is a fact.
If we acknowledge that, we can explore different ways of how to handle that use case beyond "I don't like that use case"
I clearly did a poor choice of including the meme without further contest.
I didn't meant like it was "intended" but more like a "realization" that it is what people is/will be using it for.
Here is my explanation:
bsky.app/profile/daav...
