andthattoo
@andthatto
Followers
505
Following
4K
Media
46
Statuses
580
RT @driaforall: Introducing the Inference Arena. LLM benchmarks are scattered and inconsistent. The Inference Arena ends the guesswork by….
0
12
0
RT @driaforall: DriaConnect drew more than 200 attendees to @betaworks NYC last week. Explore sessions on agentic AI, synthetic data, dist….
0
8
0
RT @driaforall: NYC July 1: . Join us to explore private/distributed inference & agent-native platforms. Talks:. Brandon Reagen (FHE Fram….
0
4
0
RT @driaforall: Introducing our research on low-overhead, privacy-preserving distributed inference: . Protecting inputs, outputs, and model….
0
14
0
RT @driaforall: Launching Decentralized Batch Inference—cutting costs by 5x+ vs. traditional providers—and hitting 20,000 daily active user….
0
11
0
RT @mustafakqazi: 1/ after some rigorous analysis, we learned that some of the “optimal” design choices in dePIN are anything but. in this….
0
8
0
sorry y'all, inference gonna be the dynamic training you're looking for.
0
0
3
RT @RedHat_AI: LLM inference is too slow, too expensive, and too hard to scale. 🚨 Introducing llm-d, a Kubernetes-native distributed infer….
0
86
0
within a set of 50 problems, it matched the sota 75% of the time and exceeded it 20% of the time.
Introducing AlphaEvolve: a Gemini-powered coding agent for algorithm discovery. It’s able to:. 🔘 Design faster matrix multiplication algorithms.🔘 Find new solutions to open math problems.🔘 Make data centers, chip design and AI training more efficient across @Google. 🧵
0
0
4
This will be dnet one year from now.
Most of the world's energy flows through heterogeneous hardware, yet today's AI software is designed for homogeneous and centralized setups. The concentration of high-performance AI into the hands of a few powerful entities poses profound risks to humanity. Introducing Dnet: a
0
1
7
AI hardware/infrastructure loves OR;.
At @modal_labs we aggregate compute capacity from all over the world, so we had to take autoscaling to the next level. We just published a blog post about how we use linear programming to scale up massive amounts of GPUs and CPUs (see below).
0
0
2
RT @driaforall: Most of the world's energy flows through heterogeneous hardware, yet today's AI software is designed for homogeneous and ce….
0
25
0
RT @driaforall: Join us for a deep dive into open-source AI, RL, commodity hardware inference, and next-gen silicon. May 7th — we’re hosti….
0
17
0
RT @driaforall: We are building a global silicon fabric, integrating CPUs, GPUs, and NPUs to create the biggest decentralized AI Accelerato….
0
38
0
RT @czamaru: Can't believe I'm actually profiting off my prompting skills on @swanforall 😂. This AI Agent inspired by the Saratoga guy just….
0
4
0
RT @driaforall: Dria is making AI inference accessible by crowdsourcing it—thanks to our incredible Node Runner community. Now, Node Runne….
0
69
0
RT @0xerhant: @driaforall launcher just got soooo much better!.- one-liner installation.- auto self-updating CLI.- interactive terminal men….
0
25
0
Holy shit this is a----mazing.
"Incoming transmission!" 📡. Classic Command and Conquer games are now open source—ready for modding, preservation, and innovation!. Read more: Dive into the code:
0
0
4