Introducing ✨Aya Expanse ✨ – an open-weights state-of-art family of models to help close the language gap with AI. Aya Expanse is both global and local. Driven by a multi-year commitment to multilingual research. cohere.com/research/aya

Our Command R+ model is one of TIME's 200 Best Inventions of 2024! 🚀 Try it out at coral.cohere.com 🌐 time.com/collection/bes…

How do LLMs learn to reason from data? Are they ~retrieving the answers from parametric knowledge🦜? In our new preprint, we look at the pretraining data and find evidence against this: Procedural knowledge in pretraining drives LLM reasoning ⚙️🔢 🧵⬇️

A moment for @Cohere and Cohere For AI team appreciation. 💙 #NeurIPS2024 - stop by the booth to catch up with our team, or find us throughout the conference.

Introducing Command R7B: the smallest, fastest, and final model in our R series of enterprise-focused LLMs! It delivers a powerful combination of state-of-the-art performance in its class and efficiency to lower the cost of building AI applications. cohere.com/blog/command-r…

Check out Laura Ruis on Machine Learning Street Talk discussing her work on understanding LLM reasoning at cohere along with fantastic collaborators 🔥

I'm hiring performance engineers for the pre-training team at Cohere. If you enjoy writing efficient kernels, hardware-aligned architecture design and optimisations, do reach out! Check out the live job posting here: jobs.ashbyhq.com/cohere/d42f5fd…

Cohere releases Command A on Hugging Face Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Command A is on par or better than models like GPT-4o and Deepseek

Really proud of the work that went into pre-training this model!

shoutout to the ascii team

🚀 Big news cohere's latest Command A now climbs to #13 on Arena! Another organization joining the top-15 club - congrats to the Cohere team! Highlights: - open-weight model (111B) - 256K context window - $2.5/$10 input/output MTok More analysis👇

I added cohere command A to this chart, I had to extend the axis a bit though….

Highly recommend working with Ed! He comes in handy.

Great interview! (even at 1x)

Excited to announce that @Cohere and Cohere Labs models are the first supported inference provider on Hugging Face Hub! 🔥 Looking forward to this new avenue for sharing and serving our models, including the Aya family and Command suite of models.

RL is not all you need, nor attention nor Bayesianism nor free energy minimisation, nor an age of first person experience. Such statements are propaganda. You need thousands of people working hard on data pipelines, scaling infrastructure, HPC, apps with feedback to drive

Very proud of this work which is being presented ICLR 2026 later today. While I will not be there — Catch up with Viraat Aryabumi and Ahmet Üstün who are both fantastic and can share more about our work at both Cohere Labs and cohere. 🔥✨

Presenting this today 3-530 at poster #208, come say hi 🙋‍♀️

new math youtube streamer just dropped

If you are based in Zurich (or anywhere rly) and write code for ML accelerators (including cuda/rocm) HMU