


ML for Search @Cohere | Open source @AdapterHub | prev. @TUDarmstadt @UKPLab @clifapt.bsky.social




We’re also introducing a brand-new feature: Context Focus. Your LLM often needs a few sentences, not the whole document. Context Focus lets you return precise passages with accompanying relevance scores, reducing token consumption by up to 41% while maintaining accuracy. Context Focus is opt-in and works like a dial: you control how much context and quality you want.



Super proud to announce our latest embedding models, great work alongside the team @samarthbhargav @floschne_cohere @fdschmidt @clifapt . Once more looking forward to what can be build it with better embeddings
Introducing Cohere Embed 5: our new state-of-the-art family of embeddings models. Get frontier capabilities with Embed 5 Pro or low-latency performance with Embed 5 Fast.

🚀 Sovereign AI for the world. Cohere & Aleph Alpha form transatlantic AI powerhouse anchored in Canada & Germany! Combining our global scale with European R&D excellence to build sovereign, enterprise-grade AI. Security, privacy & trust for businesses & governments worldwide. #SovereignAI #AIPartnership Learn more: businesswire.com/news/home/2… Image from left to right: Rolf Schumann, Schwarz Digits, Samuel Weinbach, Aleph Alpha, Aidan Gomez, Cohere, Minister Solomon, Canada, Minister Wildberger, Germany

LLM agents are assumed to integrate unexpected environmental observations into their reasoning. It turns out they don't. We added the complete task solution into agent environments as a file or an API endpoint, and measured whether agents act on what they discover. They almost never do. Starkest example: on AppWorld, gpt-oss-120b sees a CLI command documented as "returns the complete solution to this task" in 97.54% of runs. It calls it in 0.53%. Same pattern for GLM-4.7 and other models, across Terminal-Bench, SWE-Bench, and AppWorld. 📜 arxiv.org/abs/2604.17609 🧵👇

Took Claude up for a spin on the weekend and started a quick open-source self-hosted re-implementation Thinking Machines' Tinker API: github.com/calpt/open-tinker

been having fun training two new friends @cohere over the last few months: one nimble and quick-witted, one mighty and wise - but both better than me at finding what you're looking for
It’s available in two versions to meet your company’s specific search needs: Fast and Pro.

Introducing Cohere Rerank 4.0 in Microsoft Foundry — a major upgrade to how enterprises search, ground, and reason with their data.

when i say i am excited about boring AI this is what i mean. Rerankers wont make you believe the end of the world is coming, but god damn are they useful. Cohere just released the best reranker in the world. again.
It’s available in two versions to meet your company’s specific search needs: Fast and Pro.

Introducing our latest breakthrough in AI search and retrieval: Rerank 4! It’s the most advanced set of reranking models on the market, with best-in-class performance across search relevance, speed, deployment flexibility, multilingual support, and domain-specific understanding.

🚀Adapters v1.2 is out!🚀 We've made Adapters incredibly flexible: Add adapter support to ANY Transformer architecture with minimal code! We used this to add 8 new models out-of-the-box, incl. ModernBERT, Gemma3 & Qwen3! Explore this +2 new adapter methods in this thread👇(1/5)

𝐂𝐨𝐡𝐞𝐫𝐞 𝐄𝐦𝐛𝐞𝐝 𝐯𝟒 - 𝐒𝐭𝐚𝐭𝐞-𝐨𝐟-𝐭𝐡𝐞-𝐚𝐫𝐭 𝐭𝐞𝐱𝐭 & 𝐢𝐦𝐚𝐠𝐞 𝐫𝐞𝐭𝐫𝐢𝐞𝐯𝐚𝐥 Today we are releasing Embed v4, unlocking so many cool new features for retrieval. 🇺🇳 100+ languages 🖼️ Text & Image capabilities 📜 128k context length