←
Clifton Poth102 posts
Clifton Poth avatar

Clifton Poth

@clifapt

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

◷ Joined June 2020▧ 15 Photos and videos
Cohere avatar
⟳ Clifton Poth retweeted
Cohere@cohere·Nov 16

Introducing: Video Intelligence in Compass. Make every moment in your video library searchable. Now in Private Preview.

1:43
Cohere avatar
⟳ Clifton Poth retweeted
Cohere@cohere·Nov 4

Embed 5 and Rerank 5 are now live on OpenRouter! Build faster, smarter retrieval applications with our state-of-the-art models through a single API. Two models, one bill, zero switching platforms. Available in Pro and Fast tiers.

Cohere avatar
⟳ Clifton Poth retweeted
Cohere@cohere·Oct 14

Cohere Rerank has a lot of great enterprise applications. It can also play Mario. Stick around to see if Rerank 5 can beat 4's score 👀

0:15
Cohere avatar
⟳ Clifton Poth retweeted
Cohere@cohere·Oct 21

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.

Post attachment
Cohere avatar
⟳ Clifton Poth retweeted
Cohere@cohere·Oct 21

Introducing Rerank 5 A few lines of code can change how you search. With this release, we’re advancing the frontier in AI retrieval and precision. Available in Pro and Fast tiers today.

Post attachment
Cohere avatar
⟳ Clifton Poth retweeted
Cohere@cohere·Sep 30

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.

Post attachment
Carlos Lassance avatar
⟳ Clifton Poth retweeted
Carlos Lassance@cadurosar·Sep 30

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

Cohere@cohereSep 30

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.

Post attachment
Cohere avatar
⟳ Clifton Poth retweeted
Cohere@cohere·Apr 24

🚀 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

Post attachment
Leon Engländer avatar
⟳ Clifton Poth retweeted
Leon Engländer@LeonEnglaender·Apr 21

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 🧵👇

Post attachment
Clifton Poth avatar
Clifton Poth@clifapt·11 Dec 2025

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

Cohere@cohere11 Dec 2025

It’s available in two versions to meet your company’s specific search needs: Fast and Pro.

Post attachment
Microsoft Azure avatar
⟳ Clifton Poth retweeted
Microsoft Azure@Azure·11 Dec 2025

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

Nick Frosst avatar
⟳ Clifton Poth retweeted
Nick Frosst@nickfrosst·11 Dec 2025

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.

Cohere@cohere11 Dec 2025

It’s available in two versions to meet your company’s specific search needs: Fast and Pro.

Post attachment
Cohere avatar
⟳ Clifton Poth retweeted
Cohere@cohere·11 Dec 2025

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.

Post attachment
AdapterHub avatar
⟳ Clifton Poth retweeted
AdapterHub@AdapterHub·21 May 2025

🚀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)

Post attachment
Nils Reimers avatar
⟳ Clifton Poth retweeted
Nils Reimers@Nils_Reimers·15 Apr 2025

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