Ben Eagan
@beneagan
Followers
180
Following
1K
Media
36
Statuses
382
working on search @cohere
Joined January 2010
Such a strong model, great work to the team!
After 6 months, can finally tell everyone what we have been working on. Looking forward to seeing what people will be able to build with this :)
0
0
10
The Mission: Setup voice wrapper for ASR and TTS, wire it through walkie talkies, establish first contact with @cohere Command A ... !!MISSION ACCOMPLISHED!! "Your Presence is Unexpected But Welcomed" (code -> https://t.co/dU2xrhvO3w)
1
6
31
Today, we’re launching early access for North! Our all-in-one secure AI workspace platform combines LLMs, search, and agents into an intuitive interface that effortlessly integrates AI into your daily work to achieve peak productivity.
15
101
553
The focus on hard and real search use cases while building Rerank 3.5 leads to some magic experiences. You can feel it in the results, and they speak for themself.
Rerank 3.5 has enhanced reasoning capabilities that can understand complex and multifaceted user questions which have traditionally challenged search systems.
0
4
23
Loving the really tall blue rectangles here, great multilingual performance for Aya!
Today @CohereForAI and @cohere are releasing two new multilingual models spanning 23 popular languages. Across a range of use-cases, these models represent a new state-of-the-art. We're also releasing the weights (8B & 32B) on @huggingface
0
3
16
Understanding @aidangomez’s post requires processing both visuals and text together... If you can do this, you’ll know Cohere’s embedding model can too!
But the most compelling piece is the performance for mixed-modal datasets where this is a 'zero to one' unlock in performance.
1
0
10
Looking for a team lead to join our search team at @cohere working with @Nils_Reimers and many other kind & smart people. Feel free to message me if you want to know more! here is the posting:
1
13
63
Excited to share Cohere Compass! An embedding model built to handle your weirdest semi-structured enterprise data. Checkout blog for details and beta signup 👀.
Announcing the private beta of our newest foundation embedding model, Cohere Compass: designed specifically for multi-aspect data like emails, invoices, CVs, and support tickets to offer superior enterprise search capabilities. Sign up to try it out! https://t.co/CO6OIrnpDg
1
1
10
Anyone with search or RAG products should really make sure to try this out. That one line boost from rerank just got even better 🔥🔥
0
0
0
What's so cool about searching over structured text is that you can now out-of-the-box rerank on specific JSON fields! So if your business prioritizes certain fields (i.e. popularity for e-commerce), the rerank can support that requirement.
1
0
0
For a long time, the single best line of code to improve search results has been a call to @cohere's reranker. With Ranker 3 this becomes even more true! Not only is it faster, and more accurate, it also supports search over structured text, code, and tables.
Here's the blogpost with more details https://t.co/pdB69NEk4r
1
4
38
Here's a picture of me being keen about Command R+ (IYKYK)
Today, we’re introducing Command R+: a state-of-the-art RAG-optimized LLM designed to tackle enterprise-grade workloads and speak the languages of global business. Our R-series model family is now available on Microsoft Azure, and coming soon to additional cloud providers.
0
0
0
Yet another amazing launch from my colleagues! Loving the open weights, cloud availability, multi-lingual support, state of the art RAG, and oh so much more:
⌘R+ Welcoming Command R+, our latest model focused on scalability, RAG, and Tool Use. Like last time, we're releasing the weights for research use, we hope they're useful to everyone!
0
0
18
Command-R and Embed-v3 make a winning RAG combo. Checkout some details on multilingual wikipedia search, and get your dataset requests in!
🇺🇳𝟐𝟓𝟎𝐌 𝐖𝐢𝐤𝐢𝐩𝐞𝐝𝐢𝐚 𝐄𝐦𝐛𝐞𝐝𝐝𝐢𝐧𝐠𝐬 𝐢𝐧 𝟑𝟎𝟎+ 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞𝐬 🇺🇳 What could you build if your RAG has access to Wikipedia in all 300+ languages? Available for anyone to use, using our state-of-the-art multilingual embedding model: https://t.co/PCaAyboxsq
0
3
27
The search hits just keep coming. Now you can just go straight to ChatGPT plugins to search the Shop catalogue!
1
0
4
Have been working really hard on this the past few weeks and very stoked to see it out in the world! Go chat with our shopping assistant and see what it finds for you.
4
1
13
Finally generating some Cat content
@ubcAWP researchers developed an open-source behaviour real-time spatial tracking identification system for animals. BeRSTID allows accessible monitoring that correlates closely with human-coded behaviors in shelters https://t.co/vuuB6kxtBA
@BaileyHopeEagan @beneagan @dr_prot
0
0
2
