Joined December 2020
- Tweets 3,754
- Following 561
- Followers 2,280
- Likes 20,954
224 Photos and videos
Pinned Tweet
Jan 30
released a Turkish rap song today. Give it a listen, let me know what you think! 🤠
open.spotify.com/track/44Ah7…
1
2
1,350
Command A sets a new high for Cohere's machine translation capabilities.
Opening a clear gap over open source peers Mistral Medium 3.5, DeepSeek, & OpenAI's gpt-oss, as well as Claude Opus 4.6. A also outperforms specialist systems like Google Translate.
RWS is better... but we built that with them too
16
25
208
31,390
May 28
lets goooooo 🏃🏻♀️💨❤️🔥
5
285
Irem Ergün retweeted
May 26
My @cohere internship project w/ @kroscoo and @acyr_l is on arXiv! We show that efficient benchmarking (predicting scores from a subset of questions) can be greatly improved using standard feature-selection & regression techniques (mRMR and kernel ridge)! arxiv.org/abs/2605.25773
3
23
78
9,285
Irem Ergün retweeted
👏 Congratulations to @cohere on Command A — a powerful new model optimized for NVIDIA Blackwell and trained using NVIDIA CUDA-X libraries.
Proud to be a part of it!
Learn more ⤵️
Introducing: Cohere Command A
We’ve created our most powerful LLM yet, optimized it to run on as little hardware as possible, and released it open-source for all.
7
30
310
38,690
May 21
so proud of this model 🥺✨
Cohere launches open weights model Command A that achieves 37 on the Artificial Analysis Intelligence Index
The release of Command A places @Cohere in line with Claude 4.5 Haiku on the Intelligence Index, and just above NVIDIA Nemotron 3 Super and Gemini 3.1 Flash-Lite.
Key Takeaways:
➤ Command A ranks first on AA-Omniscience Non-Hallucination at 86%, ~3 percentage points ahead of the next-best model. Its AA-Omniscience Accuracy is 9%, so the headline AA-Omniscience score lands at -4, demonstrating a similar archetype to Claude 4.5 Haiku, where the model knows its limits
➤ On Cohere’s API, Command A (~281 output tokens per second) is faster than several comparable open-weights and small to mid-sized proprietary models (e.g., GPT-5.4 nano, Claude 4.5 Haiku, and Grok 4.3), but still slower than Gemini 3.1 Flash-Lite Preview, which outputs 304 tokens per second
➤ Command A trails its peer set on scientific reasoning (HLE ~11%, GPQA Diamond ~76%) and on coding (Terminal-Bench Hard ~25%, SciCode ~38%), consistent with gaps on the hardest science and agentic coding benchmarks
➤ It supports visual reasoning and scores 63% on MMMU-Pro (between Claude 4.5 Haiku at 59% and GPT-5.4 nano (xhigh) at 65%)
2
2
14
1,920
Irem Ergün retweeted
May 20
fastest model on artificial analysis
Introducing: Cohere Command A
We’ve created our most powerful LLM yet, optimized it to run on as little hardware as possible, and released it open-source for all.
2
4
83
13,623
Irem Ergün retweeted
May 20
Cohere cracks lossless quantization and native citations with first full Apache 2.0 licensed open model Command A
venturebeat.com/ai/cohere-cr…
2
16
1,380
Irem Ergün retweeted
May 20
Cohere dropped Command A 🔥
> 25B/219B MoE vision language model
> supports 48 languages with efficient tokenizer
> tool-calling/agentic 128k context window
> transformers day-0 support 🤗
free license 💗
3
8
94
7,171
Releasing open-source under the Apache 2.0 license. We want to give developers direct access to enterprise-grade agentic capabilities from experimentation to production.
Sovereign AI. For all.
Download Command A : huggingface.co/CohereLabs/co…
Or learn more: cohere.com/blog/command-a-pl…
11
31
302
32,626
Irem Ergün retweeted
May 20
Command A from @cohere is out now :) its our best model yet and its open source apache 2.0
56
132
1,342
203,234
Irem Ergün retweeted
May 20
Our first model @cohere that is all inclusive - vision enabled, reasoning on, MoE, and super efficient. Apache 2.0 is the cherry on top!
Super proud of being a part of the effort to bake this model! It has better vision perf than Command-A-Vision!
It’s a delicious release, enjoy ☺️
Introducing: Cohere Command A
We’ve created our most powerful LLM yet, optimized it to run on as little hardware as possible, and released it open-source for all.
1
5
45
2,034
Irem Ergün retweeted
May 20
Extremely excited to present Command A , our first sparse model!
I am very proud of the work we did to enable this model. We built our sparse training stack from the ground up over the past year with a lot of custom kernels, performance engineering to enable us to train large sparse models with a very small compute footprint.
We presented our work on a fully dropless FP8 kernel stack for sparse models at Nvidia GTC earlier this year. We are extremely ambitious and are marching towards a state-of-the-art model training stack, come join us if you are interested in pushing the frontier!!
Apply here - jobs.ashbyhq.com/cohere/d42f…
Our work here - nvidia.com/en-us/on-demand/s…
Introducing: Cohere Command A
We’ve created our most powerful LLM yet, optimized it to run on as little hardware as possible, and released it open-source for all.
12
83
9,456
May 20
Excited to share what we have been working on at Cohere; Command A !
- Our most powerful, fastest model yet.
- Multilingually yours in 48 languages.
- Fully open-source with weights on HuggingFace: huggingface.co/CohereLabs/co…
Enterprise-grade agentic capabilities for all ❤️🔥❤️🔥
Give it a go!
Introducing: Cohere Command A
We’ve created our most powerful LLM yet, optimized it to run on as little hardware as possible, and released it open-source for all.
3
29
1,590
May 20
LFG!!!! 🏃🏻♀️💨
A major step forward for sovereign enterprise AI in healthcare and biopharma.
Cohere has acquired @reliant_ai 🇨🇦🇩🇪
1
10
775
Irem Ergün retweeted
Konuşma ve atölye programımız yayınlandı. 🥁
Program komitemize ve başvuru gönderen herkese çok teşekkür ederiz. Harika bir konferans bizi bekliyor!
Biletler tükenmeden siz de bize katılın. Program detayları için divaconf.com/schedule sayfamızı ziyaret edebilirsiniz.
ALT Illustrated promotional graphic for the “Dive Into AI” conference. The design features layered rounded rectangles in pastel lilac and lime green with orange flower-like decorative shapes. At the top is the Dive Into AI logo with stylized mirrored faces inside the letters. Large dark blue text in the center reads: “THE SCHEDULE IS LIVE!” At the bottom, a rounded box displays the URL: “DIVACONF.COM/SCHEDULE”.
11
16
13,796
Apr 16
so proud to be a part of this company 🫶🏻🫰🏻
We're proud to be on the @Forbes AI 50 list again! It reflects our focus on building secure, sovereign AI that helps enterprises and governments put their data to work on their terms.
Learn more: forbes.com/lists/ai50/
8
625