Dinos Papakostas
@din0s.me
Research Engineer at Zeta Alpha. Likes 🧠 neural IR, 📋 model evals, and 🏋️ lifting weights. Incredibly optimistic about the future!
𝕏: din0s_ / 🖥️: din0s.me
𝕏: din0s_ / 🖥️: din0s.me
Pinned
Dinos Papakostas
@din0s.me
· Nov 20
IR people: I'm trying to maintain a starter pack of other retrieval-pilled folks as they join this platform. if you're aware of others missing let me know! (& i wish there was a way to invite collaborators on starter packs & lists...)
go.bsky.app/AZVJeDA
go.bsky.app/AZVJeDA
Quick thread on the EmbeddingGemma technical report. It's a pretty nice paper so check it out!
DeepMind just dropped the technical report behind their SOTA open-weights embedding model, packed with training details, including ablations on modeling choices like encoder-decoder initialization, mean pooling, and model souping. Let's take a look! 📚
September 26, 2025 at 1:12 PM
Quick thread on the EmbeddingGemma technical report. It's a pretty nice paper so check it out!
Really proud of this work, check it out if you're curious about the problems one typically encounters with shipping RAG solutions to production in an enterprise setting!
Shipping a GenAI solution in production with a clear path to ROI is hard. In our latest post, we outline key challenges in Enterprise RAG, go beyond the basics with agents, and explore how automatic optimization can adapt these systems to domain-specific needs.
www.zeta-alpha.com/post/why-gen...
www.zeta-alpha.com/post/why-gen...
Why GenAI Pilots Fail: Common Challenges with Enterprise RAG
Retrieval-Augmented Generation (RAG) is powering the current wave of AI applications, from multimodal question answering and technical document summarization to streamlining knowledge-intensive work f...
www.zeta-alpha.com
September 18, 2025 at 12:13 PM
Really proud of this work, check it out if you're curious about the problems one typically encounters with shipping RAG solutions to production in an enterprise setting!
Reposted by Dinos Papakostas
AI agents are only as useful as the tools they can reliably access, and the latest release of our Agents SDK makes it easy to connect to MCP servers.
We've prepared a quick guide where we bootstrap a minimal MCP-powered chat agent with just a few lines of code:
www.zeta-alpha.com/post/build-m...
We've prepared a quick guide where we bootstrap a minimal MCP-powered chat agent with just a few lines of code:
www.zeta-alpha.com/post/build-m...
August 8, 2025 at 2:13 PM
AI agents are only as useful as the tools they can reliably access, and the latest release of our Agents SDK makes it easy to connect to MCP servers.
We've prepared a quick guide where we bootstrap a minimal MCP-powered chat agent with just a few lines of code:
www.zeta-alpha.com/post/build-m...
We've prepared a quick guide where we bootstrap a minimal MCP-powered chat agent with just a few lines of code:
www.zeta-alpha.com/post/build-m...
Reposted by Dinos Papakostas
Join us for the Zeta Alpha "Trends in AI" show on Friday, July 11th at 8 AM PST / 5 PM CEST live from LAB42 in Amsterdam, and online in San Francisco and around the globe.
Register to receive your Zoom webinar invitation, or watch our live stream on YouTube and LinkedIn: lu.ma/trends-in-ai...
Register to receive your Zoom webinar invitation, or watch our live stream on YouTube and LinkedIn: lu.ma/trends-in-ai...
July 9, 2025 at 9:11 AM
Join us for the Zeta Alpha "Trends in AI" show on Friday, July 11th at 8 AM PST / 5 PM CEST live from LAB42 in Amsterdam, and online in San Francisco and around the globe.
Register to receive your Zoom webinar invitation, or watch our live stream on YouTube and LinkedIn: lu.ma/trends-in-ai...
Register to receive your Zoom webinar invitation, or watch our live stream on YouTube and LinkedIn: lu.ma/trends-in-ai...
Reposted by Dinos Papakostas
In our latest blog post, we covered how we use RAGElo, an open-source toolkit we've developed internally in Zeta Alpha, to compare multiple RAG systems head-to-head and aggregate pairwise preferences into a robust, easy-to-interpret Elo ranking.
Check it out: www.zeta-alpha.com/post/robust-...
Check it out: www.zeta-alpha.com/post/robust-...
Robust evaluations for RAG with RAGElo
Retrieval-Augmented Generation (RAG) systems have gained strong traction because of their ability to ground generated answers in knowledge sources, allowing for higher accuracy and reliability. Howeve...
www.zeta-alpha.com
June 30, 2025 at 2:20 PM
In our latest blog post, we covered how we use RAGElo, an open-source toolkit we've developed internally in Zeta Alpha, to compare multiple RAG systems head-to-head and aggregate pairwise preferences into a robust, easy-to-interpret Elo ranking.
Check it out: www.zeta-alpha.com/post/robust-...
Check it out: www.zeta-alpha.com/post/robust-...
Reposted by Dinos Papakostas
Missed last week's Trends in AI episode on evaluating AI systems? We've got you covered! Check out the highlights in our latest blog: www.zeta-alpha.com/post/trends-...
Evaluating AI Systems - Trends in AI: May '25
The rapid pace of developments in AI has made selecting the most suitable base model for a given task increasingly complex. Determining which public benchmarks accurately reflect downstream performanc...
www.zeta-alpha.com
May 15, 2025 at 8:22 AM
Missed last week's Trends in AI episode on evaluating AI systems? We've got you covered! Check out the highlights in our latest blog: www.zeta-alpha.com/post/trends-...
Join us next Friday!
Join us for the Zeta Alpha "Trends in AI" webinar on Friday, May 9th at 8 AM PST / 5 PM CEST, live from LAB42 in Amsterdam, and online from San Francisco and around the globe.
Register on Luma to receive your webinar invitation, or watch our live stream on YouTube & LinkedIn:
lu.ma/trends-in-ai...
Register on Luma to receive your webinar invitation, or watch our live stream on YouTube & LinkedIn:
lu.ma/trends-in-ai...
May 2, 2025 at 8:43 AM
Join us next Friday!
Reposted by Dinos Papakostas
📢 Zeta Alpha is going to OpenSearchCon Europe 2025 📢
We are excited to be contributing back to the OpenSearch community, sharing insights from our work in Enterprise AI, Neural Search, and Retrieval-Augmented Generation (RAG). Learn more about our talks at the conference below: 🧵
We are excited to be contributing back to the OpenSearch community, sharing insights from our work in Enterprise AI, Neural Search, and Retrieval-Augmented Generation (RAG). Learn more about our talks at the conference below: 🧵
April 24, 2025 at 3:39 PM
📢 Zeta Alpha is going to OpenSearchCon Europe 2025 📢
We are excited to be contributing back to the OpenSearch community, sharing insights from our work in Enterprise AI, Neural Search, and Retrieval-Augmented Generation (RAG). Learn more about our talks at the conference below: 🧵
We are excited to be contributing back to the OpenSearch community, sharing insights from our work in Enterprise AI, Neural Search, and Retrieval-Augmented Generation (RAG). Learn more about our talks at the conference below: 🧵
Reposted by Dinos Papakostas
Join us for our monthly Trends in AI webinar on Thursday, April 3rd, at 8 AM PST / 5 PM CEST! This edition comes live from Hannover Messe, the world's leading industrial tech trade fair, and online in Amsterdam, San Francisco, and everywhere else in the world.
Sign up on Luma with the link below:
Sign up on Luma with the link below:
Trends in AI: April 2025 - by Zeta Alpha · Zoom · Luma
Join us for the Zeta Alpha Trends in AI webinar on Thursday, April 3rd, at 8 AM PST / 5 PM CEST (time to be confirmed). This edition comes live from Hannover…
lu.ma
April 1, 2025 at 4:03 PM
Join us for our monthly Trends in AI webinar on Thursday, April 3rd, at 8 AM PST / 5 PM CEST! This edition comes live from Hannover Messe, the world's leading industrial tech trade fair, and online in Amsterdam, San Francisco, and everywhere else in the world.
Sign up on Luma with the link below:
Sign up on Luma with the link below:
A deep dive into the Gemini Embedding technical report - turns out you don't need any fancy training objectives or architectural tweaks to get SOTA on MMTEB, just a solid base model and high quality data!
Google recently introduced Gemini Embedding, a multilingual text embedding model with remarkable performance. It currently tops the MTEB leaderboard across English, multilingual, and code retrieval tasks. Here's an overview of the key insights from their technical report: 👇
March 20, 2025 at 12:08 PM
A deep dive into the Gemini Embedding technical report - turns out you don't need any fancy training objectives or architectural tweaks to get SOTA on MMTEB, just a solid base model and high quality data!
Wrote a little blog piece on reasoning models as a summary of our latest webinar episode, feel free to share with your non-terminally online friends who want a gentle intro to catch up and what they mean for overall AI capabilities!
Feeling overwhelmed by all the talk about reasoning models? We've summarized the key points from our latest Trends in AI episode, covering the history of reasoning in LLMs, DeepSeek-R1's innovations, and their impact on AI applications. Check it out!
Trends in AI - February '25: Reasoning Models
The world has been buzzing with the performance of DeepSeek R1, the first open-source reasoning model to compete with OpenAI's o1 series, and its implications for the dominance of Big Tech in the AGI…
www.zeta-alpha.com
February 14, 2025 at 1:51 PM
Wrote a little blog piece on reasoning models as a summary of our latest webinar episode, feel free to share with your non-terminally online friends who want a gentle intro to catch up and what they mean for overall AI capabilities!
Reposted by Dinos Papakostas
The whole world is buzzing with the performance of DeepSeek’s reasoning model, R1, and its implications for the dominance of Western tech companies in the AGI race. But what exactly are reasoning models? Did anyone see them coming? And how can they be used to create value?
February 4, 2025 at 5:00 PM
The whole world is buzzing with the performance of DeepSeek’s reasoning model, R1, and its implications for the dominance of Western tech companies in the AGI race. But what exactly are reasoning models? Did anyone see them coming? And how can they be used to create value?
Reposted by Dinos Papakostas
Zeta Alpha recognized as a leading native AI enterprise search technology provider.
www.zeta-alpha.com/post/zeta-al...
www.zeta-alpha.com/post/zeta-al...
Zeta Alpha recognized as a leading native AI enterprise search technology provider.
Zeta Alpha recognized as a leading native enterprise AI search technology provider.
www.zeta-alpha.com
January 23, 2025 at 10:33 AM
Zeta Alpha recognized as a leading native AI enterprise search technology provider.
www.zeta-alpha.com/post/zeta-al...
www.zeta-alpha.com/post/zeta-al...
i hope 2025 is the year of good ui/ux for ai
December 13, 2024 at 6:00 AM
i hope 2025 is the year of good ui/ux for ai
friends don’t let friends build RAG pipelines without understanding IR theory. sounds like a solid christmas gift for someone you care about!
December 12, 2024 at 9:12 PM
friends don’t let friends build RAG pipelines without understanding IR theory. sounds like a solid christmas gift for someone you care about!
Drowning in the 4000 main track papers at #NeurIPS? Here’s a guide to 10 research areas and some of the spotlight papers that grabbed my... attention!
It's #NeurIPS week! With 4K+ main papers, it's OK to feel overwhelmed. Our annual NeurIPS guide is here to help!
We've curated a list of 10 topics and papers to check out, whether you're attending the conference or want to stay updated on the biggest developments in AI.
We've curated a list of 10 topics and papers to check out, whether you're attending the conference or want to stay updated on the biggest developments in AI.
December 12, 2024 at 6:53 PM
Drowning in the 4000 main track papers at #NeurIPS? Here’s a guide to 10 research areas and some of the spotlight papers that grabbed my... attention!
Reposted by Dinos Papakostas
It's #NeurIPS week! With 4K+ main papers, it's OK to feel overwhelmed. Our annual NeurIPS guide is here to help!
We've curated a list of 10 topics and papers to check out, whether you're attending the conference or want to stay updated on the biggest developments in AI.
We've curated a list of 10 topics and papers to check out, whether you're attending the conference or want to stay updated on the biggest developments in AI.
December 11, 2024 at 5:41 PM
It's #NeurIPS week! With 4K+ main papers, it's OK to feel overwhelmed. Our annual NeurIPS guide is here to help!
We've curated a list of 10 topics and papers to check out, whether you're attending the conference or want to stay updated on the biggest developments in AI.
We've curated a list of 10 topics and papers to check out, whether you're attending the conference or want to stay updated on the biggest developments in AI.
wait what happened, why do i have apple intelligence on my mac... 👀
December 7, 2024 at 12:22 AM
wait what happened, why do i have apple intelligence on my mac... 👀
the real reason we don't have agi yet is that uv's documentation isn't in the llms' training data
December 6, 2024 at 8:22 PM
the real reason we don't have agi yet is that uv's documentation isn't in the llms' training data
"think harder" is going to become in 2025 what "shorter" has been in 2024
December 5, 2024 at 6:45 PM
"think harder" is going to become in 2025 what "shorter" has been in 2024
how about you o1-pro vide some benchmark numbers and real use cases
December 5, 2024 at 4:43 PM
how about you o1-pro vide some benchmark numbers and real use cases
Reposted by Dinos Papakostas
NeurIPS, the most prestigious conference in AI, kicks off next week! We will guide you through the top themes and highlights, tomorrow in our webinar, and next week with a detailed blog post and video.
We picked 5 papers that we previously covered in our webinar which will be presented as orals: 🧵
We picked 5 papers that we previously covered in our webinar which will be presented as orals: 🧵
December 5, 2024 at 2:36 PM
NeurIPS, the most prestigious conference in AI, kicks off next week! We will guide you through the top themes and highlights, tomorrow in our webinar, and next week with a detailed blog post and video.
We picked 5 papers that we previously covered in our webinar which will be presented as orals: 🧵
We picked 5 papers that we previously covered in our webinar which will be presented as orals: 🧵
Reposted by Dinos Papakostas
Join us this Friday for the Trends in AI webinar, as we reflect on the breakthroughs that defined 2024 and see how our predictions held up. Plus a NeurIPS highlight reel, plus the trending AI papers of the month, like OpenScholar, M3DocRAG, DeMo, and more!
lu.ma/oefbjkjl
lu.ma/oefbjkjl
December 5, 2024 at 8:50 AM
Join us this Friday for the Trends in AI webinar, as we reflect on the breakthroughs that defined 2024 and see how our predictions held up. Plus a NeurIPS highlight reel, plus the trending AI papers of the month, like OpenScholar, M3DocRAG, DeMo, and more!
lu.ma/oefbjkjl
lu.ma/oefbjkjl
spent the day reading the OpenScholar and Tülu 3 papers in detail. AI2 x UW has been on fire lately, this is what real “Open AI” looks like 😉. big thanks to both author teams for such thorough and well-crafted work.
December 4, 2024 at 4:18 PM
spent the day reading the OpenScholar and Tülu 3 papers in detail. AI2 x UW has been on fire lately, this is what real “Open AI” looks like 😉. big thanks to both author teams for such thorough and well-crafted work.