Dinos Papakostas's Avatar

Dinos Papakostas

@din0s.me.bsky.social

Research Engineer at Zeta Alpha. Likes 🧠 neural IR, πŸ“‹ model evals, and πŸ‹οΈ lifting weights. Incredibly optimistic about the future! 𝕏: din0s_ / πŸ–₯️: din0s.me

526 Followers  |  117 Following  |  75 Posts  |  Joined: 18.11.2024  |  1.5587

Latest posts by din0s.me on Bluesky

Post image

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...

08.08.2025 14:13 β€” πŸ‘ 3    πŸ” 3    πŸ’¬ 0    πŸ“Œ 0
Post image

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...

09.07.2025 09:11 β€” πŸ‘ 6    πŸ” 2    πŸ’¬ 1    πŸ“Œ 0
Preview
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...

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-...

30.06.2025 14:19 β€” πŸ‘ 1    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0
Preview
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...

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-...

15.05.2025 08:22 β€” πŸ‘ 3    πŸ” 2    πŸ’¬ 1    πŸ“Œ 0

Join us next Friday!

02.05.2025 08:43 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

πŸ“’ Zeta Alpha is going to OpenSearchCon Europe 2025 πŸ“’

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: 🧡

24.04.2025 15:39 β€” πŸ‘ 3    πŸ” 2    πŸ’¬ 1    πŸ“Œ 0
Preview
Trends in AI: April 2025 - by Zeta Alpha Β· Zoom Β· 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…

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:

01.04.2025 16:03 β€” πŸ‘ 8    πŸ” 3    πŸ’¬ 1    πŸ“Œ 0

Grok starting the month with >50% is ridiculous. Did people really think Big Tech wouldn't roll out even a single incremental update? (let alone a big push like Gemini)

26.03.2025 14:46 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

yup, it also caught my eye because they say they did this "in contrast with gecko", and although there's no ablation study in the paper on this im sure they had some internally

22.03.2025 20:25 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

I wish they elaborated more on the model souping part though, it still surprises me to this day that weight merging just works πŸ§™πŸ»β€β™‚οΈ

20.03.2025 12:09 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

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!

20.03.2025 12:08 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

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!

14.02.2025 13:51 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

great thread!

13.02.2025 09:39 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

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?

04.02.2025 17:00 β€” πŸ‘ 2    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0
Preview
Zeta Alpha recognized as a leading native AI enterprise search technology provider. Zeta Alpha recognized as a leading native enterprise AI search technology provider.

Zeta Alpha recognized as a leading native AI enterprise search technology provider.

www.zeta-alpha.com/post/zeta-al...

23.01.2025 10:33 β€” πŸ‘ 6    πŸ” 4    πŸ’¬ 0    πŸ“Œ 0

sell me on ghostty? why should one switch over iterm2/kitty

06.01.2025 11:10 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

they're all you need

13.12.2024 22:47 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

i hope 2025 is the year of good ui/ux for ai

13.12.2024 06:00 β€” πŸ‘ 4    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

friends don’t let friends build RAG pipelines without understanding IR theory. sounds like a solid christmas gift for someone you care about!

12.12.2024 21:12 β€” πŸ‘ 3    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0

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!

12.12.2024 18:53 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
AI Engineer Pack by ElevenLabs The AI Engineer Pack by ElevenLabs offers AI developers exclusive access to premium tools and services, including ElevenLabs, Mistral, Perplexity, and many more. Enhance your AI projects with this com...

www.aiengineerpack.com

This pack by Black Forest Labs gets you great value: $50 API credits for BWL, replicate, Mistral; 6 mo HF pro; 1 year perplexity pro; among others.

11.12.2024 19:59 β€” πŸ‘ 9    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0
Post image

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.

11.12.2024 17:41 β€” πŸ‘ 4    πŸ” 2    πŸ’¬ 1    πŸ“Œ 1
Video thumbnail

wait what happened, why do i have apple intelligence on my mac... πŸ‘€

07.12.2024 00:22 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

the real reason we don't have agi yet is that uv's documentation isn't in the llms' training data

06.12.2024 20:22 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

"think harder" is going to become in 2025 what "shorter" has been in 2024

05.12.2024 18:45 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

on a similar note, this is another banger paper you should read

05.12.2024 17:35 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

how about you o1-pro vide some benchmark numbers and real use cases

05.12.2024 16:43 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

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: 🧡

05.12.2024 14:36 β€” πŸ‘ 5    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0
Post image

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

05.12.2024 08:50 β€” πŸ‘ 4    πŸ” 2    πŸ’¬ 0    πŸ“Œ 0
Post image Post image Post image

spent the day reading the OpenScholar and TΓΌlu 3 papers in detail. AI2 x UW has been on fire lately, this is what real β€œOpen AI” looks like πŸ˜‰. big thanks to both author teams for such thorough and well-crafted work.

04.12.2024 16:18 β€” πŸ‘ 4    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

@din0s.me is following 20 prominent accounts