Samaya AI (@samaya

Samaya AI

61 posts

Samaya AI

@samaya_AI

An AI-powered Knowledge Discovery Platform

Joined April 2022

Samaya AI
@samaya_AI
May 14, 2025
🎉Big news: We’re announcing our Series A led by NEA and $43.5m in funding to build the future of expert intelligence in finance. Led by @NEA with support from visionaries like @ericschmidt, @ylecun, David Siegel, and Marty Chavez. Trusted by premier financial institutions like
30K
Samaya AI
@samaya_AI
Feb 25, 2025
🚀 Samaya AI is hiring 1 to 2 PhD summer research interns in Mountain View, CA! Work on cutting-edge topics: knowledge-grounded LLMs/agents, evaluations, data curation, RL, search/IR, and more! Why Samaya? 🔹 12-16 week paid internship with hands-on mentorship 🔹
27K
Samaya AI
@samaya_AI
Aug 4, 2023
Can Large Language Models effectively use knowledge in their input context? Find out more in our blog post: 'Information Overload: Challenges of Expanding Context Windows in LLMs' samaya.ai/blog🚀@nelsonfliu Ashwin Paranjape @MicheleBevila20 @Fabio_Petroni @maithra_raghu
11K
Samaya AI
@samaya_AI
Jun 5, 2025
Evaluating long-form answers to complex technical questions is very challenging. Existing methods fall short in this setting. At Samaya, we built Criteria-Eval, a checklist-based evaluation that aligns with how domain experts judge answers. 🧵samaya.ai/blog/criteria-… ✍️
3.1K
Samaya AI
@samaya_AI
Sep 19, 2024
It was amazing working with you this summer, @orionweller! 🚀 Check out our paper on Promptriever — the first dense retrieval model that can be prompted like an LLM. 📄🔍
Orion Weller
@orionweller
Sep 18, 2024
Introducing ✨Promptriever ✨ the first retriever that can be prompted like an LM with free-form prompts! Our secret: query-level instruction training lets you keep the promptability of the base LM! 🚫 keyword-matching ✅ instruction search 📝 arxiv.org/abs/2409.11136
arxiv.org
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like...
Instruction-tuned language models (LM) are able to respond to imperative commands, providing a more natural user interface compared to their base counterparts. In this work, we present...
4.1K
Samaya AI
@samaya_AI
Jul 8, 2025
Most AI “deep research” agents hallucinate 🤖💭 And almost none can connect second-order effects. After 4 months of iteration with users, we’re launching Samaya’s Deep Research Agent, built to solve both problems. (📸 example below ⬇️)
2.8K
Samaya AI
@samaya_AI
Mar 25, 2025
Samaya is building AI knowledge agents... but how do we evaluate them? Check out RealityBench: a new evaluation environment that challenges agents to make evidence-grounded predictions about future events! (spoiler: scaling compute = better forecasts!) 📖 Read here:
1.6K
Samaya AI
@samaya_AI
May 14, 2025
Replying to @ericschmidt
Thank you for the kind words and belief in our vision. We’re thrilled for what’s ahead!
309
Samaya AI
@samaya_AI
Oct 19, 2023
Excited for this achievement. Read more in our new blog post samaya.ai/blog! 🚀
Fabio Petroni
@Fabio_Petroni
Oct 19, 2023
Every researcher's path is a rollercoaster filled with numerous lows. With unspeakable joy, today I want to share a high point: our paper, “Improving Wikipedia Verifiability with AI,” has been published in the prestigious @NaturePortfolio. Dive in nature.com/articles/s4225… [1/4]
Samaya AI | Blog
From samaya.ai
8.1K
Samaya AI
@samaya_AI
Aug 28, 2025
Big news at Samaya: our Founder and CEO, @maithra_raghu, has been named to the @TIME 100 AI 2025 list! 🎉 Through her AI research at Google Brain, working with the "Godfather of AI" Geoffrey Hinton, to building @samaya_AI, Maithra has been driven by the vision of Expert AIs that
Maithra Raghu
@maithra_raghu
Aug 28, 2025
Surprised and delighted to be on the @TIME 100 AI list! (And in very good company!) It’s especially meaningful to have this recognition this year, which has been one of incredible growth and milestones for Samaya. We closed our Series A led by NEA, and with other stellar
88K
Samaya AI
@samaya_AI
Apr 8, 2025
🧐 Real-world queries can be long and complex in RAG applications - but today’s retrieval models often fail to understand the subtleties in them. 🚀 In our latest blog, we introduce ✨ Promptriever ✨, our #ICLR2025 work that supercharges retrieval models with instruction
4.4K
Samaya AI
@samaya_AI
May 31, 2023
We have a wonderful new office in London and are hiring in London and the SF Bay Area! Check out samaya.ai for details!
Pasquale Minervini
@PMinervini
May 25, 2023
Replying to @suzatweet @StabilityAI and @AnthropicAI
don't forget @samaya_AI!
samaya.ai
Samaya AI | Expert AI Agents for Financial Services
Trusted by leading financial institutions, Samaya AI accelerates research, automates complex workflows, and delivers sharper investment insights with speed and precision.
5.2K
Samaya AI
@samaya_AI
Feb 25, 2025
Check out the research from our past PhD interns! 📚 🔹 Lost in the Middle: How Language Models Use Long Contexts (TACL 2023) 👉 arxiv.org/abs/2307.03172 🔹 Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models (ICLR 2025) 👉 arxiv.org/abs/2409.11136
2K
Samaya AI
@samaya_AI
Jun 24, 2025
Even great answers can have subtle gaps—missing numbers, overlooked facts. In high-stakes workflows, those gaps cost time and trust. At Samaya, we built a real-time self-correction engine that quality-checks our summaries and fills in missing info before the user notices. 🧵👇
5.9K