Omid Madani

Insightful explanation of how do go channels work behind the scenes. Its all about yielding the ptocessor for other goroutines. https://lnkd.in/gbyQ4yH9

1

Attention documentarians interested in languages, grammar, and AI. I recently discovered that AI researchers are learning a lot by studying Sanskrit, the classical Indian language, and Sanskrit grammar in particular. I spent some time learning Sanskrit in graduate school and was often asked why I would study a dead language. It's fascinating to discover that this subject is relevant to cutting-edge research in technology! This paper spells out the connection between Sanskrit grammar and NLP research in semantic nets: https://lnkd.in/gaeFiXwV. I'm sure the research has come a long way in the 39 years since this was written, but this is a very clear paper that makes the relationship between Sanskrit grammar and NLP explicit. Who knows, maybe one day as technical communicators, we'll be asked to discuss the nuance of grammar alongside what we now think of as more technical subjects! This issue also raises important ethical questions about extracting value from classical Sanskrit scholarship to advance AI. If anyone has any thoughts about this topic or resources to share, I would love to learn more! #sanskrit #ai #grammar

11

2 Comments

Sorry for the delay, but Joachim and I are back with, dare I say it, my favorite episode of Learn, Make, Learn yet! It's focused on the intersection of generative AI and product creation. This is a thorny topic and, fortunately, we're joined by Anmol Anubhai, who brings deep expertise in the field to our conversation. Her human-centered approach to the technology—one rooted in amplifying humans instead of replacing us—actually converted me from an AI-sceptic to a (cautious) AI-optimist. I hope you'll join us for a refreshingly grounded conversation on a topic that’s typically full of hype. You can find “Learn Make Learn” at any major podcast directory or listen at https://lnkd.in/gGv-tE6F And don’t hesitate to share your questions & perspectives here! #LearnMakeLearn #ProductMarketing #ProductManagement #ProductInnovation #GenAI #GenerativeAI

60

5 Comments

Human in the loop evals 🧑‍💻👀 → custom, automated evaluation models 🤖📈? https://lnkd.in/gruPtC8d Human in the loop (HITL) is a really popular technique for teams just getting started with LLMs and their LLMOps functions. Given your biggest concern is your model acting ‘not like a human’, it’s easy to see how sticking a human in the loop, to review and edit any potential mistakes or weirdness, can solve that problem. But it’s equally easy to see how challenging this can be to scale, and how it can eat at a lot of the cost-savings promised by automations. So how should teams approach balancing the security and certainty from human-in-the-loop, with an eye towards scaling? Over the weekend I got the chance to experiment with a few approaches to turning HITL datasets into their own custom evaluation models. I also think about how I would balance my human-agent evaluations alongside my model-driven evaluations, to set me up for long-term success. https://lnkd.in/gruPtC8d

17

1 Comment

Thrilled to support 💪 Perplexity return citations param - https://lnkd.in/g7kkztxX (+4 more updates 👇) ⚡️ Azure - return response headers ✅ Streaming - break out of infinite model loops 🎉 Instructor - fix completion_cost calc 👀 [PR] logging by API key - https://lnkd.in/gAG5YKQa

6

At Corgnit Research Lab, India, we are excited to share our latest findings on the convergence of Reinforcement Learning and Federated Learning and their implications for advancing AGI. Key Insights: - 𝐒𝐜𝐚𝐥𝐚𝐛𝐢𝐥𝐢𝐭𝐲 𝐚𝐧𝐝 𝐄𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐜𝐲: The distributed nature of FL enables scalable and efficient training of RL models, significantly reducing computational overhead and accelerating convergence. - 𝐏𝐫𝐢𝐯𝐚𝐜𝐲-𝐏𝐫𝐞𝐬𝐞𝐫𝐯𝐢𝐧𝐠 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠: By ensuring that sensitive data remains local, FL facilitates the development of AGI in privacy-sensitve domains, such as healthcare, without compromising data security. - 𝐂𝐨𝐥𝐥𝐚𝐛𝐨𝐫𝐚𝐭𝐢𝐯𝐞 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠: Multiple RL agents can share knowledge through FL, enhancing overall learning efficiency and robustness without the need to share raw data. - 𝐏𝐞𝐫𝐬𝐨𝐧𝐚𝐥𝐢𝐳𝐞𝐝 𝐀𝐝𝐚𝐩𝐭𝐚𝐭𝐢𝐨𝐧: The integration of FL allows AGI models to be tailored to individual users or environments, combining global intelligence with local customization. - 𝐑𝐨𝐛𝐮𝐬𝐭𝐧𝐞𝐬𝐬 𝐚𝐧𝐝 𝐑𝐞𝐬𝐢𝐥𝐢𝐞𝐧𝐜𝐞: Aggregating diverse experiences through FL results in more generalized and resilient AGI models, mitigating the risk of overfitting. Benefits for Researchers: - 𝐑𝐞𝐬𝐨𝐮𝐫𝐜𝐞 𝐎𝐩𝐭𝐢𝐦𝐢𝐳𝐚𝐭𝐢𝐨𝐧: Leveraging distributed computational resources lowers costs and enhances the feasibility of large-scale AGI experiments. - 𝐄𝐧𝐡𝐚𝐧𝐜𝐞𝐝 𝐂𝐨𝐥𝐥𝐚𝐛𝐨𝐫𝐚𝐭𝐢𝐨𝐧: Model updates can be shared instead of raw data, promoting cross-institutional and interdisciplinary research. - 𝐀𝐜𝐜𝐞𝐥𝐞𝐫𝐚𝐭𝐞𝐝 𝐃𝐞𝐯𝐞𝐥𝐨𝐩𝐦𝐞𝐧𝐭: Faster training times and rapid iteration lead to quicker advancements in AGI. - 𝐄𝐭𝐡𝐢𝐜𝐚𝐥 𝐀𝐈 𝐃𝐞𝐯𝐞𝐥𝐨𝐩𝐦𝐞𝐧𝐭: Prioritizing user privacy and data security aligns with ethical standards and regulations, fostering responsible AI research. - 𝐑𝐞𝐚𝐥-𝐖𝐨𝐫𝐥𝐝 𝐀𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬: Immediate feedback and improvements from real-world data enable practical deployment in sectors like smart cities, healthcare, and IoT. Our research at Corgnit underscores the transformative potential of merging RL and FL in the pursuit of AGI. We believe these insights will catalyze further innovations and collaborations in the AI community. #ArtificialGeneralIntelligence #ReinforcementLearning #FederatedLearning #AIResearch #CorgnitResearchLab #PrivacyPreservingAI #ScalableAI #EthicalAI Corgnit, Corgnit Research India, Reinforcement Learning, Federated Learning Consortium

20

Very excited to share that I've completed an enriching Natural Language Processing(NLP) course at UC Berkeley this quarter(Part of my Masters degree)! Delving into the intricacies of language comprehension and analysis has been truly enlightening. As we explored concepts like information extraction, sentiment analysis, and machine translation, I couldn't help but reflect on the significance of attention in NLP. Indeed, "Attention is all you need"(Transformer based model) proved to be a guiding principle throughout our studies. Grateful for the opportunity to expand my knowledge in this field! #NLP #UC Berkeley School of Information I highly recommend diving into the research paper linked here (https://lnkd.in/ggA_SrUb), though it may take a few reads to fully grasp its depths, along with Jay Almmar's insightful blog post (https://lnkd.in/gbDJ3Ddj). Excited to delve into "Generative AI" as my focus for the upcoming quarter!

61

5 Comments

A good use case for using context-caching, specially if you are trying to build RAG on a large cluster of documents. https://lnkd.in/gTEaG_ET

3

💡 Exploring Advanced RAG Together 💡 For those considering or already working on integrating RAG-powered GenAI assistants into your products or solutions, I’m excited to share some learnings in an upcoming talk. This session builds on the basics we explored sometime before (https://lnkd.in/dBw4UGA4) and dives into recent advancements like DRAGIN, ERAGent, and GraphRAG. These concepts are inspired by some fascinating research papers that I’ve been exploring, and I hope this discussion can spark ideas and conversations within the community. If this resonates with you, feel free to join in. I’d love to hear your thoughts and experiences as well! 🙌

27

The final draft (18th October 2024) of Leslie Lamport's upcoming book has landed - (via Divyanshu Ranjan) A Science of Concurrent Programs - https://lnkd.in/gbYuxK2v "Correctness of an algorithm was expressed by properties required of its executions. I came to realize that correctness can also be expressed by an abstract program—a more abstract, higher-level one than the abstract pro- gram describing the algorithm. Proving correctness means showing that the abstract program describing the algorithm implements the abstract program describing its correctness, and I developed a method for doing that."

113

Knowledge(a) + Reasoning(b) is "Smartness" says Rangarajan Krishnamoorthy. Humans have more of (b) while machines(read AI) have more of (a). A brilliant combination of Human+Machine Intelligence implies enhanced (a) & (b). A good system of “Probing” enhances our ability to exploit AI using “Prompting”, more in today’s conversational #SmartQAMusings webcast at 1200 today. https://lnkd.in/eRp9pQmQ  #SmartQA #softwaretesting

7

🚀 Exciting News! 🚀 I'm thrilled to announce that I've launched a YouTube channel dedicated to sharing knowledge and insights about the latest in technology! 🌟 My first video, "Getting Started with Copilot Studio in Sinhala," is now live. This video is a comprehensive guide to help you kickstart your journey with Copilot Studio. Whether you're a tech enthusiast or a professional looking to enhance your skills, this channel has something for everyone. https://lnkd.in/gaQ5SuMQ Check it out, subscribe, and let's explore the fascinating world of technology together! 💡 #YouTubeChannel #TechKnowledge #CopilotStudio #Microsoft #Learning #Innovation #MicrosoftCopilotStudio #MicrosoftAI #TechInnovation #AIforBusiness #ProductivityBoost #FutureOfWork #TechSolutions #DigitalTransformation #Innovation #MSFT #Automation #BusinessTech

3

Small models becoming smarter! Phi-3 reinforces the importance of data quality.

24

When you need to play with your data in Gen Ai, you need RAG and Chunking is one of the main component in the RAG framework while consuming or processing your data. Excellent post below describing how in different ways chunking in RAG can be implemented..

23

1 Comment

Evaluating Large Language Models: Key Metrics and Their Application in Real-World Scenarios This article delves into the essential metrics used to assess LLMs, exploring their significance and practical applications, particularly in developing a Question Answering system. Join us as we unpack these evaluation criteria and illustrate their impact on real-world AI implementations. #AI #LLM #Evaluation #AIDevelopment #AIApplication For part 2 of the article, click👇 https://lnkd.in/gd8gDGPM For part 1 of the article, click👇 https://lnkd.in/gdSew4uV For a quick summary - Swipe 👉

14

1 Comment

TRIPLE BAM! If you missed it, here's the recording of our live Q/A with Jay Alammar and Joshua Starmer PhD! We talked about many AI topics, answered lots of great questions, and talked about two great books: Hands-On Large Language Models: Language Understanding and Generation, and The Illustrated Guide to Neural Networks and AI!!! https://lnkd.in/dcPHs7YQ

44

1 Comment

You don’t normally see LLM researchers and engineers talking about their day-to-day work. Big shoutout to this YouTube video from the Anthropic LLM Interpretability team, the team behind the Golden Gate Claude. It’s amazing to see that most of the team members have worked for the team for only one year, and yet they have made such a big breakthrough in interpretability research. Another thing I want to highlight is the unique challenges facing the team and how they approach these challenges, that is, through fast trial-and-error iterations and constant evaluation of what may work and what to prioritize next. #artificialintelligence #machinelearning #deeplearning https://lnkd.in/eUaPAYch

97

1 Comment