Phil Mui

The volume of biomedical research has outgrown human cognition. NLP and ontology alignment now convert this vast literature into structured, actionable knowledge. We’re proud to help biotech and pharma teams build these intelligent pipelines. Our work spans advanced data extraction, semantic normalization, and graph-driven discovery. The future of scientific insight is machine-augmented—and it’s here. #TAISTurns10 #TheAISummit #AISummitNewYork #AI #AgenticAI #HealthTech #PharmaAI #NLP #KnowledgeGraph Anshar Labs, Inc.

33

2 Comments

At the moment, "health advice" from LLMs is heavily dependent on prompt wording and is frequently wrong (study link below). This is another example of needing a "human in the loop" - in this case, a human with medical training - to use the vast knowledge base of LLMs effectively. Yes, the LLMs will continue evolving and improving. But they will likely still lack true wisdom of an experienced medical professional. At Google, we often sited this rare diseases point: while they are indeed rare, there are so many of them that ~ 1 in 10 people in the US has a rare disease. In purely hypothetical terms, who could more easily identify a specific rare disease: a physician who might have seen a handful of cases in their career, or a huge knowledge base that has recorded thousands of cases? The reality is, of course, that a clinician who is skilled at interacting with a human patient AND an LLM, would be far more effective than either of those options alone. #healthcare AI

1

2 Comments

🚀 Act Three of my Hypermodern GenAI series is live! This chapter dives into LangChain’s Deep Agents and what they mean for the future of agent frameworks. From shallow vs deep agents to reasoning LLMs, I explore how these patterns shape the way we actually build and ship GenAI apps. The series isn’t about chasing hype — it’s about asking the hard questions: 🔹 When should we follow the defaults? 🔹 When does “depth” help, and when does it just add overhead? 🔹 How do we balance user experience, developer productivity, and system cost? Think of it as a guidebook for hypermodern generative AI agents: rethinking the playbook, experimenting carefully, and building with the user in mind.

3

1 Comment

Great lineup of events in Massachusetts coming from the Massachusetts AI Coalition over the next few weeks. Why do IRL events matter? Three reasons: 1.) You'll get more practice building with AI and learn about AI, 2.) You'll meet all of the great founders & operators in Boston at their companies in case you decide you want to work at them, 3.) You'll make friends. A community of friends is a powerful community. A community of zoom aquaintances is no community at all. By meeting people in real life, you have the opportunity to connect on what each other are building, yes, but you'll also learn about each other's personal lives... hobbies... interests... families. You will make friends. It sounds cheesy, but to build a vibrant community, you have to care about the people beside you. Put in the work to get out into the community and the friends will come. Request to join an event. Your older self will thank you for it. We'll see you out there my friends. Nice work Sonika Vuyyuru for taking lead on these posts, as well as to Sam Iannone, Michelle Fitzgerald, Beth York, Liam Saven for producing content regularly for the AI Coalition. Well done!

22

4 Comments

Ontologies remain one of the most effective ways to ground AI memory, keeping extracted knowledge anchored to existing structures and adaptable through feedback. As memory systems evolve, their role remains essential, and a core focus at Cognee.

47

4 Comments

What if an AI could adopt roles like “thoughtful mentor,” “direct analyst,” or “empathetic listener”—not just by tone, but by structurally encoded behavior? Anthropic’s latest research on Persona Vectors shows how Claude can shift its personality and communication style through vector-based prompting, rather than word-based instructions. This could reshape how we think about user experience, personalization, and safety in LLMs. Worth a read for anyone thinking seriously about human-AI interaction design. 🔗 Read more here: https://lnkd.in/eyNxG53k #AI #LLM #PersonaDesign #HumanCenteredAI #PromptEngineering #Anthropic #Claude #AIUX #ResponsibleAI #FutureOfWork

13

2 Comments

Do read this fantastic piece from Andy Slavitt and Toyin Ajayi on why we must not leave out underserved populations from the wave of healthcare AI transformation that is just starting.

5

1 Comment

This recent memo from the administration shows they are thinking big about how science and technology fuel the nation’s next leap forward. AI, biotech, energy, and space are front and center, but what stands out most is the focus on people and infrastructure: building the workforce, strengthening labs, and connecting agencies to move faster together. It’s a smart reminder that successful innovation requires more than creativity and inspiration. It's needs coordination and integration across a complex ecosystem of moving parts. I’m encouraged to see a call for that kind of alignment, because when agencies share tools, talent, and trust, breakthroughs happen faster. ✨ https://lnkd.in/eEbXfBWg

1