62. Marius-Constantin Dinu - extensity.ai - Building reliable and explainable AI Agent Systems

62. Marius-Constantin Dinu - extensity.ai - Building reliable and explainable AI Agent Systems

Author: Manuel Pasieka October 29, 2024 Duration: 1:15:14

As you surely know, OpenAI is not very open about how their systems works or how they build them. More importantly for most uses and business, OpenAI is agnostic about how users apply their services and how to make most out of the models multi-step "reasoning" capabilities .


As a stark contrast to OpenAI, today I am talking to Marius Dinu, the CEO and co-founder of the austrian startup extensity.ai. Extensity.ai as a company follows an open core model, building an open source framework which is the foundation for AI Agent systems that perform multi-step reasoning and problem solving, while generating revenue by providing enterprise support and custom implementation's.


Marius will explain how their Neuro-Symbolic AI Framework is combining the strengths of symbolic reasoning, like problem decomposition, explainability, correctness and efficiency with an LLM's understanding of natural language and their capability to operate on unstructured text following instructions.


We will discuss how their framework can be used to build complex multi-step reasoning workflows and how the framework works like an orchestrator and reasoning engine that applies LLM's as semantic parsers that at different decision points decide what tools or sub-systems to apply and use next. As well how in their research, they focus on ways to measure the quality and correctness of individual workflow steps in order to optimize workflow end-to-end and build a reliable, explainable and efficient problem solving system.


I hope you find this episode useful and interesting.



## AAIP Community

Join our discord server and ask guest directly or discuss related topics with the community.

https://discord.gg/5Pj446VKNU


## TOC

00:00:00 Beginning

00:03:31 Guest Introduction

00:08:32 Extensity.ai

00:17:38 Building a multi-step reasoning framework

00:26:05 Generic Problem Solver

00:48:41 How to ensure the quality of results?

01:04:47 Compare with OpenAI Strawberry


### References

Marius Dinu - https://www.linkedin.com/in/mariusconstantindinu/

https://www.extensity.ai/

Extensity.ai - https://www.extensity.ai/

Extensity.ai YT - https://www.youtube.com/@extensityAI

SymbolicAI Paper: https://arxiv.org/abs/2402.00854


Hosted by Manuel Pasieka, the Austrian Artificial Intelligence Podcast offers a grounded, local perspective on a global phenomenon. Instead of abstract theorizing, each conversation focuses on the tangible impact and practical applications of AI within Austria's unique ecosystem. You'll hear from a diverse range of guests-researchers, entrepreneurs, policymakers, and creatives-who are actively shaping this landscape, discussing both the remarkable opportunities and the nuanced challenges specific to the region. The discussions delve into how these technologies are being integrated into Austrian industry, academia, and society, moving beyond hype to examine real-world implementation and ethical considerations. This podcast serves as an essential audio forum for anyone in Austria, or with an interest in the European tech scene, looking to understand how artificial intelligence is evolving right here. It’s about the people behind the algorithms and the local stories within a global revolution. For those engaged with the content, questions and suggestions are always welcome at the provided email address.
Author: Language: English Episodes: 73

Austrian Artificial Intelligence Podcast
Podcast Episodes
71 - NeoAlp - Humanoide Robotik - Zwischen Dystopie und Euphorie [not-audio_url] [/not-audio_url]

Duration: 1:41:48
Die letzten Jahre ware von Large Language Models dominiert, und für die meisten ist GenAI immer noch der Inbegriff von Fortschritt.Andere denken schon weiter und zielen auf physical AI ab, welche sich darauf spezialisier…
67. Mathias Neumayer and Dima Rubanov - Lora a child friendly AI [not-audio_url] [/not-audio_url]

Duration: 53:10
## SummaryLarge Language Models have many strengths and the frontier of what is possible and what they can be used for, is pushed back on the daily bases. One area in which current LLM's need to improve is how they commu…
66. Taylor Peer - Beat Shaper - A music producers AI Copilot [not-audio_url] [/not-audio_url]

Duration: 52:20
Today on the show I have the pleasure to talk to returning guest, Taylor Peer one of the co-founders of the startup, behind Beat Shaper.Taylor will explain how they are following an Bottom-up approach to create electroni…
65. Daniel Kondor - CSH - The long term impact of AI on society [not-audio_url] [/not-audio_url]

Duration: 1:04:50
Guest in this episode is the Computational Social Scientist Daniel Kondor, Postdoc at the Complexity Science Hub in Vienna.Daniel is talking about research methods that make it possible to study the impact of various fac…
64. Solo - Manuel Pasieka on the hottest LLM topics of 2024 [not-audio_url] [/not-audio_url]

Duration: 59:00
With the last episode in 2024, I dare to release an solo episode, summarizing my christmas research on the topics of - Small Language models - Agentic Systems - Advanced Reasoning / Test time compute paradigm I hope you…