https://twitter.com/aidotengineer
1. Opening music – 00:00
2. Announcement – 03:26
3. AI Engineer Summit Opening Remarks – 17:12
4. Benjamin Presentation – 17:22
ㄴ Simon Presentation – 18:39
ㄴ Mobile app function description
ㄴ How to manage session schedule
ㄴ Networking features
ㄴ Badge scanning function
5. Chris Presentation – 21:46
ㄴ Problems and improvements in AI stack
Introduction to the Mojo programming language
ㄴ AI Framework Max Description
6. AWS Presentation (Auntie Aart) – 40:13
5 Steps to Become an AI Engineer
Introducing AWS Developer Tools and Amazon Q
Select your Amazon Bedrock and model
ㄴ How to use Converse API
ㄴ Example of agent construction and use
7. AWS Presentation (Mike Chambers) – 55:01
Minecraft Bot Agent Demo
8. Alex Albert Presentation – 01:00:06
ㄴ Historical comparison of the electric revolution
ㄴ Current and future of LLM integration and utilization
ㄴ Claude 3.5 Sonet model introduction
Introducing new product feature “Artifacts”
ㄴ Project and team collaboration features
ㄴ Tool usage API and console features
ㄴ Introduction to upcoming models and research
9. Harrison Chase Presentation – 01:14:10
ㄴ History and development of agent technology
Introduction to LangGraph
ㄴ Introduction to LangGraph Cloud and Studio
10. Interview and Q&A Session – 01:27:06
11. Music Performance – 01:30:08
12. Introduction to Multimodality Track – 02:27:19
ㄴ Substrate Introduction (Rob) – 02:27:52
ㄴ Advantages of modular intelligence
ㄴ Substrate Developer SDK
ㄴ Substrate inference engine
ㄴ MoonDream Presentation (Vic Kapati) – 02:33:18
ㄴMoonDream model introduction
How to improve performance of small models
ㄴ AI agent construction case
ㄴ Data processing and learning methods
The importance of community and open source
ㄴ Live demo
ㄴ Ben Hilac Presentation – 02:54:00
ㄴ Concept and history of Unbounded products
ㄴ Vision OS design process
ㄴ Present and future of AI products
ㄴ Product structure and intuitiveness
ㄴ Karan Goyle Presentation – 03:15:00
ㄴ The importance of real-time intelligence
ㄴ Challenges and solutions of multimodal AI
ㄴ The need and development of compression models
ㄴ New model design methodology
13. Music Performance – 03:30:00
14. Chang Sha and Noah Presentation – 05:12:08
ㄴ Hierarchical necessity for dataset development
ㄴ Differences between pre-learning and post-learning
ㄴ The importance of data set management
ㄴ Dataset selection and analysis method
ㄴ Utilizing language models to improve language models
15. Steph Dua Presentation – 05:31:29
ㄴ The future of education and multimodal AI
ㄴ The need for AI education
ㄴ AI learning activities for children
ㄴ AI education for parents and teachers
ㄴ Cases of improving education through AI
16. Quinda Halman Kramer Presentation – 05:50:06
ㄴ Building a voice AI agent
ㄴ The need for real-time voice processing
ㄴ Voice recognition and text conversion
ㄴ Voice synthesis and user experience
ㄴ Use cases of voice AI
The importance of reducing latency
ㄴ Introduction to the PIP Cart Project
17. Music Performance – 06:11:00
18. Roman Presentation – 07:08:17
ㄴ Introduction to OpenAI’s developer experience
ㄴ Importance of AGI development
ㄴ Multimodal features of GPT-4
ㄴ Live demo (voice, vision, text)
ㄴ Efficiency of GPT-4 Turbo
19. Presented by Brian Bishoff and Charles Fry – 07:32:03
ㄴ Strategic considerations in LLM application development
ㄴ Team composition and workflow settings
ㄴ Model customization and the future of agents
20. Jason Lou and Hamama Hussein Presentation – 07:47:01
ㄴ Role and expectations of AI engineers
Choose the right tools and techniques
ㄴ Continuous improvement and use of data
21. Presentation by Shrea Shankar and Eugene Yan – 07:56:09
ㄴ Tactical aspects of LLM applications
ㄴ Assess, monitor and set guardrails
ㄴ Performance evaluation method for LLM
ㄴ Data-driven approach
ㄴ Continuous improvement of the system
22. Thomas Domke Presentation – 08:07:40
ㄴ Origin and Evolution of GitHub Copilot
ㄴ Integration strategy across GitHub
The future of collaboration tools
23. Closing speech (Benjamin) – 08:26:00
