compound AI systems
Systems that integrate multiple components (language models, tools, verifiers, databases) designed together to solve problems more effectively than monolithic models alone
As defined in What are AI Agents?
Other definitions
Architectures that combine multiple models, models of different sizes, and other components to achieve performance and efficiency goals.
Sarah Guo - The Power of Conviction - [Invest Like the Best, EP.383]
Where it comes up · 2
- What are AI Agents?8 claims
- Sarah Guo - The Power of Conviction - [Invest Like the Best, EP.383]2 claims
Most important claims · 10 of 10Search all claims for “compound AI systems” →
- Efficiency has never stopped mattering in computing because someone always pays for it; while a model company can absorb inefficiency for a long time with a strong other business, in a vacuum more efficiency improves latency, cost, and scalability.Sarah Guo - The Power of Conviction - [Invest Like the Best, EP.383]
- Compound AI systems recognize that certain problems are better solved by applying principles of system design, which treats the solution as modular with multiple interchangeable components (models, tools, verifiers) rather than tuning a single model.What are AI Agents?
- Compound AI systems traditionally have programmatic control logic that is defined by the human designer, but an alternative approach is to put a large language model in charge of the control logic.What are AI Agents?
- The magic of compound AI systems is unlocked when you build systems around the model and integrate the model into existing processes, providing it with access to relevant databases and tools.What are AI Agents?
- RAG systems and typical compound AI systems are defined by fixed programmatic control logic where a specific path must be followed to answer queries, causing them to fail when asked about topics outside their designed scope (e.g., asking about weather when designed for vacation queries).What are AI Agents?
- Compound AI systems can include output verifiers, programs that break down queries to increase correctness, database searches, and various tools that can be combined to solve specific problems.What are AI Agents?
- The term 'control logic' in compound AI systems refers to the path or sequence of steps a program must follow to answer a query.What are AI Agents?
- A likely big change in the AI ecosystem is using a mix of distilled models of different scales inside compound AI systems to reach performance and efficiency goals, since efficiency was not a major consideration for research labs and application companies until recently.Sarah Guo - The Power of Conviction - [Invest Like the Best, EP.383]
- Retrieval Augmented Generation (RAG) is one of the most popular and commonly used compound AI systems.What are AI Agents?
- Compound AI systems are here to stay, and the major trend for 2024 is that they will become more agentic, with an increasing amount of autonomy being placed in the LLM to control the system logic.What are AI Agents?