Introducing our work on general-purpose LLM Agents | GoodAI
goodai.com
Introducing our work on general-purpose LLM Agents | GoodAI
While chains define reusable logic by sequencing components, agents leverage chains to take goal-driven actions. Agents combine and orchestrate chains. The agent observes the environment, decides which chain to execute based on that observation, takes the chain’s specified action, and repeats.
Ben Auffarth • Generative AI with LangChain: Build large language model (LLM) apps with Python, ChatGPT, and other LLMs
The main differences between the AutoGPT project and traditional LangChain agents can be attributed to different objectives. In AutoGPT, the goals are often more open ended and long running. This means that AutoGPT has a different AgentExecutor and different way of doing memory (both of which are more optimized for long running tasks).
Autonomous Agents & Agent Simulations
am using my own hardware at home to infer, train, and fine-tune (or trying to; my training efforts have been pretty disasterous so far, but inference works very well).
My current uses of LLM inference are:
My current uses of LLM inference are:
- Asking questions of a RAG system backed by a locally indexed Wikipedia dump, mainly with Marx-3B and PuddleJumper-13B-v2,
- Code co-pilot with Rift-C