I am still learning all of this, but it seems to me that the best approach is to start with multiple agents. Each agent should perform a very specific task exceptionally well and log everything. By doing so, you can build large datasets on how each agent operates and fine-tune them accordingly. Over time, you can potentially combine agents to improve efficiency. Initially, however, it is important to observe how they handle specific tasks. I could be wrong, but it appears that if you can precisely define what the LLM is doing, you can prevent hallucinations. This approach might involve higher upfront costs, but in the long term, it could lead to faster progress, as you wouldn't be trying to solve problems with agents that are stretched too thin. The advantage here is that, unlike starting a company where having too many employees significantly increases costs, using multiple agents does not lead to a substantial cost increase. While compute costs money, it is not as expensive as hiring additional human employees.
// I could be wrong, but it appears that if you can precisely define what the LLM is doing, you can prevent hallucinations. You are right in some way. You have to remember that the AI is dumb, so it only does what you tell it to do - Hence "crap in, crap out". The more specific your prompt is the better the output would get. There is alot of tips around, like giving them more context etc. Also, you could specific control the level of hallunications by a value from 0 - 1. If I where to build instructive agents I would have them at a low temperature level of hallunication, but if I where to build some storytellers for marketing I would allow a high level of hallunication.
I'm curious to hear about what is the best approach to build multi-agents workflows in AutoGen. In particular, do you: - set up and debug every single agent, and then put them together in a group chat - or rather start building within the group chat already?
Your multi-agent AI projects will benefit from SmythOS's robust AI agent platform. It's a fantastic option for anyone trying to improve their AI products.
Thank you, great tooling. I can't wait to see it grow
I am still learning all of this, but it seems to me that the best approach is to start with multiple agents. Each agent should perform a very specific task exceptionally well and log everything. By doing so, you can build large datasets on how each agent operates and fine-tune them accordingly. Over time, you can potentially combine agents to improve efficiency. Initially, however, it is important to observe how they handle specific tasks.
I could be wrong, but it appears that if you can precisely define what the LLM is doing, you can prevent hallucinations. This approach might involve higher upfront costs, but in the long term, it could lead to faster progress, as you wouldn't be trying to solve problems with agents that are stretched too thin.
The advantage here is that, unlike starting a company where having too many employees significantly increases costs, using multiple agents does not lead to a substantial cost increase. While compute costs money, it is not as expensive as hiring additional human employees.
// I could be wrong, but it appears that if you can precisely define what the LLM is doing, you can prevent hallucinations.
You are right in some way. You have to remember that the AI is dumb, so it only does what you tell it to do - Hence "crap in, crap out". The more specific your prompt is the better the output would get. There is alot of tips around, like giving them more context etc.
Also, you could specific control the level of hallunications by a value from 0 - 1. If I where to build instructive agents I would have them at a low temperature level of hallunication, but if I where to build some storytellers for marketing I would allow a high level of hallunication.
I'm curious to hear about what is the best approach to build multi-agents workflows in AutoGen. In particular, do you:
- set up and debug every single agent, and then put them together in a group chat
- or rather start building within the group chat already?
Your multi-agent AI projects will benefit from SmythOS's robust AI agent platform. It's a fantastic option for anyone trying to improve their AI products.
what are benchmarking and evaluation tools for agentic workflow
GAIA benchmark