In-depth rational breakdowns are missing in this space… Dan definitely is one of the best AI channels on RUclips.. worthy sub too because I wanna see this channel grow
It would be interesting to explore the evaluator function in depth. Like it’s one thing if you have a hard defined set of criteria for what a good end respons is. It’s another thing when the definition of a good response can be more less easy to define. Like the advice of an AI therapist. If you have three chains you’re getting three slightly different answers and there in general very similar but in that case how do you determine the best answer? My thinking is that in that case it’s really important to understand the end user, in order to be able to accurately choose the best response to deliver them. So it’s the idea that the current mental and emotional state of the end user (patient) and their goals help make the decision of what response that evaluator will choose. It’s the idea that one of those responses will get that patient closer to their goals factoring in their current emotional and mental state. So it would definitely need to probably send the responses from the different chains and the patient data to another set of chains which attempt to simulate the future or predict make predictions.
Yeah I think the 'evaluator' is going to be a topic we touch on again for reasons you mention. "My thinking is that in that case it’s really important to understand the end user..." This is the key of a great prompt chain, evaluator, and really a great product. Determining the best answer (prompt result) comes down to knowing your user and knowing the outcome you're looking for.
Thanks for creating. Helps out a lot ! Just one small question to put an audio low-cut around 100hz because the typing sounds rumbles up the low-end. Keep grinding, good work.
I think your fusion is missing a key step in between where each LLM gets a revision step and access to all answers to revise their previous answer. Add that in before the final resolver and you have gold. I can link a demo.
8:10 U could develop system of having the best prompts chosen by an initiator agent and an evaluator agent. Have the initiator agent built into a reinforcement algorithm that's been trained or tuned with a related dataset. Then have both agents run in a feedback loop until the optimal prompt flows is chosen. Have the evaluator use some kind of metrics or benchmarks to rate the output, until the most optimized output is chosen. (This also might put prompt engineers, out of work if it ever became a thing)
interesting, would love to see this added as an option to Aider. Not sure how one can say this would outperform gpt-5 without trying it, but using gpt-5 in a fusion chain makes sense. Of course though, there's the cost... once the end result is funnelled back to the start does the whole chain run again?
It would be interesting but I also love how lightweight Aider is. It makes few assumptions and relies on the model to do the hard work. It's almost guaranteed though that a prompt chain and fusion chain would increase results coming out of Aider and really any LLM/Prompt reliant tool. In a self improving chain/workflow thats the idea - some feedback from the end result gets funneled back into the start of the chain.
How might we fold DSPY into this concept. Stanford storm employs DSPY. Storm takes prompt chains, so DSPY takes prompt chains. Is there a better workflow?
Vst am int -- Oriental where, he used, policy Dutch Waffen! V=verified -- hence; I served - with them! Hence; I -- had - that int! Fused index! You have, no f(x) - and call it, any int!
In-depth rational breakdowns are missing in this space… Dan definitely is one of the best AI channels on RUclips.. worthy sub too because I wanna see this channel grow
It would be interesting to explore the evaluator function in depth. Like it’s one thing if you have a hard defined set of criteria for what a good end respons is. It’s another thing when the definition of a good response can be more less easy to define. Like the advice of an AI therapist. If you have three chains you’re getting three slightly different answers and there in general very similar but in that case how do you determine the best answer?
My thinking is that in that case it’s really important to understand the end user, in order to be able to accurately choose the best response to deliver them. So it’s the idea that the current mental and emotional state of the end user (patient) and their goals help make the decision of what response that evaluator will choose. It’s the idea that one of those responses will get that patient closer to their goals factoring in their current emotional and mental state. So it would definitely need to probably send the responses from the different chains and the patient data to another set of chains which attempt to simulate the future or predict make predictions.
Yeah I think the 'evaluator' is going to be a topic we touch on again for reasons you mention.
"My thinking is that in that case it’s really important to understand the end user..."
This is the key of a great prompt chain, evaluator, and really a great product. Determining the best answer (prompt result) comes down to knowing your user and knowing the outcome you're looking for.
Thanks for creating. Helps out a lot ! Just one small question to put an audio low-cut around 100hz because the typing sounds rumbles up the low-end. Keep grinding, good work.
yw and that's solid feedback ty
I think your fusion is missing a key step in between where each LLM gets a revision step and access to all answers to revise their previous answer. Add that in before the final resolver and you have gold. I can link a demo.
Btw -- amazing vid. Love your work
8:10
U could develop system of having the best prompts
chosen by an initiator agent and an evaluator agent.
Have the initiator agent built into a reinforcement algorithm
that's been trained or tuned with a related dataset.
Then have both agents run in a feedback loop until the
optimal prompt flows is chosen.
Have the evaluator use some kind of metrics or benchmarks
to rate the output, until the most optimized output is chosen.
(This also might put prompt engineers, out of work if it ever became a thing)
Great vid as always, thanks! Also very interested in Zero Noise. Let me know when you Open Source that. Looks very interesting!
Could I use Flowise to accomplish a fusion chain?
How about create a video with the initial prompt being one shot and then use chain(s) and see if the response is better?
how is this the same or different from mixture of experts? or mixture of agents?
how would you do this with Local Ollama models?
Like MoA with prompt chains!
Great implementation of Fusion Chain. Thanks
interesting, would love to see this added as an option to Aider. Not sure how one can say this would outperform gpt-5 without trying it, but using gpt-5 in a fusion chain makes sense. Of course though, there's the cost... once the end result is funnelled back to the start does the whole chain run again?
It would be interesting but I also love how lightweight Aider is. It makes few assumptions and relies on the model to do the hard work. It's almost guaranteed though that a prompt chain and fusion chain would increase results coming out of Aider and really any LLM/Prompt reliant tool.
In a self improving chain/workflow thats the idea - some feedback from the end result gets funneled back into the start of the chain.
my question is, who is the one going to write the individual prompts
How might we fold DSPY into this concept. Stanford storm employs DSPY. Storm takes prompt chains, so DSPY takes prompt chains. Is there a better workflow?
You always good solutions but with very high and costly implementations. Why not use Local LLMs?
And are on, our internet -- i.e. simulated device net!
What you think about langgraph to build agentic workflows??
LangGraph can definitely work. I'll do a comparison video in the future. What do you think about LangGraph vs AutoGen vs No Library?
@@indydevdan that's gonna be great ❤️👏
what about the cost?
AWESOME! Tks
Vst am int -- Oriental where, he used, policy Dutch Waffen! V=verified -- hence; I served - with them! Hence; I -- had - that int! Fused index! You have, no f(x) - and call it, any int!
Gpt5? And clode 4? Not 4 and 3.5?
/cnt2''px jrfx < II-stp kuiry tub < mrkd int=cjx[cnt2''px II-ztp : avpxn mrkd cjx~tmp]/
/twn u vtd mrk bochel cntpn < spn hlvx kuiry tub < i.e. jrfx cjx || djz mrkd~tmp/
/twon abv~tmp u vfr bochel cntpn < mrkd hlvz djts tub/
/krch floch tub buoy < in mol + II-sztp orb arund ext avpxn cjx djz~tmp/
/i.e. kolmn cntpn i.e. cnt2''px szfluch tub jrfx < kuiry avpxn/