Smart LLM Routing & Novel Multi-Agent Framework

  Рет қаралды 5,092

Discover AI

Discover AI

Күн бұрын

Пікірлер: 5
@johnkintree763
@johnkintree763 2 ай бұрын
GraphRouter is an interesting concept. A Wiki implementation that would allow many people to input the performance of different LLMs on different tasks might be helpful. Users should also be able to specify their hardware, such as Oneplus 11 smartphone with 16 GB RAM, so the GraphRouter would select an LLM that is optimized for it.
@dennis8965
@dennis8965 2 ай бұрын
From a real world product perspective a graph ML approach towards effective prompt routing is completely over engineered. The underlying problem is simple and given the speed and intensity of ongoing progress a solution must consider performance and adaptability at the same time.
@timothywcrane
@timothywcrane 2 ай бұрын
I agree that most are just adding a higher level complexity where it is really unneeded. This does have its place however. I use this same process in general for all of my LLM selections, Prompt reiteration, and even command functions... but my graphs are DAGs built off of a custom local BTRfs subvolume set (and a btrfs/Freenet repo). When your FS is the Graph your system traverses it makes this higher level complexity go away and allows the benefits of the Graph Services to be had at a "root level". Nothing like having an LLM Agent using your FS and eBPF/Kernel hook on a GNN's Index that is the system itself... Makes the Desktop a convenience for user display instead of a need for computing or tasking ;)
@dragoon347
@dragoon347 2 ай бұрын
Its not this hard... Distributed neural network. You add on tensors onto each edge device depending how much they can handle then you distribute the computing across many many many devices. You can scale this infinitely. Its like a bonnet neural net.
@Philosophizer2
@Philosophizer2 2 ай бұрын
A neural network trained to find novel neural networks .
Automate Agentic Workflow of LLMs: AFLOW (NEW)
20:43
Discover AI
Рет қаралды 5 М.
1% vs 100% #beatbox #tiktok
01:10
BeatboxJCOP
Рет қаралды 67 МЛН
人是不能做到吗?#火影忍者 #家人  #佐助
00:20
火影忍者一家
Рет қаралды 20 МЛН
When you have a very capricious child 😂😘👍
00:16
Like Asiya
Рет қаралды 18 МЛН
The Perfect Communication Protocol for Multi-Agents AI
48:37
Discover AI
Рет қаралды 6 М.
Overparametrized LLM: COMPLEX Reasoning (Yale Univ)
30:01
Discover AI
Рет қаралды 8 М.
LightRAG: A More Efficient Solution than GraphRAG for RAG Systems?
19:49
Prompt Engineering
Рет қаралды 41 М.
This is how I scrape 99% websites via LLM
22:44
AI Jason
Рет қаралды 177 М.
Stanford & OpenAI Code an Intelligent Shield
52:28
Discover AI
Рет қаралды 4,6 М.
Seven AI Agents and a Knowledge-Graph: AGENTiGraph
24:25
Discover AI
Рет қаралды 6 М.
Multi-Agent Sys: NEW SUPER AGENT & MIT FutureYou
34:48
Discover AI
Рет қаралды 5 М.
CUDA Mode Keynote | Andrej Karpathy | Eureka Labs
23:21
Accel
Рет қаралды 18 М.
1% vs 100% #beatbox #tiktok
01:10
BeatboxJCOP
Рет қаралды 67 МЛН