Content
@
https://warpcast.com/~/channel/pinata
0 reply
0 recast
0 reaction
Steve
@stevedylandev.eth
These two images tell a fascinating story On the left, we have a server running on a GPU enabled machine that can run local AI models through Ollama, and with x402 monetize that usage On the right, we have a request being made to that server using the OpenAI SDK and x402-fetch Distributed AI is near, and so is the blog post on this experiment
2 replies
0 recast
15 reactions
osama
@osama
why would you distribute the inference infra? what's the forcing function? def is not economical/private. what is it then? how does on-device come into play here? genuine question.
1 reply
0 recast
0 reaction
Steve
@stevedylandev.eth
Admittedly it’s not a complete solution but conceptually it sets up a world where higher compute hardware is more accessible outside of large central providers, and for that hardware to be monetized.
2 replies
0 recast
0 reaction
Royal
@royalaid.eth
Yeah this feels like a sketch of what automatic and self service AI looks like, not so much "decentralized" but rather something between federated and distributed.
2 replies
0 recast
3 reactions
Kyle Tut
@kyletut
I feel like we are stumbling around in the dark trying to figure out what the room is that we are in. We've stubbed our toe on a chair so far but don't know what else is around us. If AI is going to be as dynamic as people think, access to computing definitely needs to have less boundaries but we don't have good examples of that today. In 10 years, we will be able to point at Steve's example as a primitive example of everyday computing but we are probably missing some key components right now.
2 replies
0 recast
3 reactions
osama
@osama
an asic that runs full cnn including finetuning (of sorts for new objects) and w/ a camera costs $9. compute is more accessible than ever before and will continue to be. same will happen to large models. they won't remain "large" and run on asics ($100-200 later $10) within 18mos or so
1 reply
0 recast
0 reaction
Royal
@royalaid.eth
100%, to draw an allegory from jet engine development: We know what the goal is, we know we can get there, but its a matter of tuning everything just right to get the loop to complete in a useful way. Some examples of issues that need solving: Context length restrictions - Real time world knowledge is limited Context Retrieval at long lengths - In task knowledge is limited Model Speed (this is getting solved pretty effectively over time) - Feedback cycle during agentic execution Vector-Goal Divergence - agents going off an tangents (looking at you 3.7 sonnet) Model Alignment - Prompts are lossy, this compensates for that All of this can be compensated for through things like RAG and scaffolding and eventually these issues will be solved. Once they are then its just a matter of getting tool_calls wired up, for physical stuff see work @july is doing. Crypto then provides payment rails. Then fully agentic systems can emerge. 10 years feels right.
2 replies
0 recast
3 reactions
