Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Openrouter Fusion API

openrouter.ai

Post reply on HN
Print view View original

61–70 of 98 posts

Re: Openrouter Fusion API

#61

Post by fridder »

SubiculumCode wrote: post #57
dsl wrote: post #16

Heh. I built "Fusion" a few months ago as an MCP using OpenRouter. The idea was to give Claude a "panel of experts" to go talk to when it got stuck. After extensive testing and benchmarking I discovered that when you ask one model to judge another's response you don't actually get a better answer. You are just asking it "how closely does this resemble the answer you would have given me." Additional rounds and all the…

I've found that if I tell a judge that the answer came from a small and weak local LLM, it will pick the answer apart brutally...but since I have not done this systematically, I dont know how well it generalizes past my vibes. Anyone else fell like if you can trick the LLM into a mode where it "feels" superior, it will act the asshole very well?

Yeah. I usually do this by telling it to be adversarial and find gaps and holes. Not fool proof but it does seem to increase the quality. It has helped when using local models in particular.

Re: Openrouter Fusion API

#62

Post by ElFitz »

I’ve been experimenting with two things on this:

- multi-model consensus, with multiple cross-review rounds. Obviously, the number of inference tasks explodes with the number of models. Led to some interesting results [^0].

- giving an agent "stray thoughts" produced by the same model, or another, giving the second model a selection of the agent’s context, with different triggers (random, loop detection,…)[^1]. So far has proven very helpful and much cheaper than the first.

[0]: https://github.com/lightless-labs/refinery

[1]: https://github.com/Lightless-Labs/skunkworks/tree/main/flux

Re: Openrouter Fusion API

#64

Post by SubiculumCode »

fridder wrote: post #61
SubiculumCode wrote: post #57

Earlier quoted context omitted.

I've found that if I tell a judge that the answer came from a small and weak local LLM, it will pick the answer apart brutally...but since I have not done this systematically, I dont know how well it generalizes past my vibes. Anyone else fell like if you can trick the LLM into a mode where it "feels" superior, it will act the asshole very well?

Yeah. I usually do this by telling it to be adversarial and find gaps and holes. Not fool proof but it does seem to increase the quality. It has helped when using local models in particular.

Yeah, you have to shortcut the RL-trained people pleasing

Re: Openrouter Fusion API

#67

Post by bilater »

dsl wrote: post #16

Heh. I built "Fusion" a few months ago as an MCP using OpenRouter. The idea was to give Claude a "panel of experts" to go talk to when it got stuck. After extensive testing and benchmarking I discovered that when you ask one model to judge another's response you don't actually get a better answer. You are just asking it "how closely does this resemble the answer you would have given me." Additional rounds and all the…

Nice - I built an npm package in a similar fashion called Agent Order: https://github.com/btahir/agent-order

I think there is alpha just have to be very careful how you let the models com up with solutions and collaborate.

Re: Openrouter Fusion API

#68

Post by lukewarm707 »

ljlolel wrote: post #30

Similar feature launched open-source and end-to-end encrypted on my TrustedRouter https://trustedrouter.com/

this is great

it's nice to see an actual privacy committment, i spend a lot of time reading through reams of evasive and nebulous provider terms

Re: Openrouter Fusion API

#70

Post by crooked-v »

dsl wrote: post #16

Heh. I built "Fusion" a few months ago as an MCP using OpenRouter. The idea was to give Claude a "panel of experts" to go talk to when it got stuck. After extensive testing and benchmarking I discovered that when you ask one model to judge another's response you don't actually get a better answer. You are just asking it "how closely does this resemble the answer you would have given me." Additional rounds and all the…

[dead]
Post reply on HN