91–98 of 98 posts
I ran a quick eval to see what this looks like qualitatively vs just calling Opus 4.7 or GPT 5.5 directly. As expected, Fusion was 7x slower and 4x the cost. This isn't a knock against it, just that it I think this places Fusion into a "use it only when you need it" category. https://3fpi5avcqq.evvl.io/
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’ll have codex write a detailed prd.md file of how my project works, logic, goals, tech stack etc
Then I’ll use openrouter to have multiple models analyze that file, and write me a new improvements.md file
Then I’ll have codex check all those improvements md files and implement what it thinks are the best things that were missing
It’s quick, not expensive, and usually finds things I would have never thought of on my own
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…
My daily driver is Codex I’ll have codex write a detailed prd.md file of how my project works, logic, goals, tech stack etc Then I’ll use openrouter to have multiple models analyze that file, and write me a new improvements.md file Then I’ll have codex check all those improvements md files and implement what it thinks are the best things that were missing It’s quick, not expensive, and usually finds things I would ha…
Earlier quoted context omitted.
My daily driver is Codex I’ll have codex write a detailed prd.md file of how my project works, logic, goals, tech stack etc Then I’ll use openrouter to have multiple models analyze that file, and write me a new improvements.md file Then I’ll have codex check all those improvements md files and implement what it thinks are the best things that were missing It’s quick, not expensive, and usually finds things I would ha…
What tool are you using openrouter with? Codex?
It should be called something else, maybe Ensemble? It doesn't fuse anything.
Ensemble or 'mixture of experts' (before MoE model architecture was a thing).
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…
A panel of models can debate for 5 minutes. The harder problem is making an agent remember why a decision was made 5 weeks ago.