Project HydraFusion: Frontier quality via multi-model orchestration
1–10 of 36 posts
Re: Project HydraFusion: Frontier quality via multi-model orchestration
#2This has got to be the worst project name I've seen all year.
Re: Project HydraFusion: Frontier quality via multi-model orchestration
#3This has got to be the worst project name I've seen all year.
Why? I feel it kinda implies what the approach is. Could definitely be worse, strongly prefer this over just giving the thing a random-ass name like Laguna.
Re: Project HydraFusion: Frontier quality via multi-model orchestration
#4I have a custom agent that I call my "G.S.D." (Get Stuff Done) agent.
It is explicitly not a foreman, task routing, or an orchestrator agent. It has a bias toward direct action and is instructed to only delegate when necessary.
I've found that this approach yields significantly faster results, without much of a quality trade-off, than an agent whose primary impulse is to delegate.
In contrast, HydraFusion starts with a task routing step, then sequential planning, execution, and review stages. My guess is that this workflow is best for people who are prioritizing cost over speed for the same level of quality.
Re: Project HydraFusion: Frontier quality via multi-model orchestration
#5> One model drafts a result, an independent read-only critic from a different model family reviews it
Multiple model vendors is key here, the cascade pattern doesn't need it, but the critique pattern does.
Last Nov, my team wrote a paper ("Team of Rivals") on the difference between using an OpenAI model to Critique an Anthropic model's output vs running a self-review agent loop on the same vendor.
The ablations [1] proved that neither company alone was better than using both.
The paper was a general response to "What does your company do that Anthropic can't?" but more so a demonstration of how to make something 90%+ good with models which eval at 60% or so (& Gas Town post unblocked our "this is a trade secret" argument about the paper).
Re: Project HydraFusion: Frontier quality via multi-model orchestration
#6They should probably focus on “project hydrastable infrastructure” instead
Re: Project HydraFusion: Frontier quality via multi-model orchestration
#7This has got to be the worst project name I've seen all year.
I think the problem here is that we're running out of names. Which is ironic after calling everything copilot or office 365
Re: Project HydraFusion: Frontier quality via multi-model orchestration
#8From the article:
> In controlled offline evaluations, HydraFusion’s selective coding workflows matched or exceeded the evaluated Opus 5 baseline
Opus 5 (in practice) is not a good baseline to compare against.
I'm shocked that they chose to primarily compare against Opus 5 in all the article's charts. It's pretty disingenuous that they're claiming "frontier" quality, but didn't compare against Fable or Sol.
Re: Project HydraFusion: Frontier quality via multi-model orchestration
#9From the article: > In controlled offline evaluations, HydraFusion’s selective coding workflows matched or exceeded the evaluated Opus 5 baseline Opus 5 (in practice) is not a good baseline to compare against. I'm shocked that they chose to primarily compare against Opus 5 in all the article's charts. It's pretty disingenuous that they're claiming "frontier" quality, but didn't compare against Fable or Sol.
Well, saying it was a shitshow compared to … is just not good marketing i guess
Re: Project HydraFusion: Frontier quality via multi-model orchestration
#10From the article: > In controlled offline evaluations, HydraFusion’s selective coding workflows matched or exceeded the evaluated Opus 5 baseline Opus 5 (in practice) is not a good baseline to compare against. I'm shocked that they chose to primarily compare against Opus 5 in all the article's charts. It's pretty disingenuous that they're claiming "frontier" quality, but didn't compare against Fable or Sol.
They did also compare to Sol and the comparisons are still favorable. However, they were most favorable comparing to Opus 5 because of the cost judging by the charts.