Is this yet another Sakana Fugu / OpenRouter Fusion?
Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
21–30 of 254 posts
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#22I'm not an expert on this, but this sounds a lot like a larger-scale MoE (Mixture of Experts) type of architecture.
As I understand it, in an MoE model, you essentially have hundreds of smaller sub-models ("experts") that are good at different tasks, and for every generated token, a single "master" model chooses which ones are most relevant to participate, and you only activate them.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#23I'm not an expert on this, but this sounds a lot like a larger-scale MoE (Mixture of Experts) type of architecture. As I understand it, in an MoE model, you essentially have hundreds of smaller sub-models ("experts") that are good at different tasks, and for every generated token, a single "master" model chooses which ones are most relevant to participate, and you only activate them.
In MoE systems the routing decision is made per-token, not per prompt or task. It’s one of ML’s many confusing naming conventions.
Even more confusingly, there are older pre-LLM MoE systems which ensemble and pool the predictions from multiple sub-components. For example in a random forest you could take the majority vote of the decision trees or the average of their numerical predictions.
After that, we developed neural net architectures for predicting a single thing like whether the user will click on your ad. An MMoE is in the same family.
And so now we are at massive MoE networks for LLMs which have similarities with MMoE in that the “decision” is about the very next token to predict.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#24I don’t find the recent spate of blog posts and systems delegating and combining LLMs to get better performance particularly interesting. Especially given that anyone who’s taken an ML 101 course has learned about ensemble methods. While an LLM isn’t what you’d traditionally consider a weak learner, the theorems on learning systems clearly point to them being so in this context. The feigned surprise at combining them…
The entirety of "agents" and tool calls is a process of combining LLMs to get better results. Is it the same LLM in many cases? Yes. But it doesn't have to be.
It's the natural move that happened after people realized you couldn't throw away half a century of AI research.
Most of these focus on costs. But it is simply the case that the one-shot output did not scale for harder problems on workflows.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#25This reminds me on OpenRouters report that combining multiple different models gave comparable performance to Fable 5. I think this approach has lots of potential. Maybe OpenAi was ahead of its time with GPT-5 (it being a router to different models rather than just being one new model)
You might be interested in a project that I'm working on, which is kind of like OpenRouter Fusion, but instead of waiting for all models to synthesize, we stream the best model immediately and background the rest. The background models then reconcile with an emoji reaction and optional reply. It gets similar results to Fusion and is a lot faster! There's a free version that leverages open weight models here: http://pellmell.ai.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#26No benchmarks, no info on which models are used, ai generated video, just a signup page with nothing else. Anyhow, this kinda reminds me of that quote about architecture: "We replaced our monolith with micro services so that every outage could be more like a murder mystery."
> No benchmarks, no info on which models are used, […] The benchmarks are here → https://echo.tracerml.ai/eval/ They are not good benchmarks but at least they exist.
I've been working on a similar project and I found that it's easy to replicate Fable results if you use saturated benchmarks.
In my project, I wasted a huge amount of time trying to improve GPQA Diamond results above ~93% range. I realized my mistake when Fable dropped and made no improvement on this benchmark vs. Opus.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#27M-o-MoE
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#28Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#29such a scam, there is only one fable-like model, that somewhat behind, it cost half, not 3x. so from here you can stop reading.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#30Intuitively, your savings depend heavily on how hard the tasks are in the first place. If you have a base rate where 99% of your tasks can be routed to a cheap model, yeah, you can save a ton by not using Fable for that.
So “1/3 the cost” really depends.