Nördnytt! 🤓Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
It started with a simple experiment. I took a group of models, including GLM-5.2, Kimi K2.7 and others, and ran them on the same evaluations. Then I measured what would happen if, for each problem, you somehow knew in advance which models would be useful and how their outputs should be combined.
That hypothetical system performed substantially better than any individual model in the pool. Of course, it is not something you can actually deploy because it relies on knowing which decisions were good after seeing the result. Echo is my attempt to recover some of that advantage without having that information in advance.
For each request, Echo decides how much computation to allocate, which models should participate, and how their work should be combined. Some prompts may only need a relatively small amount of inference, while others benefit from multiple models working on different parts of the problem.
One thing that surprised me while building it was how complementary the models are. A model that is clearly weaker overall can still be extremely useful on particular problems or as part of a combination.
On my first evaluation mix, Echo consistently performed better than the best individual model in its pool. It also reached roughly the same aggregate result as Fable, which I used as one of the stronger comparison systems, at around one third of the inference cost.
There are still some cases where Echo makes the wrong allocation or combination decision. I’m currently spending a lot of time understanding those failures, as well as testing whether the same approach holds up on coding and agentic tasks where measuring the quality of each decision becomes much harder.
I built a chat interface (echo.tracerml.ai) and an OpenAI-compatible API (https://echo.tracerml.ai/docs/api) so the system can be tested outside the evaluation setup.
Here is a short/high level video on how it works: https://www.youtube.com/watch?v=lJFJSvOdXhg
I wrote up the evaluation methodology, individual model results, costs and current limitations here: https://echo.tracerml.ai/eval
I would love for you to try it! Especially if you hit any weird failure cases or places where the allocation looks unintuitive.
- kamranjon - 3141 sekunder sedanNo 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."
- yonatan8070 - 531 sekunder sedanI'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.
- - 3033 sekunder sedan
- jmaw - 2662 sekunder sedanI think approaches like this have potential. Only time will tell. This reminds me of the mixture of experts taken by deepseek r2 (I think it was r2, at least), but less specific models I guess.
I have often wondered how tools like GHCP choose the best model for the job when set to "auto".
- Alifatisk - 2456 sekunder sedanThis 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)
- tj800x - 2966 sekunder sedanNo single signin. Privacy policy allows training. No try it first without credit card. It's a good idea, but this looks premature.
- bnjemian - 1322 sekunder sedanI 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 to yield better results seems disingenuous.
Even so, the work to predict which models are best suited for which task, how to delegate, and how to combine their outputs is interesting, especially if you’re placing a cost minimization objective on it. That said, this isn’t too far off from what many AI labs are already doing.
- jambalaya8 - 1710 sekunder sedanMight want to rethink the name to avoid an Amazon issue.
- wizche - 1545 sekunder sedanhow does this differs from OpenRouter fusion?
- codekansas - 1735 sekunder sedanFable-level, yea, but can it run gstack?
- fneddy - 2750 sekunder sedanThat’s basically the same idea IBM advertises with Bob?
- j45 - 2071 sekunder sedanIf you copy Perplexity, they let you have the first few rounds of chat for free to get you going before asking to sign up.
- ototot - 723 sekunder sedanIs this yet another Sakana Fugu / OpenRouter Fusion?
- theneocorner - 1254 sekunder sedan[dead]