Echo

AI

model routing and ensembling

SHOW HN2026

484points
228comments
#55of 4,366 in 2026
Top 2%of 2026 by points

How HN took it

MixedNo clear lean

10 positive, 35 neutral or asking, 6 mixed, 47 critical, out of 98 comments about the project. Thread score -0.38.

Idea: 8 for, 14 againstDesign: 0 for, 10 againstPricing: 0 for, 7 againstExecution: 0 for, 4 againstDocs: 1 for, 2 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Model complementarity and ensembling idea is interesting

    From 2 comments
    • I think one of the most interesting takeaways is that model selection may matter more than model size. The industry has largely focused on building larger models, but your…
      smokeeaasd on HN
    • I 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…
      bnjemian on HN

Objections

  • Claimed cost savings are unclear versus subscriptions and caching

    From 3 comments
    • > Fable-level results at 1/3 the cost using open-weight models But we get ~$2500/mo worth of Fable credits for $200/mo on Anthropic pan? I'm still confused why people (who don't…
      jacobgold on HN
    • This does not really work well, if you don't know the complexity of the problem ahead of time and ensure all future conversations go to the same model. Else, you break the cache…
      subygan on HN
    • but u wouldnt get caching savings
      purplecats on HN
  • Sign-up flow and login issues

    From 3 comments
    • Can't sign up: `too many authentication attempts`
      qainsights on HN
    • No 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…
      kamranjon on HN
    • No single signin. Privacy policy allows training. No try it first without credit card. It's a good idea, but this looks premature.
      tj800x on HN
  • Ensembling is not new

    From 3 comments
    • I 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…
      bnjemian on HN
    • enjoying how people are re-discovering ensemble methods.
      fgoose180 on HN
    • The "ensemble of models" is nothing new. It's just that it's not really a moat that can be monetized. In the end you're always paying for something. You can engineer an elaborate…
      Art9681 on HN
  • Benchmarks thin or hard to verify

    From 2 comments
    • No 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…
      kamranjon on HN
    • I’m very confused on what this is, my initial thought was “oh nice, open source router.” I go to the website…and it’s a sign up. I expected a repo. Otherwise how do I use it? As…
      ninjahawk1 on HN

Requests

  • Benchmarks for coding and agentic tasks

    From 1 comment
    • thanks to everyone for taking the time to try Echo and share feedback, this is precisely why i wanted to launch early. i am going to try to address a couple of topics that came…
      adam_rida on HN
  • Clearer eval page with more graphs

    From 1 comment
    • Hi this is very cool. As a student (read: more dumb than adults), I find the eval page too loaded with words. Maybe more graphs could help?
      sudo_cowsay on HN

Questions

  • How does this differ from OpenRouter Fusion

    From 3 comments
    • how does this differs from OpenRouter fusion?
      wizche on HN
    • How is this different from what that feature OpenRouter does?
      thatxliner on HN
    • Seems similar to Openrouter Fusion - https://openrouter.ai/docs/guides/routing/routers/fusion-router
      meander_water on HN
  • What signals decide which models participate

    From 1 comment
    • What signals does Echo use to decide which models should participate before it has seen their outputs?
      islambaraka on HN

Alternatives named

  • OpenRouter Fusion

    From 2 comments
    • Seems similar to Openrouter Fusion - https://openrouter.ai/docs/guides/routing/routers/fusion-router
      meander_water on HN
    • how does this differs from OpenRouter fusion?
      wizche on HN
  • Sakana Fugu

    From 2 comments
    • There's so many people reimplementing Sakana fugu from its two ICLR papers but no open source version of it.
      alightsoul on HN
    • Is this yet another Sakana Fugu / OpenRouter Fusion?
      ototot on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/49026810)