Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models • Hacker News Board

Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

#91

Post by johnvanommen » Thu, Jul 23, 2026, 11:29 PM UTC

ignoramous wrote: post #63

dluan wrote: post #39

So this is the dogpile.com of the askjeeves, alta vista, and lycos approach? Time is a flat circle?

Mixture of Models , perhaps? tbf to OP, the setup they're proposing has also been recently evangelized by other "ai gateway" products (like OpenRouter, JusCode, Fireworks etc), so there's likely something useful here.

This sounds like networking.

Did OP invent an “intelligence router?”

Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

#92

Post by alightsoul » Thu, Jul 23, 2026, 11:33 PM UTC

There's so many people reimplementing Sakana fugu from its two ICLR papers but no open source version of it.

Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

#93

Post by nickthegreek » Thu, Jul 23, 2026, 11:45 PM UTC

killingtime74 wrote: post #90

cheema33 wrote: post #80

> Fable-level results at 1/3 the cost I am guessing this is not targeting those of us on the heavily subsidized $200/mo plans. Sure, these plans may be temporary, but none of us really know how temporary they are. Until then, 1/3rd of the published API pricing is not very appealing.

All enterprises users (people using them for work and not side projects) can't get the subsidized plans. I would say subsidized plans are a minority of usage?

The subsidized userbase is large enough that cheema is right to call this out this distinction for other readers.

Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

#94

Post by raver1975 » Thu, Jul 23, 2026, 11:50 PM UTC

I can't sign up: too many authentication attempts

Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

#95

Post by islambaraka » Thu, Jul 23, 2026, 11:51 PM UTC

What signals does Echo use to decide which models should participate before it has seen their outputs?

Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

#96

Post by qainsights » Thu, Jul 23, 2026, 11:52 PM UTC

Can't sign up: `too many authentication attempts`

Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

#97

Post by cantalopes » Fri, Jul 24, 2026, 12:11 AM UTC

By the way, is it just me or opus 4.8 is much better at some programming tasks than fable? I've been really disappointed lately, i stopped using it evem though it's "premium on my subscription"

Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

#98

Post by adam_rida » Fri, Jul 24, 2026, 12:13 AM UTC

raver1975 wrote: post #94

I can't sign up: too many authentication attempts

looking at it now

Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

#99

Post by adam_rida » Fri, Jul 24, 2026, 12:14 AM UTC

qainsights wrote: post #96

Can't sign up: `too many authentication attempts`

looking at it now

Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

#100

Post by meowface » Fri, Jul 24, 2026, 12:15 AM UTC

cantalopes wrote: post #97

By the way, is it just me or opus 4.8 is much better at some programming tasks than fable? I've been really disappointed lately, i stopped using it evem though it's "premium on my subscription"

It's just you. Fable 5 is consistently better than Opus 4.8 at literally every single level, for me. (I always use both at xhigh, for reference.) I could go down a laundry list of various issues I have with Opus that I don't have with Fable. For me, Opus 4.8 Plus Fable is way less annoying to talk to than Opus 4.8. Opus 4.8's writing style is absolutely insufferable. Fable has some of the same quirks but it's way less bad.