Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

news.ycombinator.com

Post reply on HN
Print view View original

141–150 of 254 posts

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

#141

Post by aroman »

byzantinegene wrote: post #130
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.

I believe they will last until they IPO, and not long after that. $200/mo plans are not good for their P&L when their users using $10000 worth api credits. That's -98% margin loss per user.

I simply do not believe the switching costs are high enough that they could eliminate those plans. The Chinese models will eat their lunch.

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

#142

Post by user_7832 »

adam_rida wrote: post #114

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 up often: - i'll keep publishing stronger evals, including more difficult coding and agentic benchmarks, to map out more precisely the differences with sota - the public eval dashboard will keep expanding and be updated (very open to more benc…

Small feedback: the "create password" requires a symbol too, which Google's password manager by default does not use. I'm fairly sure a double-digit-level alphanumeric jumble is sufficient to be a password (or at least, Google thinks so). Great idea nonetheless!

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

#143

Post by somenameforme »

byzantinegene wrote: post #130
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.

I believe they will last until they IPO, and not long after that. $200/mo plans are not good for their P&L when their users using $10000 worth api credits. That's -98% margin loss per user.

Open weight models are catching up, and I see no reason to think this will change. That will largely define the economics of this industry. It seems highly improbable that there will be people spending thousands on API credits will be a thing in the future.

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

#144

Post by rablackburn »

user_7832 wrote: post #140
Terretta wrote: post #87

Earlier quoted context omitted.

> Dogpile was only a good idea while Search Engines were mostly trash. Precisely.

LLMs fail in such bizzare, obscure methods (to the average observer) at times. Sometimes even simple questions ("who was that x person who was super famous I'm thinking of") type questions fail terribly. The more vague and non committal and hand-wavey and subjective the field for AI to answer, the better the results (imo).

I daresay it's because the assistant training corpus is heavily biased towards one-shot solution answers.

Because the correct response to that query is "I have no idea -- you will need to provide more information"

and LLM Agents suck at that.

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

#145

Post by ignoramous »

ljlolel wrote: post #108
dluan wrote: post #39

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

ensemble models always did the best at Kaggle we did the same: https://trustedrouter.com/blog/prometheus-2-new-draco-state-...

You need update your blog posts.

  Our whole stack is radically open source — frontend and backend alike, Apache-2.0 licensed — and so is everything behind this benchmark. That is how a benchmark number earns trust: verifiability, not hype.
The repos have since been moved to BUSL-1.1: https://github.com/Lore-Hex/quill-router/commit/8155ac666ae0...

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

#146

Post by joe_the_user »

onlyrealcuzzo wrote: post #82
glasss wrote: post #56

Earlier quoted context omitted.

Good ideas are usually still good across time and tools

Dogpile was only a good idea while Search Engines were mostly trash. You needed to search all of them to find something decent. That's roughly analogous to today. Ignoring cost, you'd be way better off asking all the LLMs to solve a problem (like coding) where you can verify the answer. So the question is, for things like that -> can a group of models perform better than frontier models, especially at a reasonable co…

Dogpile was only a good idea while Search Engines were mostly trash.

Well, search engines are trash again. Perhaps it should come back

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

#147

Post by neonstatic »

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.

> Sure, these plans may be temporary, but none of us really know how temporary they are.

Anthropic emailed me today:

  Fable 5 moved to usage credits on July 20. It is still available to you, but it requires pay-as-you-go usage credits and is not included in your subscription rate limits.

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

#148

Post by XCSme »

kamranjon wrote: post #2

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 replaced our monolith with micro services so that every outage could be more like a murder mystery."

I thought login-protected apps are not allowed on Show HN.

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

#149

Post by XCSme »

springtimesun wrote: post #124

I have been trying something like this with local only models. I think I’ve tried everything that will fit in 96GB alone and in concert with each other using real project data (Rails). I haven’t found much benefit to anything other than Qwen 3.6 27b dense feeding a Claude final pass. I really thought layering was going to work like the law of large numbers, but for my workload it just hasn’t.

I have a spare 3090 that I want to use to off-load some tasks from Claude to a local model (probably Qwen 3.6 27b), any success with that? Is it good enough to follow some tasks, coding requirements or browser usage?

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

#150

Post by jambalaya8 »

stilesja wrote: post #121
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.

I burned though my weekly fable usage last night on the $200 plan. I had $200 in promotional usage credits and was in the middle of executing a moderate sized coding plan. Ran on usage credits for about 1h 15m and burned $120 in usage credits. I was astounded to see how fast the $ usage added up. One problem was that I was using sub-agent execution so multiple agents were running simultaneously and I realized at the…

I am too young (most of us on here are) to have lived through the paying for time on time-share machines in the 60s/70s, but this is giving me creepy memories of paying for sprintnet/telenet and tymnet... And I guess aol, compuserv, delphi. Are we really doing this computing model again?
Post reply on HN