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

231–240 of 254 posts

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

#231

Post by adam_rida »

smokeeaasd wrote: post #229

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 results suggest that intelligently routing requests to the right combination of specialized models can deliver greater gains at a much lower cost. It also reinforces the idea that weaker models are not necessarily obsolete. They may simply excel in…

exactly, if you ensemble heavily small uncorrelated models (while each being expert on its task) you can get really interesting resutls.

on agentic and coding what's make the problem even deeper is the granularity. how and when to use each model and at which layer of abstraction (session, goal, task, turn/tool calling). this is also something we are working on actively!

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

#232

Post by jambalaya8 »

cube00 wrote: post #194
stkdump wrote: post #189

Earlier quoted context omitted.

I think you were able to buy VS Pro perpetual licenses for one time 500-1000 at all times. Of course they had higher tiers and a subscription model which were more expensive but in reality for most people there was little to no added value.

>subscription model which were more expensive but in reality for most people there was little to no added value The value was the multiple CDs of MSDN documentation and code samples which where very handy considering the slim pickings on the internet in 1995. These weren't included with an IDE perpetual license retail box.

yeah. those msdn cd's were very valuable back then. it was before the market was flooded with tech books also. aside from Russinovich's stuff, you basically needed that cd set to do any hardcore windows coding up til probably 15ish years ago.

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

#233

Post by adam_rida »

rufasterisco wrote: post #224
adam_rida wrote: post #223

Earlier quoted context omitted.

removing it now

Thanks. Since you are fixing dark patterns, can you also put data privacy links somewhere other than on the gdpr banner? Once clicked is impossible to see them, or at least I could not find them.

good catch, on it too now!

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

#234

Post by adam_rida »

user_7832 wrote: post #142
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!

thanks! adjusting it now

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

#235

Post by schwetim »

kamranjon wrote: post #213
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…

You keep saying open weights - but you aren't sharing any information on which models you are using. What benefit does using open weights models provide to the end user if there is zero transparency?

I guess it’s their IP

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

#237

Post by recursivegirth »

dang wrote: post #139
recursivegirth wrote: post #40

Earlier quoted context omitted.

[flagged]

> The good ole American way. Could you please stop posting unsubstantive comments and flamebait? You've unfortunately been doing it repeatedly. It's not what this site is for, and destroys what it is for. If you wouldn't mind reviewing https://news.ycombinator.com/newsguidelines.html and taking the intended spirit of the site more to heart, we'd be grateful.

> unsubstantive

LOL, seems your only issue is when someone goes against you politically. You allow so much anti-American propaganda on this site, and me calling out capitalistic tendencies is where you want to draw the line?

Do you not think that YC culture, startup culture, is not intertwined with the economy? I could stop, but is that the type of community you want to cultivate?

My contact information is in my bio if you want to seriously talk about this topic, I would be more than happy to get on a call with you. I feel you are being more than disingenuous with your application of the "rules".

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

#239

Post by adam_rida »

blobbers wrote: post #128
adam_rida wrote: post #122

Earlier quoted context omitted.

there are and this what you optimize for. ensemble learning has a long literature on this. you want models that have the most diverse pool of capabilities so they complement each other. in verifiable tasks or classification this is straightfroward but a bit tricker in open ended text gen or CoT. this is one of our core research question

My experience is mostly around either ensembles of weak learners that are bootstrapped to create a strong learner, or around boosted learners where you're training on residuals. With CoT you're sort of adding entropy to your answer, but you're also possibly getting a more thorough answer? I'm curious though if these training methods are convergent or are models actually different; just like how in the stock market pe…

i think that’s exactly the core of the question. There is meaningful decorrelation across models in some domains, like language for instance. but i agree that it’s much less obvious for reasoning.

I don’t think more models is necessarily better, and one of our research questions is also: when does adding another reasoning path actually add useful information, and when is a single strong path better than an ensemble?

Post reply on HN