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

41–50 of 254 posts

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

#41

Post by seizethecheese »

codekansas wrote: post #19
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."

It's basically trying to replicate OpenRouter, which works pretty well and has a lot of nice features to abstract away any single provider, such as failover, metering, autoswitching, etc. It's actually a really smart infrastructure abstraction. I just wish this were solving an actual problem rather than being a fairly transparent attempt to say something approximating, "Hey VCs, OpenRouter just became a unicorn but I…

OpenRouter's model router for coding isn't really sophisticated. This is very different.

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

#42

Post by dbbk »

combyn8tor wrote: post #38
jacobgold wrote: post #33

> 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 have to use API billing) are chasing open weight models based on cost.

You may want to consider the incomes of developers outside the US, students, unemployed. $200/month is a lot to a lot of people.

They can still write code.

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

#43

Post by gruez »

combyn8tor wrote: post #38
jacobgold wrote: post #33

> 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 have to use API billing) are chasing open weight models based on cost.

You may want to consider the incomes of developers outside the US, students, unemployed. $200/month is a lot to a lot of people.

The point still stands. The chinese labs don't have super discounted plans, so if the price per task benchmarks[1] are correct, and we apply the discount, you'll actually be paying more by using cheaper chinese models and this technique.

https://artificialanalysis.ai/agents/coding-agents#artificia...

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

#44

Post by seizethecheese »

tj800x wrote: post #5

No single signin. Privacy policy allows training. No try it first without credit card. It's a good idea, but this looks premature.

If you want to try a similar idea that you can chat with immediately (free tier uses open weight models), I'm working on this: http://pellmell.ai

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

#46

Post by drnick1 »

recursivegirth wrote: post #40
jacobgold wrote: post #33

> 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 have to use API billing) are chasing open weight models based on cost.

[flagged]

> When they are successful at making those illegal/inaccessible

This would be like trying to outlaw Linux or peer-to-peer file sharing. It's technically possible to write and pass a law, but it's basically impossible to enforce it.

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

#47

Post by dimitrios1 »

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."

Unrelated - but reminds me of my favorite quote by tenderlove:

"microservices turn function calls into distributed computing problems"

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

#49

Post by switchbak »

drnick1 wrote: post #46
recursivegirth wrote: post #40

Earlier quoted context omitted.

[flagged]

> When they are successful at making those illegal/inaccessible This would be like trying to outlaw Linux or peer-to-peer file sharing. It's technically possible to write and pass a law, but it's basically impossible to enforce it.

Enough to make it a non-started at the organizations that pay their bills. Everyone else isn't big enough to matter.

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

#50

Post by hmokiguess »

seizethecheese wrote: post #25
Alifatisk wrote: post #8

This 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)

You might be interested in a project that I'm working on, which is kind of like OpenRouter Fusion, but instead of waiting for all models to synthesize, we stream the best model immediately and background the rest. The background models then reconcile with an emoji reaction and optional reply. It gets similar results to Fusion and is a lot faster! There's a free version that leverages open weight models here: http://p…

This is really cool, super fun!
Post reply on HN