Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- So the word security or any topic related to it is mentioned and it flips to an older gen model? Fable is nearly useless now it you do anything around auth.by jmspring
- I can get it to write win32 unsafe rust code.
I can't get it to review win32 unsafe rust code.
Make it make sense.
by dijit - The business use case of rather than going on one model choosing the best openweight model and reducing the cost seems fascinating, however the context memory, or auditability of what is happening behind would be more complicated, even within single model we have to spend tons of time to decode and understand llm behavior , add context layers and so on, having said that for GenAI executions this might be the direction. Wish you best for the project
- 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 different areas and become much more valuable when combined with others. I'm curious to see whether this still holds for coding and agentic tasks, where choosing the right models is likely much more challenging.
by smokeeaasd - 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!
by adam_rida - Seems similar to Openrouter Fusion - https://openrouter.ai/docs/guides/routing/routers/fusion-rou...
- Fusion is a totally different approach, though similar in the sense that it leverages different models.
Fusion generates many replies then synthesizes. This adds a ton of latency and cost, so it's going to be better only for cases where you're willing to wait a lot and pay a lot more.
Routers (like this project) are a different thing, they can theoretically improve performance and cost at the same time without increasing latency much. I'm a bit skeptical though, since knowing which LLM is going to be better on a cost adjusted basis is hard (see https://artificialanalysis.ai/models/capabilities/coding?cos..., where the cost per task vs. performance is not what you expect, for example comparing Qwen 3.7 Max to GPT Sol.
A project I'm working on is aimed at improving performance without added latency but from a different angle. Instead of waiting for all replies for synthesis (like OpenRouter Fusion), it streams the "best" reply immediately (using a router to pick the best model) then synthesizes with emoji reactions and optional replies from the background models. It's free to use here with no login: http://pellmell.ai
- Replace "Show HN:" with "Advertisement:" ?by slashdave
- 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 by doing a round robin of the same conversation across different models. Likely you'll end up paying more than what it would've cost with a cache aware system
by subygan - Cache hits should be part of the strategy.by hahahaa
- You can use the Ralph Wiggum technique: https://ghuntley.com/ralph/by lbriner
- So this is the dogpile.com of the askjeeves, alta vista, and lycos approach? Time is a flat circle?by dluan
- timecube?by cdelsolar
- metacrawler.comby moralestapia
- Indeed. What a deep cutby alizaki
- Well, you can try to make triangular wheels, but they are round for a reasonby gchamonlive
- This is the don't use the same EC2 size for everything on your service approach.by hahahaa
- 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.by ignoramous
- ensemble models always did the best at Kaggle
we did the same: https://trustedrouter.com/blog/prometheus-2-new-draco-state-...
by ljlolel - Good ideas are usually still good across time and toolsby glasss
- 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."
by kamranjon - I thought login-protected apps are not allowed on Show HN.by XCSme
- It's easy enough to copy and paste in a prompt, no?
Eval tests while giving general indicators might not be similar for each use case.
by j45 - Unrelated - but reminds me of my favorite quote by tenderlove:
"microservices turn function calls into distributed computing problems"
by dimitrios1 - 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 can basically vibe code it"
Calling it "Fable-level" feels intellectually lazy / dishonest, but then again, what do you expect when there's so much money on the table.
by codekansas - > No benchmarks, no info on which models are used, […]
The benchmarks are here → https://echo.tracerml.ai/eval/
They are not good benchmarks but at least they exist.
by guessmyname - The evaluator is public here: https://echo.tracerml.ai/eval/
It currently exposes 907 stored rows across seven benchmark families, with prompts, outputs, grades, and cost records. More benchmarks are coming soon.
Echo does not disclose its per-request routing decision because that policy is the product. We can, however, publish some of the eligible open-weight model pool, version dates, aggregate allocation mix, and evaluation settings without exposing the request-level recipe.
New video is also being made.
by adam_rida - No single signin. Privacy policy allows training. No try it first without credit card. It's a good idea, but this looks premature.by tj800x
- That would open him up to lots of abuseby DatCodeMania
- I assume trying without a credit card will bankrupt him immediately.