Beating GPT-5.6 Sol on retrieval with 100x cheaper open models • Hacker News Board

Re: Beating GPT-5.6 Sol on retrieval with 100x cheaper open models

#131

Post by fennecfoxy » Fri, Aug 07, 2026, 2:31 PM UTC

podocarp wrote: post #87

sroussey wrote: post #46

Earlier quoted context omitted.

Product search model: https://www.linkedin.com/posts/introducing-ontology-1-ugcPos... Edit: more direct links, sorry: https://onton.com/research/ontology-1 https://onton.com/research/ontology-1-benchmarks

Sorry but what is neurosymbolic model, it's not explained I think

I would also like someone to clarify this for me. I (think) I understand what people mean by a neurosymbolic model however common definitions are a bit funky.

If it's neuro (llm/transformer similar) symbolic (symbolic with hand crafted rules) then, imo, that's no different from current tool calling harness implementations and I'd love for someone to explain it further to me if I've misunderstood.

If it's neuro (llm/transformer similar) symbolic (symbolic rules that have also been learned via training) then yeah I can understand how it's a distinct concept.

But every definition I've seen tells me that a standard harness of:

query->llm->[tool call symbol + tool name + tool params] aka symbols governed by logic, including param/arg validation->llm->etc

Already meets the requirements for being "neurosymbolic"...

Re: Beating GPT-5.6 Sol on retrieval with 100x cheaper open models

#132

Post by drob518 » Fri, Aug 07, 2026, 4:10 PM UTC

fennecfoxy wrote: post #129

drob518 wrote: post #106

Earlier quoted context omitted.

IMO, purpose built or “adapted” models are The Next Big Thing. If I’m using a model to write Python code, for instance, I really want the 8B or 27B expert model for exactly that, which would also be runnable locally. I don’t care about the 1.8T model that can answer every query under the sun and that only runs in a remote data center.

It is nice to have a model that can "do it all", though. And surely that's still the end goal? Like how MoE is still somewhat popular in certain areas even after its heyday. I am wondering if models will end up being some sort of evolution of MoE where it has something internally like the model the author refers to that gets surfaced when it needs to search in some way. I guess it makes sense; our own brains have so…

Yes, agreed, but I think it’s going to be difficult to have a high quality model that “does it all” and have it be local. For a quality “does it all” model, you’re going to need a lot of parameters and that means you’re almost always going to be running in the cloud. But it seems like you could probably get a smaller, focused model that runs locally and is also high quality. In other words, I want the programming expert portion of a 2T model that is maybe 35B or 70B parameters or whatever but it’s running locally (and yes, I know you don’t just carve out an expert from a larger model, but conceptually that’s what I’m after).

Re: Beating GPT-5.6 Sol on retrieval with 100x cheaper open models

#133

Post by fennecfoxy » Mon, Aug 10, 2026, 11:13 AM UTC

drob518 wrote: post #132

fennecfoxy wrote: post #129

Earlier quoted context omitted.

It is nice to have a model that can "do it all", though. And surely that's still the end goal? Like how MoE is still somewhat popular in certain areas even after its heyday. I am wondering if models will end up being some sort of evolution of MoE where it has something internally like the model the author refers to that gets surfaced when it needs to search in some way. I guess it makes sense; our own brains have so…

Yes, agreed, but I think it’s going to be difficult to have a high quality model that “does it all” and have it be local. For a quality “does it all” model, you’re going to need a lot of parameters and that means you’re almost always going to be running in the cloud. But it seems like you could probably get a smaller, focused model that runs locally and is also high quality. In other words, I want the programming exp…

Yeah, I always thought the future of this stuff would be hot-pluggable MoE modules or LORAs that are able to be downloaded and applied/used at will like how skills have become a thing.

Like, atm most architectures seem limited by a single context and fixed architecture with no hot loading. Especially for robotics, being able to load/unload various specialised skills on limited mobile hardware will (I hope) definitely become a thing.