A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost | Hacker News Reader

A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost

hightouch.com

116 pointstheanomaly35 comments

If you use Qwen3.8 27B to manage, to orchestrate, do do shallow research, and then make it ask claude you will notice that Qwen can get out of Haiku, Sonnet and Opus almost as good answers... I was researching how good the model asnswers where, I can't get to work with anything but Fable, but Qwen can get good work from any of them. My theory is that if you make Qwen understand you, Qwen can elaborate as much as needed to get any of those models get good results, because it's filling in details. So using Qwen to direct claude also get's you amazing results way way cheaper...

Update: let me elaborate more, I read the HN entry about the team of 5 Qwens being close to fable quality... so I embarked to add to my harness (https://github.com/alainnothere/privibe because we all have one right?) and once I had added the orchestrate tool I had to now measure somehow it it's able to improve quality, so I claude and then Qwen to run a experiment to call my harness passing the model to use and ask them to do something, 3 rounds I think and see what quality came out of it... and as per the grading... qwen and claude agreed that the quality of the response comming out the harness using the orchestrate was VERY CLOSE, with opus and fable providing more "in my opinion you should" which matches my experience on why they are better.

One more update: I can't get copilot models to work decently, it may be my way of working... but I can get Qwen to follow what I try to do... if Qwen get's me he can then fire copilot cli and get amazing results by using copilot... bonus points seems like copilot cli is cheaper with the AIC (cost of the requests) so you can make the copilot subscription longer

> My theory is that if you make Qwen understand you, Qwen can elaborate as much as needed to get any of those models get good results, because it's filling in details.

How is this different than just telling the model you’re using to fill in the gaps itself?

If you’re not manually reviewing the intermediate hop, how does that add to the “understanding you”?

there is no difference... each case may be different, I have a local qwen gpu setup... and is fast... but not as fast as claude. Fable is amazing and if it cost the same as my qwen setup I'll be running fable and never had qwen in first place. But Fable is crazy expensive, Qwen is not as fast but cheaper... Haiku is fucking dumb IN MY HANDS... BUT my local qwen is quick enough to be briefed, get the idea and delegate. I work with Fable mostly delegating to opus/sonnet and it's cheaper than just fable, I can't stand working with opus or the other models.

Why Qwen directing the others? For the things claude refuse, Qwen can make very specific questions and still get an answer without triggering the thing.

I do the opposite of this, use Qwen3.8-27B as subagents, Opus 5.5 as orchestrator and planner, never implementer, and it cuts my token usage significantly. So it is using Claude to direct Qwen. Never thought of the other way around, will give this a try soon as possible.

What do you use to get Opus to call Qwen?

You can have a setup like this with OpenCode agents, where you can define custom top-level agents, subagents, and assign specific models to each.

https://opencode.ai/docs/agents/

There are a lot of ways to do this if you stop using Big Ai harnesses that make it difficult to use models besides theirs.

Install the llm cli and tell opus to use it to prompt qwen.

Custom MCP with a variety of functions, I have different Qwen profiles with a variety of subagent numbers and cache pools, my default is 192k pool with 64k initial context that can grow 32k at a time up to 128k, allowing 3x64k, 2x96k or 1x128k and 1x64k subagents. Qwen uses Pi harness. Model I use specifically is ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF

ohmypi will spawn subagents across different providers out of the box. Opus will spawn subagents running on my local ds4 installation just fine

Anthropic has a native solution to this which is that you can use `/advisor` to adjust config to enable using Sonnet but set Opus as an advisor or use Haiku and then set Sonnet or Opus as advisor that the weaker model will automatically call when it thinks something warrants it:

https://code.claude.com/docs/en/advisor

It allegedly will automatically judge when to call the stronger model, not sure how much instructions in prompts or AGENTS.md can steer it.

Excellent read. I use the same hybrid approach for a lot of security engineering work and it’s working well after initial calibrations, for example for our own harness we rebuilt auto mode exactly like this to judge tool calls and intent.

I had the same idea, I extended opencode-warden to use a local decision model to validate tool inputs and outputs. It seems to work... ok? d1 is fast enough to run locally on an old 1080 GTX. Not sure if I can recommend relying on it.

This sort of stuff has me believing that decision model controlled/prioritized context is the future of context management beyond the raw AGENTS.md file.

Why give all the context to an agent, when the context can also be curated, updated and made concise automatically for each new problem.

Yes × 1000... Jev is the classic type of scientific discovery, any human can see it's effectiveness without actually trying it. We were only deprived the discovery because of the incredible noises created by the AGI/ASI ferver....

We've been doing this for a while. Fine tuning the decision model helps a lot too. The problem is you still need a pretty low confidence threshold (e.g 10%), but often times that reduces the work by 70% with 0% quality loss (in our benchmarks)

Ideally, "system one" intelligence is good both at quick reactions and at knowing when to hold off and wait for "system two." Sure enough, that works with Jev.

I don't usually get excited about the high-level, "whoooa man" marketing-speak, but the parallel is striking.

Been doing this on Discourse for Spam and locale detection, mostly doing d3-turbo with Qwen 3.8 Flash Next Help.

> We tested whether fast, cheap decision models like Jev and GPT-6 Luna

GPT-6 Luna is a small LLM, not a decision model :P

No but it's the only OpenAI model with a decisions API https://developers.openai.com/api/docs/guides/decisions

There's actually a decision model version of GPT-6 Luna... You are right to be confused though. OpenAI and their never ending naming games. https://openrouter.ai/openai/gpt-6-luna-decisions

Small LLM + no reasoning + fixed JSON-only output = decision model

I wonder if something like this is the undisclosed new approach from Anthropic that presumably has massive improvements by combining multiple models. Leveraging decision models as much as possible seems logical for extra speed and token efficiency.

they do have the 'advisor' model setting now which also plays well with this

> undisclosed new approach from Anthropic

Any source on that?

I think OpenAI and Anthropic have both been doing similar "routing" approaches for a while. Wasn't OpenAI one of the first to have a small model start responding to you for the first several tokens so that you got an instant response while the big model became available?

Similarly, Grok has been routing to Opus internally for a little while now I think.

4x lower is so mathematically awkward.

So like, -3x?

More like 0.25x.

Liked the read. I wish there were some code examples for how jev/Luna were actually done as I try wrapping my head around their new paradigm.

i'm so numb to these headlines nowadays... i guess i've been disappointed by how effective these approaches end up being for actual work but i feel like it's easy to produce these headlines with "proof" that doesnt prove anything besides the sandboxed scenario it was run in

[delayed]

What about Sonnet? Haiku? Does it need Opus specifically?

Seems to me that the important factor is that Jev has well-calibrated confidence for this task. Which secondary expensive model it defers to is probably less critical in this technique as long as that model has higher performance than Jev.

Yeah exactly - very interesting that Luna is calibrated so poorly despite working better on easier problems.

Funny they called it Jev, as if the w was too expensive.

Reply on news.ycombinator.com