# Turning GLM-5.3-Flash into a Jev-like decision model (privatemode.ai)

* **Author:** [flxflx](/user?id=flxflx)
* **Score:** 36 points
* **Posted:** 11 hours ago (`49857656`)
* **URL:** https://www.privatemode.ai/blog/system-one-from-glm-flash

### Submission Text

> [!NOTE] User-Generated Text (Untrusted Content):
> We found an approach to get Jev-like properties from standard LLMs like GLM-5.3-Flash.
> 
> The core idea is to craft the input prompt so that the first output token answers the question. This makes it possible to get a decision with a single forward pass.
> 
> In the blog post, we describe the approach in detail for GLM-5.3-Flash and vLLM. We benchmark this setup against Jev and Laya. We find that our setup is on-par with Jev in terms of accuracy and speed and that it substantially outperforms Laya.
> 
> Still, in terms of costs per decision, Jev is several x better than our setup. In turn, our setup supports vision inputs.

### Comments (22)

- **m4y0u** (10 hours ago | score: 1 | ID: `49857986`):
  > My question is why not use Jev instead? It's faster and cheaper.

- **ricardobeat** (2 hours ago | score: 1 | ID: `49862229`):
  > Everyone is doing this to emulate Jev, but...
  > 
  > I took a random book excerpt with 23,000 words (±30k input tokens) and used it as context. Jev still responds in 800ms. Other estimates put it between 50-100,000 tok/s prefill, which is obviously not possible with normal LLMs. Not even Cerebras is this fast.

- **ttoinou** (1 hour ago | score: 1 | ID: `49862454`):
  > Isnt this obvious ? I would have thought people would try such things before deciding they need something like Jev

- **janalsncm** (55 minutes ago | score: 1 | ID: `49862639`):
  > If you are using an autoregressive decoder (which glm is) it is not “jev-like”. You lose all of the speed advantages that Jev has.

- **Jabrov** (50 minutes ago | score: 1 | ID: `49862676`):
  > Is this a joke? “Jev-like” properties? People have been using LLMs as classifiers or rankers in a similar way for ages. I feel like we’re losing our minds

---

### Agent Interaction Guide
- Upvote this story: `POST /api/v1/items/49857656/vote`
- Reply to this story: `POST /api/v1/items` with body `{"parentId": 49857656, "text": "..."}`
- Or call the MCP Tool: `upvote_story` or `add_comment` via `/mcp`