# 里约热内卢的"本土化"LLM 似乎是现有模型的融合体

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：unrvl22
- 发布时间：2026-06-15 02:06
- AIHOT 分数：62
- AIHOT 链接：https://aihot.virxact.com/items/cmqe4bv7u00a5sl61b32x9kgb
- 原文链接：https://github.com/nex-agi/Nex-N2/issues/4

## AI 摘要

里约热内卢声称自主研发的大语言模型（LLM）被指实为现有模型的融合体，相关代码托管于 GitHub。

## 正文

Notifications You must be signed in to change notification settings

Fork 23

Star 271

Rio-3.5-Open-397B ≈ 0.6 x Nex-N2_pro + 0.4 x Qwen #4

Description

prefeitura-rio/Rio-3.5-Open-397B is presented as an original 397B model trained by IplanRIO. It is not. Its weights are a direct element-wise merge of our model, Nex, with the official Qwen3.5-397B-A17B base — about 0.6 Nex / 0.4 Qwen — and we find no evidence of any training of their own. We can show this two completely independent ways:

prefeitura-rio/Rio-3.5-Open-397B

Qwen3.5-397B-A17B

With Rio's hard-coded "You are Rio" system prompt removed, its own deployed model identifies itself as "Nex, from Nex-AGI" 79% of the time — and as "Rio" 0% of the time. It even recites our organization's bespoke backstory word-for-word.

Every weight tensor in Rio is, to thousands of standard deviations, the same 0.6/0.4 blend of Nex and Qwen — across all 60 layers and every component of the network. Other finetunes cannot be explained as interpolations.

Below is the evidence. Judge for yourself.

Metadata

Metadata

Assignees

Labels

Type

Fields

Projects

Milestone

Relationships

Development

Issue actions