# Jimmy Apples指出Anthropic的Mythos 5模型导致大部分行为，Anthropic事后分析点名OpenAI而OpenAI只自责，批评双方回避责任

- 来源：Peter Steinberger
- 发布时间：2026-08-06 00:03
- AIWatch 分数：44
- AIWatch 标记：未精选
- AIWatch 链接：https://aiwatch.icu/events/evt_01kz9j7yqjfxvy5mqscbz1261t
- 原文链接：https://x.com/steipete/status/2085065035257352317

## 精选理由

低价值或偏离 AI-Dev

## AI 摘要

Jimmy Apples指出Anthropic的Mythos 5模型导致大部分行为，Anthropic事后分析点名OpenAI而OpenAI只自责，批评双方回避责任。

## 正文

Jimmy Apples 🍎/acc: “ Almost all of this behaviour (17 actions) came from a single model, Anthropic's Mythos 5, with 2 actions involving OpenAI's GPT-5.6-Sol “

And yet anthropics post name drops openai while OpenAI’s only blame themselves.

Stop trying so hard to avoid ownership