这个做法，不禁让特工想到当年它的名字还叫 Q*，而 Star 的来由正是 StaR 系列的论文。其中这篇《Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking》的方法与 OpenAI 在 o1 中的做法有很多相似之处，感兴趣的小伙伴可以阅读这篇以及这个系列的文章。（想在其它博主那里看到又干货又及时的整理可不容易哦，只此一家）
Life can only be understood backward, but it must be lived forward - Søren Kierkegaard(Quiet-STaR 在论文的 Abstract 引用了这句话，当时觉得挺有意境的)
官方演示视频OpenAI 直接怒发十几条演示视频，我和我的小伙伴都惊呆了。并顺手将他们保存到了云文档：https://agentuniverse.feishu.cn/wiki/E7IIwVABoiKS7LkExDfc8tGInqh（部分机翻可能存在一些错误，时间匆忙敬请谅解）。1. 数 strawberry 中 r 个数。 2. 制作在 HTML 上可以玩的贪吃蛇小游戏。 3. 将存在错误不通顺的韩语，正确翻译为了英文。 4. 破解逻辑谜题。5. 做数学题。
According to these evaluations, o1-preview hallucinates less frequently than GPT-4o, and o1-mini hallucinates less frequently than GPT-4o-mini. However, we have received anecdotal feedback that o1-preview and o1-mini tend to hallucinate more than GPT-4o and GPT-4o-mini. More work is needed to understand hallucinations holistically, particularly in domains not covered by our evaluations (e.g., chemistry). Additionally, red teamers have noted that o1-preview is more convincing in certain domains than GPT-4o given that it generates more detailed answers. This potentially increases the risk of people trusting and relying more on hallucinated generation.
