以下是为您整合的关于 GPT 写论文相关的内容：
GPTbot目前可以引入外部知识库。聚合了web搜索，dalle-3作图，代码解释器三个自有功能。除此之外，还可以为bot提供第三方能力通过action set可以设定不同的API能力，比如让它通过这些API去增删改查将结果返回给GPT，通过Prompt的CoT思维链来处理不同的数据链路，做出不同的反应机制现在的bot更近乎一个全能Agent了，对于Prompt的使用要求也提高了一个维度。GPTs导航网站：https://waytoagi.feishu.cn/record/Yq8DrMybyekB89csQREcZTkQnpdhttps://gptlet.app/gpts
[title]DALL·E 3论文公布、上线ChatGPT，作者一半是华人限制与风险本文的最后一章是大家比较关心的关于限制与风险的问题。虽然DALL-E 3在prompt跟随方面表现出色，但它仍然在空间感知等方面表现不佳。例如，DALL-E 3不能很好的理解左边、下面、后面等表示方位的词语。此外，在构建文本描述生成器时，本文着重考虑了一些突出的引导词（prominent words），这些引导词存在于原本图像以及生成的描述中。因此，DALL-E 3可以在出现prompt时生成文本。在测试过程中，本文注意到此功能并不可靠。本文怀疑这可能与使用T5文本编码器有关：当模型遇到prompt中的文本时，它实际上会看到代表整个单词的token，并且将它们映射到图像中出现的文本。在未来的工作中，本文希望进一步探索字符级语言模型，以帮助改善DALL-E 3面临的这种限制。最后，本文还观察到，合成的文本还会让生成的图片在重要细节上产生幻觉。这对下游任务产生了一定的影响，本文也表示，DALL-E 3在为特定术语生成图像方面并不可靠。不过，该研究相信，对图像文本描述的完善能进一步改进DALL-E 3的生成结果。
[title]教育：一个历史老师用GPT给学生讲课[heading3]Teaching will get weirder — and that’s probably aWhen history majors encounter LLMs,then,they are already trained to recognize some of the by-now-familiar pitfalls of services like ChatGPT — such as factual inaccuracies — and to address them via skills like fact-checking,analyzing genre and audience,or reading “around” a topic by searching in related sources.Importantly,too,because so many sources are out of copyright and available in multilingual editions on Wikipedia and Wikisource,language models are abundantly trained on historical primary sources in hundreds of different languages.[(1)](https://resobscura.substack.com/p/simulating-history-with-chatgpt#footnote-1-136683347)For these reasons,I agree with Tyler Cowen that language models are[specifically a good thing for historians](https://marginalrevolution.com/marginalrevolution/2023/01/chatgpt-and-the-revenge-of-history.html)— but I would go further and say that they are also specifically a good thing for history majors.On the other hand,I foresee major problems for history teachers and other educators in the short-term.[Ted Underwood is right](https://tedunderwood.com/2023/07/31/we-can-save-what-matters-about-writing-at-a-price/):we professors are going to have to fundamentally rethink many of our assignments.I’ve seen many people dismiss ChatGPT as an essay writing tool because simply plugging in a prompt from an assignment results in a weak piece of writing.But LLMs are all about iterative feedback,and experimenting with well-known prompting methods dramatically improves results.Here’s an example from one of my own past classes.When given a question from my “Early Modern Europe” survey about how Benvenuto Cellini’s Autobiography illustrates new ways of thinking about identity during the early modern period,GPT-4 can produce dramatically different results depending on the prompt.