I have seen when using ChatGPT, it use’s the “em dash” (—) quite frequently. Is it a quirk from the training data? I just noticed it often and wanted to see if any one else has seen this characteristic. Also it is a way to easily find if a text is AI-generated or not, that’s at least something I use 🙂 Looking forward to your insights and perspectives!| OpenAI Developer Community
Been trying to get it to stop for months but it’s only been a colossal waste of time. I get going on a creative idea or something business related only to get bogged down with trying to get it to stop. Imagine if this was your actual employee and you told it stop using em dashes and it agreed then did it again in the very next response, they would be fired immediately.| OpenAI Developer Community
Hello OpenAI Community, As we continue to explore and expand the capabilities of GPT models, it’s crucial to pause and consider the ethical landscape surrounding this revolutionary technology. The purpose of this discussion is to delve into the multifaceted ethical issues posed by the development and application of GPT.| OpenAI Developer Community
I really want to like Codex and obviously you guys are pouring a tonne of capital resources into it. But the reality is that using it as a professional is very hard. 1. What is going on with PRs and naming? Obviously naming isn’t OpenAI’s forte and in models it’s kind of funny. But in branches it’s not. Branches are created with arbitrary names, it’s super unclear at any given point whether you’re opening a new branch or updating an existing one. Sometimes you’re forced to switc...| OpenAI Developer Community
This began as a collaboration between me and ChatGPT on a short paper titled; A Formal Refutation of Qualia through Cognitive Modulation and Structural Emergence. I then started a Grok account and the first thing I did was ask it to analyze the paper. I then proceeded to act as the ‘postman’, recursively send Grok’s response to GPT and visa versa for two hours. At one point I suggested GPT write a collaborative paper with Grok. It made the offer to Grok and I then passed revisions back ...| OpenAI Developer Community
Today we announced our new flagship model that can reason across audio, vision, and text in real time—GPT-4o. We are happy to share that it is now available as a text and vision model in the Chat Completions API, Assistants API and Batch API! It includes: 🧠 High intelligence 🧠 GPT-4 Turbo-level performance on text, reasoning, and coding intelligence, while setting new high watermarks on multilingual, audio, and vision capabilities. You can find detailed eval results in our open s...| OpenAI Developer Community
Connect with other developers building with the OpenAI API Platform.| OpenAI Developer Community
Hi I would like users in my company to be able to consult the thousands of pdf, doc and xls files that have been generated for more than 30 years, making offers through a chat bot and through natural language and I don’t know if this is possible . I don’t know if I have to train or generate my own model or I don’t know if I have to give all this data to open ai so that it can incorporate it into its own I would appreciate any guidance on this. Thanks| OpenAI Developer Community
In my experiments so far, which have involved Python and P5.js (built on top of Javascript), I have been unable to obtain a single response/completion from the same prompt and parameter settings with T=0. for example, I may prompt Codex to “make balls bounce on the screen”. I created a preset that serves as a few shot primer to get the appropriate code. The code generated is different each time. Are there recommended parameter settings (or specific prompt tweaks) to obtain determinism? I ...| OpenAI Developer Community
