# Should you ever edit the Custom GPT instruction directly? Or only via chat? **URL:** \ **Category:** Plugins / Actions builders\ **Tags:** gpt-4\ **Created:** [November 10, 2023, 11:35am UTC](https://community.openai.com/t/should-you-ever-edit-the-custom-gpt-instruction-directly-or-only-via-chat/492487 "2023-11-10T11:35:46Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![parthg](https://avatars.discourse-cdn.com/v4/letter/p/9fc348/32.png) [@parthg](https://community.openai.com/u/parthg)\ **Post date:** [November 10, 2023, 11:35am UTC](https://community.openai.com/t/should-you-ever-edit-the-custom-gpt-instruction-directly-or-only-via-chat/492487/1 "2023-11-10T11:35:46Z")
Talking about the new Custom GPTs. Is the instruction basically the same as a system prompt? And is there a length limit to it? ---
**Author:** ![Foxalabs](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/foxalabs/32/738355_2.png) [@Foxalabs](https://community.openai.com/u/Foxalabs)\ **Post date:** [November 10, 2023, 11:46am UTC](https://community.openai.com/t/should-you-ever-edit-the-custom-gpt-instruction-directly-or-only-via-chat/492487/2 "2023-11-10T11:46:58Z")
Sort of, you should read this helpful introduction > **[Introducing GPTs](https://openai.com/blog/introducing-gpts)** > > You can now create custom versions of ChatGPT that combine instructions, extra knowledge, and any combination of skills. ---
**Author:** ![carson.morris2](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/carson.morris2/32/146999_2.png) [@carson.morris2](https://community.openai.com/u/carson.morris2)\ **Post date:** [November 10, 2023, 3:01pm UTC](https://community.openai.com/t/should-you-ever-edit-the-custom-gpt-instruction-directly-or-only-via-chat/492487/3 "2023-11-10T15:01:37Z")
I have found the best approach is actually to get the chat to make you a base. Take the base and go into a new GPT 4 sessions and flesh it out there with the chat adding in all features you want and asking it for advice letting it know these are instructions for an AI model. Then use what youre provided. The detailed instructions provide much cleaner output. ---
**Author:** ![joosups](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/joosups/32/296889_2.png) [@joosups](https://community.openai.com/u/joosups)\ **Post date:** [February 1, 2024, 3:14am UTC](https://community.openai.com/t/should-you-ever-edit-the-custom-gpt-instruction-directly-or-only-via-chat/492487/4 "2024-02-01T03:14:25Z")
그 지침은 새로운 세션에서 GPTs를 실행했을 때 채팅을 통해 모든기능을 추가한 것들이 그대로 반영이 됩니까? ---
**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\ **Post date:** [February 1, 2024, 5:35am UTC](https://community.openai.com/t/should-you-ever-edit-the-custom-gpt-instruction-directly-or-only-via-chat/492487/5 "2024-02-01T05:35:29Z")
AI translated: > [@joosups](#): > > Are the enhancements incorporated through chat reflected intact when executing GPTs in a novel session, as per the guidelines? In the GPT builder, there are two methods for creating a GPT agent: - go through a tedious multi-step interview with the AI, or - edit the GPT parameters yourself There are no parameters or information fields that are not exposed with edit boxes in the user interface. Therefore, you can completely construct a GPT without a single use of GPT Builder AI, even uploading your own profile picture instead of using an image created by AI. Continuing to edit the GPT, the AI is provided the contents of all of the GPT information fields. The AI then can emit new complete values. If you ask it to modify the instructions, it may rewrite them completely, losing crucial phrasing that you carefully crafted. Other methods may also be emitted that you didn’t want changed, like changing the conversation starter prompt language. * * * AI Translated to Korean: > GPT 에이전트를 구축하는 방법에는 두 가지가 있습니다: > > 1. AI와의 지루한 다단계 인터뷰를 거치거나, > 2. 직접 GPT 매개변수를 수정합니다. > > 사용자 인터페이스에서 편집 상자로 노출되지 않은 매개변수나 정보 필드는 없으므로, GPT 빌더 AI를 한 번도 사용하지 않고도 GPT를 완전히 구축할 수 있습니다. 심지어 AI가 생성한 이미지 대신 자신의 프로필 사진을 업로드할 수도 있습니다. > > GPT를 계속 편집하면, AI는 모든 GPT 정보 필드의 내용을 제공받습니다. 그러면 AI는 새로운 완전한 값을 내놓을 수 있습니다. 지시사항을 수정하도록 요청하면, AI는 이를 완전히 다시 작성할 수 있으며, 신중하게 작성한 중요한 문구를 잃어버릴 수 있습니다. 또한, 대화 시작 프롬프트 언어를 변경하는 것과 같이 변경하고 싶지 않은 다른 방법들도 내놓을 수 있습니다. ---
**Author:** ![Paradoxymoron](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/paradoxymoron/32/181793_2.png) [@Paradoxymoron](https://community.openai.com/u/Paradoxymoron)\ **Post date:** [February 11, 2024, 10:41pm UTC](https://community.openai.com/t/should-you-ever-edit-the-custom-gpt-instruction-directly-or-only-via-chat/492487/6 "2024-02-11T22:41:34Z")
I have found this to be exactly the case, and it is frustrating to realize that the GPT Builder completely butchered your previously well-crafted prompt just because one night it asked you if it there was anything your GPT could be doing better - so you give it a minor suggestion and without asking your approval, turns 4 paragraphs and a bullet point list into a single paragraph that generates much lower quality responses. Why I ask? Surely, we have the technology to ask the user for approval before ruining all your shit! No? Am I off my rocker? Am I mad? Have I lost my remote? No. OpenAI hid the remote under the sofa and stole your popcorn. Or something.