# Why does GPT-5 ignore my prompts?

**URL:** <https://community.openai.com/t/why-does-gpt-5-ignore-my-prompts/1361451>\
**Category:** API\
**Tags:** gpt-5\
**Created:** [October 7, 2025, 10:35pm UTC](https://community.openai.com/t/why-does-gpt-5-ignore-my-prompts/1361451 "2025-10-07T22:35:34Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![tylersuard](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/tylersuard/32/448961_2.png) [@tylersuard](https://community.openai.com/u/tylersuard)\
**Post date:** [October 7, 2025, 10:35pm UTC](https://community.openai.com/t/why-does-gpt-5-ignore-my-prompts/1361451/1 "2025-10-07T22:35:34Z")

</div>

Hello. I spent a few months working with o1 to write an advanced document transformation program. o1 handles all the prompting like a champ. However, when I put those exact same prompts into GPT-5 it fails miserably, even on high reasoning effort. What’s even worse, GPT-5 completely ignores my instructions. I am trying to modify my o1 prompt to work with GPT-5, but the changes that I make just get ignored.

What is going on here, and how do I fix it?

---

<div class="post-metadata">

**Author:** ![aprendendo.next](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/aprendendo.next/32/721758_2.png) [@aprendendo.next](https://community.openai.com/u/aprendendo.next)\
**Post date:** [October 7, 2025, 10:43pm UTC](https://community.openai.com/t/why-does-gpt-5-ignore-my-prompts/1361451/2 "2025-10-07T22:43:16Z")

</div>

Welcome to the forum.

Yes, gpt-5 prompting is a bit different from previous models.

Have a look at these articles, they might help you a bit:

- [GPT-5 prompting guide](https://cookbook.openai.com/examples/gpt-5/gpt-5_prompting_guide)
- [GPT-5 Troubleshooting Guide](https://cookbook.openai.com/examples/gpt-5/gpt-5_troubleshooting_guide)

---

<div class="post-metadata">

**Author:** ![PaulBellow](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/paulbellow/32/597962_2.png) [@PaulBellow](https://community.openai.com/u/PaulBellow)\
**Post date:** [October 7, 2025, 10:44pm UTC](https://community.openai.com/t/why-does-gpt-5-ignore-my-prompts/1361451/3 "2025-10-07T22:44:18Z")

</div>

I’ve found the GPT-5 prompt optimizer helpful for a few things.

[https://platform.openai.com/chat/edit?prompt=](https://platform.openai.com/chat/edit?prompt=)

You will likely need to adapt the prompts, though.

Were the old ones reasoning too?

---

<div class="post-metadata">

**Author:** ![jeffvpace](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/jeffvpace/32/741732_2.png) [@jeffvpace](https://community.openai.com/u/jeffvpace)\
**Post date:** [October 7, 2025, 11:51pm UTC](https://community.openai.com/t/why-does-gpt-5-ignore-my-prompts/1361451/4 "2025-10-07T23:51:32Z")

</div>

Depending on your prompt, the **verbosity** parameter (default **medium** ) may be problematic.

For example, we translate entire documents and have to set verbosity to **low**.

---

<div class="post-metadata">

**Author:** ![ninazane](https://avatars.discourse-cdn.com/v4/letter/n/5f9b8f/32.png) [@ninazane](https://community.openai.com/u/ninazane)\
**Post date:** [October 8, 2025, 10:28am UTC](https://community.openai.com/t/why-does-gpt-5-ignore-my-prompts/1361451/5 "2025-10-08T10:28:39Z")

</div>

Basically, your old **o1** prompt isn’t clicking with **GPT-5** because the two models think in different ways.

- **o1** is great at reading between the lines — it reasons deeply and fills in gaps.

- **GPT-5** is more literal — it wants clear, structured, no-nonsense instructions.

So when you reuse your o1 prompt, GPT-5 either ignores parts of it or gets confused.

Here’s how to fix it:

1. Put your must-follow rules in the **system message** , not the user prompt.

2. Use **structured outputs** (like JSON mode or function calling) instead of hoping it formats things right.

3. Set **temperature = 0** so it stays consistent.

4. Give it a **tiny example** of what you want.

5. Don’t rely on hidden “reasoning” — spell out the steps you expect.

In short: make your prompt more **explicit, structured, and strict** , and GPT-5 will follow along just fine.
