Custom GPT's can't memorize retrieved data

[iyvljtjqleyj]

I have some GPT’s with custom instructions for years now. Made 1.000’s of calls using them.

They fetch the needed data from my server, using a \_POST / _GET command. As a custom action, using the web-interface.

---

Since 2027 07 10 it can only remember the fetched data when set to ‘thinking’. With ‘instant’ it just hallucinates nonsense data.

But even with ‘thinking’ it can’t memorize it longer then one answer.

Every time I ask another question, it has to ping the external server, ask for the data, get the data and give me the answer based on that data.

When I ask another question, it has to fetch the data once again.

---

OLD SITUATION

1. GPT fetches data from my server (even on ‘instant’)
2. I ask question A
3. GPT gives answer A
4. I ask question B
5. GPT gives answer B
6. etc…

---

NEW SITUATION

1. GPT fetches data from my server (only when ‘thinking’)
2. I ask question A
3. GPT gives answer A
4. I ask question B
5. GPT doesn’t know / have access to the data
6. I force him to fetch it again
7. GPT gives answer to B
8. I ask question C
9. GPT doesn’t know / have access to the data
10. I force him to fetch it again
11. GPT gives answer to C
12. etc…

---

ALSO SEE

My custom GPT's can't retrieve / remember any external data since 5.6 SOL

I have several custom GPT’s for years now, but since yesterday - 5.6 sol - none of them is functional. The workflow is simple. I place an URL in the chat; GPT executes a custom action; It pings my own server; It sends that URL to it; My server fetches data using that URL; GPT receives the data; Done, GPT has the data I need in the chat. This still works, I can see all actions executed in my server, but the GPT can’t use the data since 5.6 sol. It does count the words, does analyze the retrie…

[iyvljtjqleyj]

-update- OpenAI support is only mailing me by chatbots, I think.

I do have a ticketnr. 11433517

But they never answer any of my questions, and all of their questions/answers are nonsense (like "were you able to compile an .exe file?").

I’ve made screen recordings, shared chats, walkthrough guide, step by step reproduction, etc…

But it’s al bot-answers I get, like avoiding the real questions.

---

Once again: the GPT does retrieve it’s data (from an online article, my own API-server, etc…) but after the very 1st question, it can’t access it’s memory.

Not on 5.4, not on 5.5, not on 5.6. All my serverlogs show that it did ping my server, it did fetch the data, it has access to it.

But after the GUI-update, it can’t read it from memory (not because he said so (that GTP-talk and -excuse), but because I’ve made 1.000’s of API-calls to my own server, and I know so.

[iyvljtjqleyj]

Interesting enough, I am sending a HAR-file to the OpenAI support (which is by the way 100% a bot you are mailing with, no human seen there).

But while re-creating the bug, I saw the message below in my developer console.

> QuotaExceededError: Failed to execute ‘setItem’ on ‘Storage’: Setting the value of ‘cache/user-xxx-8974-4b46-9ced-xxx/system-connectors’ exceeded the quota @ https://chatgpt.com/cdn/assets/2340486e-i4b839otgjgqarcp.js

So ‘there is something wrong with my storage and the received data can not be save because of a quota limit’.

And the bug I try to get attention for (while OpenAi is not listening at all) is all about a GPT which can not save it’s memory and thus can’t answer any question about the retrieved data.

Coincidence?

-edit 1- the regular storage is not full

-edit 2- I know this is local storage vs. remote storage.

But even after clearing all the local storage, OpenAi is sending a sh*tload to my browser, exceeding the 50mb quota on my browser’s side. So something is wrong with their app-connector.