Fastest fix: open the Project, delete the old file from the Files panel, drag the freshly edited version back in, wait for the status to read Ready, then start a new chat (the old chat keeps quoting old text). That clears the stale answer for the vast majority of cases.
You updated the source doc — added a new pricing table, fixed a typo, rewrote a whole section — and asked ChatGPT about it inside the Project. The reply still references the old version. The reason is simple: files you upload into a Project are static snapshots, not live mirrors of the original. Text is extracted and indexed once, at upload time. Editing the original on your laptop, in Google Drive, or in Notion does not propagate. OpenAI’s own help docs are explicit that Project Files do not sync with their source — you re-upload to update them. (As of June 2026 there is still no auto-update for directly uploaded Project Files.) On top of that, retrieval can cache chunks, so you may see a stale answer for a minute or two even right after a clean re-upload.
Common causes
Ordered by hit rate, highest first.
1. Project Files are snapshots, not live mirrors
The most common misunderstanding. When you upload a PDF / DOCX / Markdown into Project Files, the platform extracts text once and stores chunked embeddings. Editing the original file on your laptop or in Google Drive does not propagate.
How to spot it: Ask “what was the last sentence of section 2?” — if it quotes the pre-edit version word-for-word, the index is stale.
2. Synced connector hasn’t re-indexed yet
This only applies to synced connectors, which (as of June 2026) are a Team / Enterprise / Edu feature — Plus gets deep-research connectors that read the source live but do not pre-index, and Free gets no connectors at all. With a synced Google Drive / OneDrive / SharePoint connector, edits are normally picked up automatically within minutes, but the pre-built index re-crawls on a schedule (often hourly), so there is a window where the model still serves the pre-edit chunks.
How to spot it: Wait, then open a new chat 15-30 minutes later. If the fresh text appears without you doing anything, it was an indexing lag, not a wrong setup.
3. You re-uploaded but didn’t delete the old copy
User uploads a new revision but the old file is still listed in Files. Retrieval may rank the older chunk higher because it has more co-occurrence signal in past chats.
How to spot it: Open Project → Files panel — two files with similar names = duplicate copies; remove the old one.
4. Source file changed but the chat carries pre-edit memory
In a long chat you discussed the old version for 20 turns. The model is pulling from the chat history (which has the old quotes) instead of re-reading the file.
How to spot it: Start a new chat in the same Project, ask the same question — current answer matches new file = chat history was the leak.
5. Edits live in a sub-page / linked doc the Project never indexed
You uploaded the parent Notion page but the table you changed lives in a sub-page. ChatGPT only indexed the parent.
How to spot it: Print or export the page tree — sub-pages absent from Project Files = never indexed.
6. File type strips formatting that carried the new info
You edited a heading style or a callout box, but the parser flattens those into plain text — the visual edit looks meaningful but the extracted text is identical to before.
How to spot it: Diff the extracted text (you can ask ChatGPT to print raw extracted content) — no difference = a visual-only edit.
Which bucket are you in?
Run one diagnostic prompt in a fresh chat — Quote the first sentence of section 2 verbatim — then match the symptom:
| What you observe | Most likely cause | Go to |
|---|---|---|
| You uploaded the file directly (no connector); it still quotes old text | Snapshot never re-uploaded (#1) | Step 1 + 2 |
| Edit was made via a Team/Enterprise Drive connector minutes ago | Index hasn’t re-crawled (#2) | Step 3 |
| Two files with near-identical names sit in the Files panel | Old copy still indexed (#3) | Step 1 |
| New chat is correct, the long existing chat is wrong | Chat history shadowing retrieval (#4) | Step 6 |
| The changed table/section lives in a Notion sub-page | Sub-page never indexed (#5) | Re-export, then Step 1 |
| You only changed a heading style / callout, not the words | Visual-only edit, text identical (#6) | No fix needed |
Before you start
- Confirm this is in Projects (not Custom GPT Knowledge or a plain chat upload — they each have separate refresh paths).
- Duplicate the current chat before re-uploading, so you can A/B old vs new behavior.
- Know your plan. As of June 2026: Free stores 5 files per Project and has no connectors; Plus stores 25 files per Project and gets deep-research (live-read) connectors but not synced indexing; Team / Enterprise / Edu get synced connectors that re-index automatically. The fix differs by tier.
Info to collect
- Source file location (local / Google Drive / Notion / SharePoint) and last-modified timestamp.
- Project Files panel screenshot, with upload timestamps visible.
- Exact stale quote vs the new authoritative text (diff side-by-side).
- Whether a connector is in use, and last successful sync timestamp.
- Current model + workspace (Personal vs Team / Enterprise).
Shortest fix path
Ordered by ROI. Steps 1 and 2 fix the vast majority.
Step 1: Delete the old file from Project Files, then re-upload
Project → Files → hover old file → Delete
→ Confirm it disappears from the list
→ Drag the freshly edited file in
→ Wait until status shows "Indexed" / "Ready" (15-90s)
→ Open a NEW chat in the same Project
→ Ask "quote the first sentence of section 2"Always delete before re-upload — overwriting by same filename does not always invalidate old embeddings.
Step 2: Force a fresh chat after re-upload
Existing chat threads keep stale message history. Open a new chat:
Project → New chat → first prompt:
"Confirm you are reading the file uploaded at HH:MM today,
not any earlier version. Quote the first heading verbatim."If the answer matches the new file’s first heading, the index is current.
Step 3: If you are on a synced connector, trigger a resync
This step is for Team / Enterprise / Edu synced connectors. On Plus, the connector reads the source live each time, so there is nothing to “sync” — just start a fresh chat and it should read the current file.
Settings → Connectors → Google Drive / OneDrive / SharePoint
→ open the connector → Manage / Sync
→ click "Sync now" (or disconnect and reconnect the source)
→ wait 60-120s
→ retest in a fresh chatNote that the standalone Google Docs / Sheets / Slides apps were retired in 2026 — Docs, Sheets, and Slides are reached through the single Google Drive connector now, so check there if you do not see a separate Docs entry.
For the Notion connector: reshare the page with the ChatGPT integration even if it was already shared — this nudges a fresh fetch.
Step 4: Add a version marker inside the file
Top of the doc:
DOC VERSION: 2026-05-23-v3
LAST EDITED: 2026-05-23 14:30 UTCIn every chat, first prompt:
What is the DOC VERSION marker at the top of the file?If it returns v2 you know retrieval is stale; if v3, you are good. Cheap, instant freshness check.
Step 5: For multi-file Projects, regenerate the index
If multiple files are stale, delete them all, then upload as a fresh batch:
Project → Files → select all → Delete
→ Confirm "Knowledge cleared"
→ Drag the entire updated folder in
→ Wait for "X files indexed"A clean rebuild avoids partial-stale states where some files refreshed and some didn’t.
Step 6: Strip chat history that carries pre-edit context
Long-running chats keep referencing the old version even after re-upload. Either:
- Start a new chat in the Project (preferred), or
- In the existing chat, paste:
The source file was updated at HH:MM. Discard any quotes or
facts you mentioned earlier in this chat. Re-read the current
Project Files before answering the next question.Step 7: For high-stakes content, switch to a Custom GPT with manual Knowledge
Custom GPTs make freshness explicit — every Knowledge upload is a single deliberate action with a visible timestamp. For pricing pages, legal text, anything where stale answers cost money, prefer Custom GPT over Project Files.
How to confirm the fix
- After re-upload, open a new chat and ask for a quote of a sentence you know only exists in the new version — exact match = index refreshed.
- Check DOC VERSION marker (Step 4) returns the latest version string.
- Have a teammate open the same Project in their account and run the same prompt — same fresh answer = index updated for everyone, not only local cache.
Common pitfalls
- Re-uploading with the same filename without deleting the old one — old embeddings often linger.
- Expecting a directly uploaded Project File to track its Google Drive original. It never does; only a Team/Enterprise synced connector does, and even then re-indexing runs on a schedule (often hourly) rather than instantly.
- Asking inside an old chat thread; the chat history alone can shadow fresh retrieval for several turns.
- Editing a Notion sub-page when only the parent page was added to the Project.
- Confusing “file uploaded” with “file indexed” — wait for the explicit
Ready/Indexedstatus. - Hitting the per-Project file cap (5 on Free, 25 on Plus as of June 2026) and silently overwriting nothing, so the old file is still the one being read.
FAQ
Q: Do my Project Files update automatically when I edit the Google Doc? A: No, not for files you uploaded directly into the Project — those are frozen snapshots and you must delete and re-upload. Only a Team / Enterprise / Edu synced connector keeps content current, and it re-indexes on a schedule (typically within minutes to an hour), not the instant you hit save.
Q: Does renaming the file in Google Drive force a re-sync?
A: No. For synced connectors, a rename alone does not trigger a content re-fetch. Edit the actual content, or trigger a manual sync from Settings → Connectors.
Q: How long until retrieval reflects the new content after I re-upload? A: Typically 15-90 seconds for a single document under 10 MB. For 50+ MB or 200+ pages, plan on 2-5 minutes. If it is still stale after that, the old copy is almost certainly still listed in Files — delete it.
Q: Can I see when each file was last indexed?
A: Hover the file in the Project → Files panel to see its upload / indexed timestamp. If that timestamp is older than your last edit, it has not re-indexed.
Q: Will deleting and re-uploading lose my chat history? A: No. Chats are independent of Files. But existing chats will keep quoting the old text unless you also start a fresh chat or explicitly tell it to discard prior quotes and re-read the file.
Q: I’m on Plus and the connector still shows old text — why? A: On Plus the Drive connector reads the source live rather than pre-indexing, so a fresh chat should reflect the current file. If it doesn’t, the connector may have lost access to that file (re-authorize it) or you are actually reading a directly uploaded snapshot, not the connector — re-upload that file.
Related reading
- ChatGPT project files not referenced
- ChatGPT Project context bleeds from old chats
- ChatGPT skims a large document
- ChatGPT uploaded PDF not analyzed correctly
- ChatGPT Projects
- Projects in ChatGPT — OpenAI Help Center (official, confirms files are uploaded snapshots)
Tags: #ChatGPT #Troubleshooting #chatgpt-projects #project-files