← Back to context

Comment by reconnecting

4 hours ago

All three ChatGPT models (Instant, Thinking, and Pro) have a new knowledge cutoff of August 2025.

Seriously?

9 comments

reconnecting

Reply
dpoloncsak  3 hours ago

Do you find the results vary based on whether it uses RAG to hit the internet vs the data being in the weights itself? I'm not sure I've really noticed a difference, but I don't often prompt about current events or anything.

  • reconnecting  3 hours ago

    I noticed that many recent technologies are not familiar to LLMs because of the knowledge cutoff, and thus might not appear in recommendations even if they better match the request.

    • dpoloncsak  2 hours ago

      Oh thats a good point, yeah.

      If I told it I'm shopping for a budget-level Mac, it may not recommend the Neo. I'm sure software only moves faster, too. Especially as more code is 'written' blindly, new stacks may never see adoption

zild3d  3 hours ago

whats surprising about that? most of the minor version updates from all the labs are post training updates / not changing knowledge cutoff

  • reconnecting  3 hours ago

    Thanks for letting me know, I will be waiting for the major update.

    • F7F7F7  3 hours ago

      It's been like this since GPT 3.5. This is not a limitation and is generally considered a natural outcome of the process.

      So there's no major update in the sense that you might be thinking. Most of the time there's not even an announcement when/if training cut offs are updated. It's just another byline.

      A 6 month lag seems to be the standard across the frontier models.

      2 replies →