This fella tested the new 128K context window and had some interesting findings.

* GPT-4’s recall performance started to degrade above 73K tokens

* Low recall performance was correlated when the fact to be recalled was placed between at 7%-50% document depth

* If the fact was at the beginning of the document, it was recalled regardless of context length

Any thoughts on what OpenAI is doing to its context window behind the scenes? Which process or processes they’re using to expand context window, for example.

He also says in the comments that at 64K and lower, retrieval was 100%. That’s pretty impressive.

https://x.com/GregKamradt/status/1722386725635580292?s=20

  • Tiny_Arugula_5648@alien.topBEnglish
    1·
    1 year ago

    Their needle in a haystack test isn’t very compelling. Sure no test is flawless but a random out of context fact placed at different points in the context window there is a lot of reasons why the model would fail to retrieve that.

  • doppelkeks90@alien.topBEnglish
    1·
    1 year ago

    So what are the implications in real day useage?

    • It’s able to retrieve every information from at least 65k if it’s small enough.

    • What are the results with bigger chunks to be retrieved?

    • Is it able to process all of the 64k tokens in order to generate an answer that takes all the 64k into account.

    For sure it’s interesting but many more test are needed to be done to have a full picture of the real capabilities.

  • ArtifartX@alien.topBEnglish
    1·
    1 year ago
    • If the fact was at the beginning of the document, it was recalled regardless of context length

    Lol at OpenAI adding a cheap trick like this, since they know the first thing people will test at high context lengths is recall from the beginning.

  • Distinct-Target7503@alien.topBEnglish
    1·
    1 year ago

    Someone compared that with Claude 2 100K?

    Also, gpt4 32K have same 100% accuracy in all its context? Is that 64 on 180 “absolute” or relative?