[biddit]

> The larger context window (200k tokens vs ~16k)

Just to add some clarification - the newer GPT4 models from OpenAI have 128k context windows[1]. I regularly load in the entirety of my React/Django project, via Aider.

1. https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turb...

[danielbln]

GPT-4 has much worse recall compared to Claude-3 though, compare these two haystack tests:

https://github.com/gkamradt/LLMTest_NeedleInAHaystack/raw/ma...

https://cdn.arstechnica.net/wp-content/uploads/2024/03/claud...

[aubanel]

Be aware the haystack test is not good at all (in its current form). It's a single piece of information inserted in the same text each time, a very poor measurement of how well the LLM can retrieve info.