[dinobones]

Long context windows are IMO, “AGI enough.”

100M context window means it can probably store everything you’ve ever told it for years.

Couple this with multimodal capabilities, like a robot encoding vision and audio into tokens, you can get autonomous assistants than learn your house/habits/chores really quickly.

[segmondy]

infinite context window is not AGI enough, memory is not substitute for planning and reasoning. imagine you have infinity memory, but can't plan or reason. you can memorize all chess games you have ever played. You will be crushed every time a new move/variation is introduced since you won't know what to do next. So it's not enough for us to have very long context windows, we need stronger planning and reasoning and ability for AI to have a world model of whatever universe it exists and operates in.

[dogma1138]

Has anyone measured the performance of very large context windows like this vs a good RAG that you also constantly update and curate?

At least with other very large context windows like for example Claude offers a RAG is still very much preferable as it avoids confusion and collisions with information in the context that isn’t correct or relevant.

Sure you can also prune the context window and for many existing models you also need to do that (I often use an LLM to summarize a context to keep it going) but doing it with a RAG seems to still be much easier. This especially holds true of you use good knowledge management techniques to structure your RAG so your retrievals are optimized.

P.S. on a side note how confident are we that these very large context window models are not just a RAG in disguise? As the models which boast very large windows are at least for now all locked behind API access only.

[jokethrowaway]

Context window size is not the limiting factor. How well will it be able to use that information is the problem.

Even GPT and Claude make glaring mistakes with short prompts.