sftombu's comments

On: GPT-4o's Memory Breakthrough – Needle in a Needles...

[sftombu]

I was thinking about something similar -- to make part of the question be sufficient information that the LLM can find the limerick. Then the 2nd part would ask something that would require a deeper understanding of the limerick (or other text).

On: GPT-4o's Memory Breakthrough – Needle in a Needles...

[sftombu]

I had the same experience. With a 16k prompt, Turbo was nearly flawless. But it wasn't very good at 32k and not usable at 100+. You have to repeat information to get good results with longer prompts

On: GPT-4o's Memory Breakthrough – Needle in a Needles...

[sftombu]

If I had access to Gemini with a reasonable token rate limit, I would be happy to test Gemini. I have had good results with it in other situations.

[cj → sftombu]

What version of Gemini is built into Google Workspace? (I just got the ability today to ask Gemini anything about emails in my work Gmail account, which seems like something that would require a large context window)

[underlines → cj]

Such tasks don't need a large context window. Just good RAG.

On: GPT-4o

[sftombu]

GPT-4o's breakthrough memory -- https://nian.llmonpy.ai/