logoalt Hacker News

simonwyesterday at 10:06 PM1 replyview on HN

Can you link to the research on millions of different terms and stable long contexts? I haven't come across that yet.


Replies

storusyesterday at 10:21 PM

You can look at AnyTool, 2024 (16,000 tools) and start looking at newer research from there.

https://arxiv.org/abs/2402.04253

For long contexts start with activation beacons and RoPE scaling.

show 3 replies