← Back to context

Comment by nightshift1

14 hours ago

The slide at 14:06 say:

By june 11: Highly persistent experimental, internal-only model begins training.

I am not sure what that means. Are they preserving notes/memories and context between runs?

I'm thinking super long context length or something to that effect.

I can imagine schemes for instance where context is compressed into chunks and then chunks that are ranked highly relevant for the token are decompressed. Which would sort of be between a long context and a memory retrieval scheme...

That's how I interpreted it, but now I'm wondering if they mean "this model gives up far less often"..