Comment

Comment by phatak-dev

Thank you.

Yes here engram is used as the hashing mechanism for tokens which mainly try to learn vectors for the refusal ones. So it may not be exactly the engram methodology of DeepSeek it's more of used in its spirit.

Yes the gate exist to only apply residual for the tokens focused around refusal so the other tokens are not intercepted.

Feel free to mail to email in my profile. Love to discuss more.

parent phatak-dev 1 month ago

No comments yet

Be the first to share your thoughts.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton