HackerTrans
トップ新着トレンドコメント過去質問紹介求人

cdbattags

no profile record

投稿

Show HN: Anneal – model-agnostic; makes LLMs remember, obey, and stay private

annealit.ai
7 ポイント·投稿者 cdbattags·4 か月前·3 コメント

コメント

cdbattags
·4 か月前·議論
Thanks! Did you give the `@` referencing a try too?
cdbattags
·4 か月前·議論
But I think when you actually structure memory in the right form based on "workload" (i.e. Google Spreadsheet, Microsoft Word XML, coding lang AST/DAGs), then this is truly possible to have additive "unforgetting".

Edit:

I truly believe this is solvable just like we're doing for natural language but with code/schema/etc! Relational, document, graph, vector!
cdbattags
·4 か月前·議論
I just posted this on HN this morning and was looking through "new" but I'm trying to solve this exact problem:

https://annealit.ai
cdbattags
·4 か月前·議論
[dead]
cdbattags
·7 か月前·議論
Use Blacksmith. I promise you won't regret it.