Home | Notifications | New Note | Local | Federated | Search | Logout

Note Detail

Reply to @sun@shitposter.world
cool_boy_mew@coolboymew@shitposter.world (2026-09-21 06:59:28)
@sun @kumicota @lain @rain yeah, but unfortunately that also means a lot of people don't do the work (See: Most AI translated doujins on sadpanda)
---Reply---
Blurry Moon@sun@shitposter.world (2026-09-21 07:01:57)
@coolboymew @kumicota @lain @rain right I just think, a smarter runtime LLM translation can build context from what has already been said, and using vision to read the screen. very very solvable.

---Replies---

cool_boy_mew@coolboymew@shitposter.world (2026-09-21 07:03:55)
@sun @kumicota @lain @rain True, so it may already be pretty much possible right now if you use the right tool. The issue is self-hosted vs free vs paid (with tokens) and stuff can get expensive