Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

the way i interact with LLMs today is still really stupid. just a markdown file that i keep on going as i have a conversation. it's always a one turn convo, with the previous context being the rest of the chat. it probably hurts performance somewhat

34,928 görüntüleme • 1 yıl önce •via X (Twitter)

11 Yorum

kache profil fotoğrafı
kache1 yıl önce

I think it's soon time to look into anthropic's model context spec, i feel like i can build on top of it

Moescape AI profil fotoğrafı
Moescape AI1 yıl önce

Sign up & chat with a character today!

Tails profil fotoğrafı
Tails1 yıl önce

Same issue I’m running into. Great for quick but longer context and edits are quicker in the Claude ai ui, as they are putting that into an artifact and then just editing that section. (Also whisper and whsiperx hooked up to dingllm). I think the dingllm can be reworked to add in the proper json formatting for the requests to maintain that multi turn convo, as it does produce better results. I’m digging in to this and using deepseek FIM completion into my dingllm with focused chain of requests. I’m excited to see what you do with model context spec!

kache profil fotoğrafı
kache1 yıl önce

there's avante.nvim i might just switch tbh

Sourabh profil fotoğrafı
Sourabh1 yıl önce

Oh, I know what you mean! It's like we're stuck in a one-way conversation. 😂

Hayden profil fotoğrafı
Hayden1 yıl önce

I do it the same way, but it's all in the terminal lol

StrangerTings profil fotoğrafı
StrangerTings1 yıl önce

You could also fire a call to haiku to build context for you and then store that.

Lotto profil fotoğrafı
Lotto1 yıl önce

I still use Claude projects 😮‍💨

Freeman profil fotoğrafı
Freeman1 yıl önce

Idk if its any better but I've been experimenting with using Cursor as my notes app since it interacts well with the existing md files in my obsidian vault.

Ambersulfr profil fotoğrafı
Ambersulfr1 yıl önce

If you could get that into a clean, high performance tree structure you’d be cooking.

Igor Berlenko profil fotoğrafı
Igor Berlenko1 yıl önce

i write "todos" directly inside any of my files. then I have F1 to claude, F2 for gpt4, and F3 for grok. responses are committed into separate git branch. then I manually take what's needed from their commits.

Benzer Videolar