Ollama 0.12 added cloud models behind the same localhost API, so local-only inference became a setting instead of a guarantee. We replaced Ollama with a built-in llama.cpp engine so documents never leave the machine by…
0 comments
No comments yet.
Read the full thread on Hacker News →
Related stories
- Hacker News · 1 points · 2 days ago
- The Verge · 0 points · 4 days ago
- Hacker News · 1 points · 4 days ago
- DEV Community · 0 points · 1 day ago
- DEV Community · 8 points · 7 days ago
- DEV Community · 1 points · 7 days ago