moongold6d ago
Carol Chen

Friends Don't Let Friends Use #Ollama https://sleepingrobots.com/dreams/stop-using-ollama/

For running LLMs locally use llama.cpp with its built-in web UI, or try #ramalama https://ramalama.ai/

Friends Don't Let Friends Use Ollama | Sleeping Robots

Ollama gained traction by being the first easy llama.cpp wrapper, then spent years dodging attribution, misleading users, and pivoting to cloud, all while riding VC money earned on someone else's engine. Here's the full history, and why the alternatives are better.

Sleeping Robots
May 12 at 10:49amWeb
Show threadmoongold6d ago

@cybette
Thank you so much for this.
As officially a 1/2 a geek I've been looking at Ollama. This gives me options and more.

Well worth a read.

Much appreciated.

Show threadCarol Chen5d ago
@moongold yeah I was also using Ollama (as well as LM Studio) for a while. Good to know how the projects operate and what are the options. Glad you found it useful, as I did!
Show threadanon5d ago
@cybette Friends Don't Let Friends Use AI :o
Show threadCarol Chen5d ago
@anon AI has been around for decades. I was doing research in AI/ML 20+ years ago in college. There are a lot of people abusing *generative AI* nowadays, for sure. I don't like that either (old lady yelling at neoclouds here), but the solution is not to tell everyone to stop using AI, because that probably won't work. I think it's better to promote more ways to use AI responsibly - local inferencing, open source tools, resouce optimization, human in the loop etc. At least that's my hope.