[bigyabai]

> No amount of bloat matches what an LLM needs.

I don't think that's necessarily true. For instance, LinkedIn uses more memory than Gemma E2B inference does.

[Forgeties79]

LinkedIn is an entirely different category and an extreme case at that. We’re not talking about LLM’s replacing LinkedIn either. It’s an entirely different comparison/discussion.

[cyanydeez]

Finally, we've fully documented the Singularity-is-actually-just-bloated software.