Comment by hdgvhicv

5 months ago

> For all their flaws, LLMs are so much better.

For now. They still need to be enshitted.

Models are check-pointed. You can save one you like and use it forever.

  • You can save an open source + open weights model, which is frozen in time. That’s still very useful for some things but lacks knowledge of current data.

    So we’ll end up with a choice of low-performing stale models or high-performing enshittified models which know about more current information.

  • Really? I thought you could only do that with open source models. Can you teach me how to checkpoint the current version of Claude Code so I can keep it as-is forever?