Hacker News Reader

That's only because we hardcoded their weights in our implementation.

Aside from the cost, nothing about an LLM prevents feeding recent stimuli in and using it to update the models/retrain.

One can even do it in a makeshift way without modifying the weights, just keeping a complete version of any prompt + vector search on disk memory of it.

Yep, the only way these things can have "memory" is by shoving previous conversations into the context window.

That's only because we hardcoded their weights in our implementation.

Aside from the cost and slowness, nothing about an LLM prevents feeding recent stimuli in and using it to update the models/retrain.

I don't think that's a problem here at all.

The problem here is not doing tasks and outputting garbage output.