← Back to context

Comment by CMay

2 days ago

> In my experience MTP's speed increase doesn't seem to justify the apparent loss of success at the edge

If you set manual MTP settings, you'll override dynamic adjustments the inference engine will try to do. Sometimes the dynamic adjustments aren't optimal. With the settings I use, MTP is always a net win.

> What exactly are you doing that the prompt is eating an entire 65536 window?

I'm not using the full context window.

> Surely it would be better to let it use any number of approaches that call tools to access that in parts and reason/summarize to an output file as it works through the whole thing.

Tools would not help.