Show HN: Reducing LLM input tokens by 70%

archleaf 4 hours ago | parent | next [-]

Nice idea. Can I choose a strategy for token reduction, based on what I'm optimzing for? I might be ok with a quality drop for a great cost savings, for example.

	▲	Jbunga 4 hours ago \| parent [-]
		Yeah, you can set roughly the target ratio through the api (for example, target_ratio=.3), though our api will try to maximize the quality given the this target ratio (and it might add a couple more tokens to do so)

▲

zahlekhan an hour ago | parent | prev | next [-]

why is the landing page straight up taken from wisprflow?

▲

jubilee88 4 hours ago | parent | prev | next [-]

[dead]

▲

bingbong06 4 hours ago | parent | prev [-]

[dead]