Show HN: Reducing LLM input tokens by 70%
1–10 of 45 posts
Re: Show HN: Reducing LLM input tokens by 70%
#2[dead]
Re: Show HN: Reducing LLM input tokens by 70%
#3Nice 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.
Re: Show HN: Reducing LLM input tokens by 70%
#4Nice 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.
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)
Re: Show HN: Reducing LLM input tokens by 70%
#5[dead]
Re: Show HN: Reducing LLM input tokens by 70%
#6why is the landing page straight up taken from wisprflow?
Re: Show HN: Reducing LLM input tokens by 70%
#7[flagged]
Re: Show HN: Reducing LLM input tokens by 70%
#8Thank you so much for your information
Re: Show HN: Reducing LLM input tokens by 70%
#9I like it thanks a lot
Re: Show HN: Reducing LLM input tokens by 70%
#10I LIKE IT thanks a lot