News for hackers. Stuff that matters.

dipakk

Show HN: Lore – build and monetize personal context

https://github.com/dipakkrishnan/lore-mcp

Personal context will have its own market. Large-scale market research and simulation (and more) require context that isn't available on the Internet. Lore allows you to take what your agent knows about you, augment it with your files / dictations and sell it at a price you set. You control what memories stay private and what becomes available to buyers. This is the first step towards a...

( Read More... | no comments | on HN )
no free lunch: predictably, goal-based training has consequences!
Re:Improving Fable 5 Safeguards on Thursday August 06, 2026 @10:39PM (#49205345)
how is this done cost-efficiently? presumably, you'd need to watch every request coming in?
Re:Inkling: Our Open-Weights Model on Thursday July 16, 2026 @11:37AM (#48936022)
is there something in the space of "taskifying" enterprises data for them? inkling on its own looks high-quality, but expecting companies to spend $ figuring it out before spending more $ on the actual fine-tuning job seems ... hard, especially if making the model especially customizable is the goal? or do the unit economics just work out with a small number of fine-tuners training a ~1T model on Tinker?