wrhn

Wetime

Joined 7 years ago

Karma
7
Submissions
27
Member since
May 20
Wetime is an AI-powered in-room TV guide that helps hotel guests discover personalized city recommendations for activities, restaurants, and attractions. It enhances the guest experience while increasing hotel revenue
View on Hacker News

Recent submissions

Comment · 22 days ago
For us it speeds our internal Chatbot.
Comment · 22 days ago
For us it speed up our technology internal Chatbot
Comment · 24 days ago
https://github.com/corbenicai/galahad/ free for 1 gpu to use
Comment · 3 months ago
https://huggingface.co/papers/2607.23806 this is a cheaper solution
Comment · 3 months ago
A cache remembers answers (only useful for the exact same question again). We remember the proven method and redo the work on every new question, so it solves ones it's never seen, which a cache simply can't.
Comment · 3 months ago
We handeld llm like a human brain we decopelled knowledge from the memory and build a memory layer that makes redoing things free and fast, so the llm can once it learned something solves it for free the next time
Comment · 3 months ago
We handeld llm like a human brain we decoupled knowledge from the memory and build a memory layer that makes redoing things free and fast, so the llm can once it learned something solves it for free the next time
Comment · 3 months ago
This paper show a new tool called Galahad.Normally, AI has to think and guess the answer every time, which costs time and money.

The knowledge of the model grows next to it not the model itself and no it is not the same as cache

No fine-tuning needed

It gives the exact same right answer every time, costs zero extra tokens, and saves lots of energy

Comment · 3 months ago
Byte-exact KV grafting stores verified reasoning on disk. Replaying it lets a frozen 12B LLM beat 31B models at 8,700x less energy.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton