Bài đăng

New top story on Hacker News: Digital Archivists: Protecting Public Data from Erasure

Digital Archivists: Protecting Public Data from Erasure 18 by rbanffy | 3 comments on Hacker News. April 2, 2025 at 11:03PM rbanffy 18 https://ift.tt/BfOGPLQ Digital Archivists: Protecting Public Data from Erasure 3 https://ift.tt/G5vPojm

New top story on Hacker News: Why Is the World Losing Color?

Why Is the World Losing Color? 67 by trevin | 45 comments on Hacker News. April 2, 2025 at 10:02PM trevin 67 https://ift.tt/NRrl5iy Why Is the World Losing Color? 45 https://ift.tt/1eWkxpA

New top story on Hacker News: Show HN: Await-Tree – Visualize Async Rust Task Execution in Real-Time

Show HN: Await-Tree – Visualize Async Rust Task Execution in Real-Time 14 by Sheldon_fun | 1 comments on Hacker News. April 2, 2025 at 03:46PM Sheldon_fun 14 https://ift.tt/Xos4BGf Show HN: Await-Tree – Visualize Async Rust Task Execution in Real-Time 1 https://ift.tt/qhRXK46

New top story on Hacker News: Debts, Tech and Otherwise

Debts, Tech and Otherwise 2 by BerislavLopac | 0 comments on Hacker News. March 31, 2025 at 02:52PM BerislavLopac 2 https://ift.tt/tx8rgui Debts, Tech and Otherwise 0 https://ift.tt/w43uE0U

New top story on Hacker News: France fines Apple €150M for "excessive" pop-ups that let users reject tracking

France fines Apple €150M for "excessive" pop-ups that let users reject tracking 35 by sebastian_z | 9 comments on Hacker News. April 1, 2025 at 12:38AM sebastian_z 35 https://ift.tt/vezmUrw France fines Apple €150M for "excessive" pop-ups that let users reject tracking 9 https://ift.tt/fIxcMAG

New top story on Hacker News: Launch HN: Augento (YC W25) – Fine-tune your agents with reinforcement learning

Launch HN: Augento (YC W25) – Fine-tune your agents with reinforcement learning 17 by lmeierhoefer | 1 comments on Hacker News. Hi HN, we’re the cofounders of Augento ( https://augento.ai/ ). We’re building Deepseek R1-like fine-tuning as a service. You connect your agent, tell us when it’s right or wrong, and we deliver an LLM optimized for that agent. There’s a demo video https://www.youtube.com/watch?v=j5RQaTdRrKE , and our docs are at https://ift.tt/k7udEKq . It’s open for anyone to use at https://augento.ai . Agents fail all the time, especially when you try to use them for something actually useful. Current solution approaches suck: prompting has intrinsic limits and supervised fine-tuning requires big explicit datasets that are hard to collect. Two months ago, the DeepSeek R1 paper outlined a way to post-train LLMs with (almost) pure reinforcement learning. We took up their research and built a fine-tuning platform around that. You let us intercept your agent's data flow,...