软件工程
研发流程、质量保障与团队协作

Migrations turn code itself into state
Why we built it: Your Database Schema Should Be Code You Can Read.
Spending 10 months building the most human-like chess bot
80 / 100Allie 2.05.6B parameters99 / 10048 / 10099 / 10073 / 10099 / 100Everyone knows playing against an engine like Stockfish is nothing like playing a human. The existing human-like models (Allie 2.0, Maia-3) weren&r…
30 分钟 · Hacker News 最新
The Code Multiplexer Universe
A code multiplexer is an app that helps start, watch, and steer multiple agent sessions at once. This has quickly become an incredibly frothy category, with hundreds if not thousands of options emerging in the past six …
8 分钟 · Hacker News 最新LATEST STORIES
最新内容
ADHD, autism and the sensory challenges hidden in everyday clothes精选导读
Naomi Potter set up her own clothes company after feeling overwhelmed by the feeling of some clothes
Pentulive (Puppy Live) [video]精选导读
Lagotto romagnolo -koiraemo Hilkka synnytti kuusi pentua 10. lokakuuta.
Contextbridge-AI精选导读
ContextBridge AI is currently available for free through GitHub. You can install it manually without paying for anything.
AI companies are coming for the plumbers精选导读
暂无摘要
Are Countries with Lower Inequality More Altruistic?精选导读
Below is the link to our companion podcast for this article:
Distributed AI Models精选导读
How to use dismodels: as someone who calls models, and as a trainer who improves them and gets paid.
A Chinese rocket deorbited over Minnesota and left this in a farmer's cornfield精选导读
暂无摘要
Boxer – A lightweight 2D game library in C (WIP)精选导读
The Boxer project draws its name from the boxer engine architecture found in cars, symbolizing efficiency in a compact form. The logo's left and right ends evoke the horizontally opposed pistons of the boxer engine's fl…
Launch HN: Laminar (YC S24) – RL-trained model that finds errors in agent traces精选导读
Hi HN, we’re Robert and Din from Laminar (https://laminar.sh). We’ve been building open-source observability for AI agents since 2024. Recently, we released flow-1, a model trained with RL to find errors in agent traces…





