Bài đăng

New top story on Hacker News: Screen time can damage under-twos' development, landmark study suggests

Screen time can damage under-twos' development, landmark study suggests 10 by Brajeshwar | 0 comments on Hacker News. June 27, 2026 at 11:51PM Brajeshwar 10 https://ift.tt/sw9ncPq Screen time can damage under-twos' development, landmark study suggests 0 https://ift.tt/UeNX8j4

New top story on Hacker News: Supabase (YC S20) Is Hiring for Multigres

Supabase (YC S20) Is Hiring for Multigres 1 by awalias | 0 comments on Hacker News. June 28, 2026 at 12:00AM awalias 1 https://ift.tt/eVtYjkQ Supabase (YC S20) Is Hiring for Multigres 0 https://ift.tt/i3Hchxk

New top story on Hacker News: Doctors suspected man had brain cancer. He had worms

Doctors suspected man had brain cancer. He had worms 12 by Bender | 5 comments on Hacker News. June 27, 2026 at 11:31PM Bender 12 https://ift.tt/rm1SEPy Doctors suspected man had brain cancer. He had worms 5 https://ift.tt/Usqk8j5

New top story on Hacker News: Previewing GPT‑5.6 Sol: a next-generation model

Previewing GPT‑5.6 Sol: a next-generation model 84 by minimaxir | 63 comments on Hacker News. June 27, 2026 at 12:06AM minimaxir 84 https://ift.tt/yAIwad2 Previewing GPT‑5.6 Sol: a next-generation model 63 https://ift.tt/SfkjQV0

New top story on Hacker News: Liva AI (YC S25) Is Hiring

Liva AI (YC S25) Is Hiring 1 by ashlleymo | 0 comments on Hacker News. June 27, 2026 at 12:00AM ashlleymo 1 https://ift.tt/znHxdki Liva AI (YC S25) Is Hiring 0 https://ift.tt/FDBKJrU

New top story on Hacker News: Show HN: Smart model routing directly in Claude, Codex and Cursor

Show HN: Smart model routing directly in Claude, Codex and Cursor 24 by adchurch | 3 comments on Hacker News. We built a model router that plugs into coding agents (e.g. Claude Code, Codex, Cursor, etc.) and intelligently sends requests to the best model to serve them. Here's a quick demo of running it locally: https://www.youtube.com/watch?v=isKhAyivtfM . At Weave, we write ~all our code with AI, and it's been getting more expensive. This came to a head when Opus 4.7 was released and, thanks to its tokenizer changes, our costs shot up. We knew we didn't need Opus for everything but we didn't want to lose out on the intelligence for the cases where you really need it. So we decided to build a model router to handle this for us. The Weave Router acts as an Anthropic/OpenAI endpoint specifically for coding agents. It looks at every inference request and intelligently (more on that in a sec) decides what model to send it to, handling all the translations required alo...