Assa Abloy has laid off the majority of staff at Level Home, the smart lock company known for building smart tech into traditional-looking deadbolts, and is folding the business into Kwikset, according to a source familiar with the decision. The Verge obtained exclusive details from a person familiar with the restructuring who requested anonymity as […]
Less than 24 hours after news broke that OpenAI would stagger its next model release at the request of the Trump administration, that model, GPT-5.6, is here. On Friday, the company unveiled the limited preview of its new GPT 5.6 model suite: Sol, the flagship; Terra, a medium-tier model for "high-volume work"; and Luna, a […]
Article URL: https://www.ycombinator.com/companies/liva-ai/jobs/gvtc3Ep-founding-operations-lead
Comments URL: https://news.ycombinator.com/item?id=48688961
Points: 0
# Comments: 0
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 along the way. So it can use faster/cheaper models (e.g. DeepSeek v4, GLM 5.2, Kimi K2.6) when possible, and frontier models (Opus 4.8 & GPT 5.5 (& Fable whenever it's back)) when necessary.
How do we know what model to route to? We trained an RL model on tens of thousands (so far!) of agent traces. We reward the routing model when it selects an LLM that successfully completes the given task.
Here's an example: if you ask the router to plan a complex change, it will (probably) route that request to Opus 4.8. Subagents exploring the codebase to gather context will be routed to more suitable models (e.g. DeepSeek V4 Flash). Then when you have the plan ready to implement, it will be (most likely) be handed to a quicker model (e.g. GLM 5.2) to carry it out.
We've been using this internally for the last month or so. We've saved 40% on tokens vs. what we otherwise would have paid, with no noticeable differences in quality or velocity.
The router is source-available under Elastic License 2.0, so you can self-host it. Or if you prefer, you can also use our hosted version: weaverouter.com.
I'll be here to answer any questions you may have!
Comments URL: https://news.ycombinator.com/item?id=48688700
Points: 11
# Comments: 0
The lawsuit was connected to a fatal 2023 crash involving a vehicle using the company's advanced driver assistance system known as Full Self-Driving.
Exposed records from the private group included the personal information of a senior White House intelligence official and an active-duty special operations officer.
TikTok may be working to become the app that people use for most of their digital activities.
Apple just raised prices across its iPad and MacBook lineup. The good news is that many retailers are still selling their inventory at the old prices or far less, which means you can still score some of the best iPad deals we may see in awhile — if ever again. So if you’ve been thinking […]
Join us on the livestream at 1 pm ET and ask questions about the aftermath of New Glenn
AI models have progressed to the point where their capabilities have real political consequences. Dealing with those consequences will require collective action.