Jev’s Paradox

Today’s issue: React Router trims the fat, Aflac for agents, and what framework authors actually think about before they go to sleep.

Welcome to #522.

---

Jev’s Paradox

The internet is verrry exciiite about a new AI model called Jev that was released earlier this week. It’s a frontier model from TypeSafe AI (a company founded by one of the creators of ChatGPT) that is 200x faster and 400x cheaper than other LLMs. The catch: it can’t generate text.

That’s right, Jev is not an LLM. The best way to describe it is that it is a general-purpose classifier. It’s designed for speed, making decisions in parallel instead of generating text token by token. You give it a question, a set of answers, and it gives you the probability that each answer is correct in about 40ms - without the giant wall of text.

Here are some of the patterns that are starting to emerge:

• Speculative Fanout: Ask multiple questions in a single query and get all of them answered in parallel. For example: triage a support ticket and assess its type, severity, frustration level etc.

• Confidence Gated Routing: Jev can generate confidence scores that can be used to route to different actions. If you are highly confident you can take the action directly, or if you have low confidence, you can add a user prompt to clarify.

• Composite Scoring: Give Jev a rubric, and it can give a composite score to all of your criteria. The canonical example here is automated resume screening.

• Intent Routing: Intent is ambiguous, but often the decision tree of how to respond is deterministic. This means Jev can sit in front of complex queries, classify them and route them to the appropriate response.

Bottom line: Developers were tired of the text gods doing everything for them and getting an outrageous bill at the end of the month. So it’s no surprise that Jev appears to be the missing AI primitive that developers actually want to work with.

---

Fewer findings. Only real risks.

AI-generated code can introduce vulnerabilities that are easy to miss in a pull request.

CodeRabbit Security continuously reviews your codebase for complex bugs and security risks, using full-codebase context to follow data flows, dependencies, and patterns beyond the latest diff.

Run CodeRabbit Security on your own repositories today.

---

1. Nub built a phantom dependency detector that finds undeclared deps in popular packages and publishes them in a new @nubjs/extensions package.

2. React Router released version 8.4 featuring more efficient route matching, reduced route re-renders, and reduced team size (bye Ryan and Pedro 🥲).

3. For years, mobile shipped slower than the web. But now agents are writing, testing, shipping, monitoring, and fixing their code using Expo. Try it today. [sponsored]

4. Anthony Fu created Devframe, a framework that lets you BYODT (build your own dev tools).

5. Aflac Turso created their own accident prevention plan so you don’t have to worry about agents dropping your database.

6. Brooks Lybrand is asking the question every framework author asks when they’re alone in bed at night: “do frameworks even matter anymore”?

7. webmcp-react helps modern React websites build WebMCP support so agents can call them directly. Zod-first and Strict Mode safe. [sponsored]

8. Ahmad Shadeed wrote about how to properly align icons with labels using CSS. Everyone with OCD can breathe a sigh of relief.

9. Jacob Kernel is doing the Lord’s work helping developers to stop using double negatives with the cheatsheet for interface design patterns he created.

10. SerpApi lets you scrape 100+ search engines with a single API. One simple GET request gets you real-time results from Google Search, Maps, AI Overviews and more – all as structured JSON. [sponsored]

11. GitHub Copilot, you guessed it, migrated to Rust. It’s tough out there for the TypeScript truthers.

12. Claude finally adopted AGENTS.md… trying to drum up a little goodwill for that IPO?