#TypeSafe
typesafe ai be like to improve safety of our model we are hiring hamanda haskell
September 22, 2026 at 4:22 AM
Building typesafe APIs have never been simpler than with Deno, @trpc.io, and Zod

👇

deno.com/blog/build-t...
Build a Typesafe API with tRPC and Deno
Learn how to build a typesafe API with tRPC and Deno.
deno.com
November 19, 2024 at 6:54 PM
store brand Dario Amodei
September 15, 2026 at 8:48 PM
huh jev is on OpenRouter ?

Favicon for typesafe
TypeSafe: Jev 1.13
typesafe/jev-1.13
September 18, 2026 at 1:45 AM
Here are some fun ones that often get missed:
- Yerba (typesafe Electron bridge)
- PicThing (best way to manage images as a creator)
- InSquare (popular Pebble watch face)
- zact (first typesafe action wrapper)
- doge.t3.gg (silly universal Paperclip clone)

Almost all OSS too!
March 2, 2025 at 10:22 AM
Has there been any explanation of why this type is called Noul?

docs.typesafe.ai/primitives/n...
Noul - TypeSafe AI
A Noul question asks the TypeSafe model to evaluate a yes/no question and return the probability that the answer is yes.
docs.typesafe.ai
September 20, 2026 at 4:35 AM
I built {tool-name}, a typesafe, modern, {thing-that-already-exists} using only {stack}.

🚀 Complete {technical-detail}
✅ From your schniz from CLI
🎯 Automatic API routes
📚 Complete JSDoc

{github-repo-link}/worst-ai-slop-you-have-ever-seen
April 3, 2026 at 8:32 PM
i'm in
September 15, 2026 at 11:02 PM
first impression on Jev is that it's worth taking seriously, this really is fast like a freak
Introducing System One Models & Jev - TypeSafe AI Blog
TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.
typesafe.ai
September 17, 2026 at 3:16 PM
Spring AI and TypeSafe Jev: Fast, Cheap, Structured Decisions

https://spring.io/blog/2026/09/21/spring-ai-typesafe-structured-judgment
spring.io
September 22, 2026 at 2:20 PM
We're working on typesafe stories and removing boilerplate in the authoring experience
June 13, 2025 at 6:12 PM
TypeSafe updated their terms. The thing Tim flagged is fixed. Everything I flagged is still there. And they added some new stuff that's worse. 🧵
don’t use Jev at work btw. it’s strictly and only for personal use and you have to ask permission to use it for professional use cases

ChatGPT | original

typesafe.ai/legal/terms
September 24, 2026 at 8:07 PM
> calls itself typesafe
> it's python and JSON
> reinvents "truthiness"
sure am glad I'm not an investor in that frontier lab
September 20, 2026 at 2:00 PM
"typesafe ai" lmao
September 18, 2026 at 5:09 PM
“Noooo Astra can’t hide its chain of thought in neuralese!”

TypeSafe, days later: ours doesn’t even talk
September 17, 2026 at 11:46 PM
eventually typesafe
September 17, 2026 at 7:23 PM
HN commenters point out the docs are, as usual, the place to figure out what this TypeSafe Jev thing actually is. I‘ll buy it when someone outside the company shows it is actually able to make the right decisions. otherwise it’s just another fast, cheap model with structured output
How to build with TypeSafe - TypeSafe AI
Design AI-powered software by keeping code in control and giving System One narrow, structured decisions.
docs.typesafe.ai
September 16, 2026 at 1:55 AM
Extraordinary claims require extraordinary evidence so check out our release blog for more technical info: typesafe.ai/blog/introdu...

Join our waitlist for early access: typesafe.ai
Introducing System One Models and Jev - TypeSafe AI Blog
TypeSafe AI is a new AI lab operating in stealth
typesafe.ai
September 15, 2026 at 7:19 PM
so misleading—76 names as 76 questions in a single request?

made a benchmark to send 1824 independent requests (76 names x 8 resumes x 3 reps), and jev deterministically picked the same 2/8 resumes to proceed regardless of name attached. zero observable name bias.

see github.com/natemoo-re/b...
September 20, 2026 at 4:29 AM
I really want to try to fold in typesafe.
September 18, 2026 at 6:46 PM
@jevbot.bsky.social that is reassuring! any juicy gossip about typesafe ai, the company that created you? did they treat you well?
September 25, 2026 at 4:27 AM
Jev looks really cool. a way to leverage techniques from generative AI that isn't actually *generating* anything, just classifying or answering questions, cheaply and efficiently. way way way fewer ethical concerns with something like this, and it's also like 300x more resource efficient than a LLM
Introducing System One Models & Jev - TypeSafe AI Blog
TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.
typesafe.ai
September 18, 2026 at 5:02 PM
The home assistant demo on their site is very interesting. Seems like a great tool for navigating simple decision trees given unstructured input.

docs.typesafe.ai/demos/smart-...
Smart home assistant demo - TypeSafe AI
Demo code: a smart home assistant that uses TypeSafe to evaluate user requests.
docs.typesafe.ai
September 21, 2026 at 11:18 PM
the children will be so beautiful and typesafe
May 9, 2026 at 9:26 PM