←
TypeSafe AI245 posts
TypeSafe AI avatar✓

TypeSafe AI ✓

@typesafeai

An AI lab building intelligence beyond chat.

◷ Joined January 2026▧ 45 Photos and videos
TypeSafe AI avatar
TypeSafe AI@typesafeai·Oct 15

we announced Jev 1.14 on 10.14 at 1:14pm PT 🔥 a new and improved model, along with experimental features for our dreamers: • images • a new box type • longer context surprise, Jev was already able to see you! 👁️ BUT our bar for production-grade intelligence is quite high, so builders beware, these are preview features. enter the ~*~ danger zone ~*~ at your own risk. 🚨

Post attachment
Diogo Almeida avatar
⟳ TypeSafe AI retweeted
Diogo Almeida@CompleteSkeptic·Nov 12

AWESOME work showing the importance of calibration for real applied AI (my favorite photo attached)

Post attachment
Lightpanda avatar
⟳ TypeSafe AI retweeted
Lightpanda@lightpanda_io·Nov 16

Lightpanda + Jev @typesafeai How it started: > Could Jev handle the page checks we were sending to chat models? How it’s going: > Built into the Lightpanda binary: triage, cookie walls and logins in ~0.2s What’s next: > Chat model sets the goal, Lightpanda + Jev paginate and extract lightpanda.io/blog/posts/lig…

TypeSafe AI avatar
TypeSafe AI@typesafeai·Nov 16

how to Jev • you pay for the `state` part of your request once, no matter how many questions you ask about it • so it's usually cheaper to ask every question you might want answered, even before you know if you need the answer • then use code to sort it out take in all the information you might need, and filter down to what's important! reliable automation means covering all your bases

AI/ML API avatar
⟳ TypeSafe AI retweeted
AI/ML API@aimlapi·Nov 3

We killed $349/mo Semrush+Ahrefs💥 Run a SEO-optimized campaign in one prompt for just $0.61! With aimlapi.com/mcp your agent can: 1. Analyze your website and competitors’ ads 2. Score 10k+ keywords with @TypesafeAI’s Jev 3. Create, set up and launch the Google Ads campaign 0% markup. No subscriptions. No extra signups. First 100 commenters will get a $10 promo code to try it! Give your agent this prompt: “Connect aimlapi.com/mcp and build a Google Ads campaign for my company: yourwebsite.com”

0:53
TypeSafe AI avatar
TypeSafe AI@typesafeai·Nov 13

blurry photo in the field? Jev makes a snap judgment to find out. @elise_ai clocked Jev at 94ms a photo: ~30x faster than Sol, with ~50x as many judgments for the same cost

Justin Skycak avatar
⟳ TypeSafe AI retweeted
Justin Skycak@justinskycak·Nov 13

Never underestimate how much time and effort you can waste by trying to automate a process you do not understand manually.

TypeSafe AI avatar
TypeSafe AI@typesafeai·Nov 13

jevbot's the realest one on slack

0:34
TypeSafe AI avatar
TypeSafe AI@typesafeai·Nov 12

was the most expensive part of your last vacation rental the four evenings you spent picking it? Jev gives you those evenings back

Kunal Abichandani avatar
⟳ TypeSafe AI retweeted
Kunal Abichandani@kunalabcdani·Nov 9

What if we could manipulate UI at the speed of thought? Built this voice coffee ordering system with @typesafeai Jev. The drink and any updates show up while I’m still mid-sentence, ~200 ms from word to screen. Feels pretty magical!

0:34
Nick Shirobokov avatar
⟳ TypeSafe AI retweeted
Nick Shirobokov@nicksherrow·Nov 7

Can't stop thinking how much stuff Jev is doing to save AI engineers asses from stupid systems design patterns while the rest of the domain keeps pushing tool calling loops everywhere

TypeSafe AI avatar
TypeSafe AI@typesafeai·Nov 6

oh so everybody vibecoding their own app is easy now? just a slop cannon away from everything you want in life? prove it! hypership your dreams into reality today

0:13
TypeSafe AI avatar
TypeSafe AI@typesafeai·Nov 6

you can smuggle your semantic logic in string caveats, embedding vectors, and all the complicated ML you want, but data distributions will always be far more ridiculous than you can be clever so: • be clear about what you need to know • be clear that a plain reading of your data is enough to know and you're ready to make reliable decisions! that's System One for you

Post attachment
TypeSafe AI avatar
TypeSafe AI@typesafeai·Nov 6

so we heard you like decision models but how do you make reliable decisions against gnarly data with a model? you don't: reliability requires code, and so reliable decisions are made by composing reliable judgments in code Jev makes reliable judgments