TypeSafe AI

An AI lab building intelligence beyond chat.

[TypeSafe AI @typesafeai]

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. 🚨

[TypeSafe AI @typesafeai]

jevbot's the realest one on slack

[Nathan LeClaire @dotpem]

little known fact jev is from oakland actually

[TypeSafe AI @typesafeai]

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

Jev gives you those evenings back

https://t.co/I5zLgbgp3k

[Eugene Shvarts @mathfax]

Never read an Airbnb listing again. Tell Jev what you want in plain English, and it reads 1,000 Cape Town listings and hands you the 10 best, scored out of 10, in about a second. Right inside Google Sheets 🏠

(trying something new with our demos!)

[Kunal Abichandani @kunalabcdani]

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!

[Nick Shirobokov @nicksherrow]

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 @typesafeai]

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

[Product Hunt 😸 @ProductHunt]

Hypership is BACK for our 13th birthday!!

Celebrate with us by requesting features and reporting bugs on the launches featured on today's leaderboard.

To those who ship, you have a chance to win credits from @typesafeai and @supabase! Makers, how fast can you get features to prod?

[TypeSafe AI @typesafeai]

now you have no more excuses, it ain't a decision model

https://t.co/DANkB0WLJU

[TypeSafe AI @typesafeai]

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

[Allie the Icon @allietheicon]

Why don't we at TypeSafe call Jev a decision model?

If you think of Jev's questions as making *decisions*, I believe you'll use it at the wrong layer of abstraction and your reliability will suffer.

I wrote all about this on our site 🧵👇

[TypeSafe AI @typesafeai]

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

[TypeSafe AI @typesafeai]

what did they mean by this

[Kevin Zhang @notkevinzhang]

Straight to onsite. I have to know.

[TypeSafe AI @typesafeai]

build it fast. build the right thing.

HYPERSHIP on @ProductHunt, this friday.

[Product Hunt 😸 @ProductHunt]

Two days to get yourself onto the HYPERSHIP board.

@supabase and @typesafeai are both back with credits, and the day runs on you launching, taking the requests that land and shipping them before midnight.

[Allie the Icon @allietheicon]

One thing that can be tricky to figure out is how to use Jev's primitives to handle more than one intent in a single user query.

My favorite way to approach this is what I call the "shopping cart" pattern: recursively pick the next thing until Jev says we're done.

I've personally used this to make a coffee ordering bot for our company Slack (using @DoorDash's CLI!), as well as a fast multi-intent handler for my smart home system.

Give it a shot!

[Harry Stebbings @HarryStebbings]

Why Jev epitomizes what a great brand is today

“Everyone wants to clone Jev. No one wants to get up on stage, wear a fucking pink fur coat and talk about the Jevolution in an unhinged way.

That is what brand is to me.

That guy is playing the game on a whole different level. Companies today have to think about that.” @bernhardsson

Love to hear your thoughts @CompleteSkeptic @sonyatweetybird @davegerhardt

[TypeSafe AI @typesafeai]

get those creative juices flowing
https://t.co/OQ1PveAhFX

[TypeSafe AI @typesafeai]

where to use Jev? Jeverywhere!

(missed opportunity)

but seriously we've barely begun exploring the space of possible smart software and y'all are thinking small?

[Allie the Icon @allietheicon]

Having built many dozens of Jev-powered projects and demos over the past few months, I can say with confidence my #1 advice for how to use Jev is:

Just put Jev everywhere.

Every time I think of a new (not Jev specific) project, I think to myself "what could Jev do in this system to make it cooler/smarter/weirder/sillier/whateverer" and then I do it.

The objective is not to use it in places where it makes total sense. The objective is to continue to expand my mind to see Jev the way our long term vision has always been: as an enabler of a new kind of smart software. The more you train your brain to truly think of Jev as smart primitives that can slot in to code in anywhere a primitive could live, the more you find novel use-cases.

Don't stop building. Don't stop playing. Experiment forever and ever and have fun with it!

[TypeSafe AI @typesafeai]

can you smell that?

it's thousands of developers pushing to prod on a friday like god intended, thanks to @ProductHunt

we'll be seeing you november 6

[Product Hunt 😸 @ProductHunt]

HYPERSHIP day returns Nov 6, with @typesafeai and @supabase putting more credits on the line!

Submit your launch, and build and ship features in real-time as the requests land to earn extra points.

Last time around, over 8,000 points were awarded 👀

[Allie the Icon @allietheicon]

Are you at @githubuniverse this week? Be sure to catch my session "Jev: Shipping a category-creator" where I'll talk all about the journey of bringing Jev to market from the DevRel perspective.

Thursday @ 1:15pm!

https://t.co/LNL9Qx1z2d

[Shengkun Ye @shengkunye]

Introducing Jev @typesafeai powered people search

$0.0024/lead. No more $2,000 subscriptions.

Your agents can now:

> Waterfall across Apollo, Clay, People Data Labs, Hunter, ContactOut, Ploid
> Run 1,000 leads through Jev
> Pay for enrichment only on the leads Jev kept

Open source. No subscriptions. 0% markup.

[TypeSafe AI @typesafeai]

they say @CompleteSkeptic is getting everyone in the office a pigeon chair

[Ramin Nasibov @RaminNasibov]

pigeon chair

[Allie the Icon @allietheicon]

In a Discord town hall a few weeks back, I talked about Intelliprompter: my first-ever AI-integrated personal project.

I had shelved it due to LLM costs, but revived it the day I first learned about Jev.

We now have a Cookbook up on our docs showing how to make your own! 🔗 ➡ 🧵

[TypeSafe AI @typesafeai]

@allietheicon today's is one of our old favorites
https://t.co/NPqjB1U0Lx

[TypeSafe AI @typesafeai]

you too can learn to Jev the way @allietheicon Jevs!

new cookbooks hot & fresh every week.

[Allie the Icon @allietheicon]

One of my favorite Jev patterns is "line-by-line search", where you put an entire document in state, and ask a question for each line (or paragraph). This is super useful when you want to find the most relevant line for a query.

Use nouls when you expect one dominate answer, use scores when you want to highlight lines by overall relevance. The former is good for answering a specific question while the latter is good for finding all relevant passages.