Ankit

Builder, Product Person, Love trying out new tech!

[Justin Schroeder @jpschroeder]

I’ve put a ton of tokens through Jev now, and...I have thoughts.

1. The big labs lost the script

TypeSafe’s intro video says, “We’re building prod, not God” — and can I just say? Hell yeah. @typesafeai built something for engineers like me, so I can build products for people like your mom (she says hi btw). They’re not trying to create “Machines of Loving Grace”; they’re trying to build things that let OTHER HUMAN BEINGS create new types of products.

The proof is in the pudding. When ChatGPT shipped, we were all blown away by…ChatGPT. When Jev shipped, we were all blown away by what everyone was making with it.

I cannot tell you how refreshing this is. It takes a sincere form of humility to believe that you, the creator of a technology, will not be the best at deploying the technology into the marketplace. The big labs, especially Anthropic, have proven not to have this humility…and now everyone hates AI. Thanks, Dario.

I guess what I’m saying is: Diogo for president.

2. Ultra-smart classifiers were genuinely a missing primitive.

I don’t know how this got missed. Diogo calls it “machine-native intelligence,” and that’s really what it is. I cannot tell you how much bending and twisting I've had to do with LLMs to get them to act like a classifier when they just weren’t. I’m absolutely shocked this is the first time this “type” of model has come to market.

These models will unlock AI utility for entire industries: robotics, trucking, aviation, meteorology, finance, defense, retail…even your smart coffee mug is going to use this.

3. It’s still too expensive

Jev is really, really cheap compared to LLMs. But you don’t use it like an LLM. In my full self-driving example, or any robotics example, you’ll be making decisions several times per second continuously. The #1 value proposition of a model like this is speed and cost.

To be clear, at current pricing, the model will still be successful and well integrated. It will be able to replace a number of tasks that were already being performed (poorly) by LLMs. However, to unlock industrial-scale demand (Jevons paradox), I believe it needs to be roughly 10x cheaper.

Currently, Jev is $0.042/M input, which is actually 7x more expensive than a cache read on DeepSeek V4.1 Flash ($0.006). If our industrial application requires decisions at 10 Hz and we provide only 10k of context, that would cost $0.0042/second to operate, or $15/hour, $600/week, etc.

The good news is Diogo said on a recent AMA that they have substantial margin at their current pricing and have already considered dropping the cost further. I hope it's a lot further.

4. Latency is a real limiter

I really hope TypeSafe AI works with an edge network provider to improve the co-location of models and reduce network latency. Ultimately, these models really need to run on-device. I would even be willing to pay some kind of recurring license fee to have a great closed model running on my own hardware, just so I can reduce the TTD (Time To Decision) as much as possible. Imagine running a model like this at 60 Hz, or even 120 Hz.

At that point, we’re looking at a new kind of logic gate — we can’t even imagine what that will be like.

In summary, this one really is a game changer for everyone building AI products, and, assuming cost and latency are further improved…it’ll be a game changer for everyone doing anything.

[Diogo Almeida @CompleteSkeptic]

unironically huge yes!
make AI a background technology
make software fun and powerful

[Diogo Almeida @CompleteSkeptic]

@digitalshane_ yes!!! the analogy we use is like logic gates. look at how many incredible things were made from just a few dumb primitives. IMAGINE that with smart primitives!

[Shane @digitalshane_]

Simply put, Jev is a new form of compute.

Most just have not awoken to this realization.

[Ankit @ItsAnkitAg]

Finally got access to Jev and spent my friday evening hacking a tiny 10-K analyzer.

Drop in a ticker → pull the SEC filing → Jev checks demand, supply, pricing, capex, competition + risk.

Tried AAPL first. kinda wild how fast this went from idea to working.

Disclaimer: Not financial advice, just a faster way to figure out what’s worth reading in a filing.

[Ankit @ItsAnkitAg]

When Does Your AI Need a Supervisor?
https://t.co/5pO0FpRR6z

[Moritz Kremb @moritzkremb]

Full Jev Tutorial

What it is, how you can build with it and what new applications it can unlock

→ 0:00 Intro
→ 0:34 Jev explained
→ 4:06 API setup
→ 5:59 Demo 1: Voice-controlled browser
→ 11:33 Demo 2: AI memory
→ 17:27 Demo 3: YouTube predictor

[tamara @tamarajtran]

found the perfect use case for @typesafeai Jev:

instant compaction

in 2026, why is compaction still a summarization prompt?

Jev can make it instant by scoring every tool call and dropping what’s irrelevant

[Diogo Almeida @CompleteSkeptic]

YES! internally called this use case "dark data": leftovers from the big data era when everyone expected value from this data but couldn't get it out... when the price of intelligence drops, all of a sudden, you can analyze so much more!

[Ipsita Praharaj @ipsita_praharaj]

I am guessing a new type search will emerge

- Planner + router + tool calls + evals - @typesafeai
- Summarization - @claudeai

[TypeSafe AI @typesafeai]

Check your emails! We just let off a huge batch of people from the Jev waitlist. Getting as many people off waitlist today as possible.

[Z.ai for Startups @ZaiforStartups]

The model optimizes the system; the system runs the model.

[Ankit @ItsAnkitAg]

@PratapRohit Did you figure out a way to book H1B emergency appointment? I am in the same boat, Emergency request is approved, but getting the same error message.. would appreciate your reply

[zaкovsкa @sanjazakovska]

Devs watching QA test the product

[Thomas Sowell Quotes @ThomasSowell]

People who enjoy meetings should not be in charge of anything.

[GHA Technologies @GHATechnologies]

.@HPE white paper demonstrates benefits of AI-powered data storage. Download "Can Machine Learning Prevent Application Downtime?" brought to you by GHA Technologies, Inc., to learn the answer to infrastructure bottlenecks. #HPEInfoSight https://t.co/0EUN3H81Ub

[Stephane Bureau @SBUCloud]

Introducing cross-stack analytics for #Microsoft Hyper-V thanks to #HPEInfosight : learn more at https://t.co/V1Kpv4kr7j

#HPE #HyperV @hypervserver @SCAutomation @hyperv_r2 @JamesvandenBerg @DmitriyDolgii #Virtualization #WindowsServer #DataAnalytics

[Tarek Fatah @TarekFatah]

If only this innocence grew with us as we age...

[Ankit @ItsAnkitAg]

How are you embracing AI to simplify your infrastructure?

#AI #mlearning #datacenter #infrastructure https://t.co/l5xCJxI5At

[Ankit @ItsAnkitAg]

HPE InfoSight unveils new must-have features for effective AI infrastructure.

https://t.co/bqZ6Yu7Bqp
#AI #ML #datacenter #InfoSight #infrastructure https://t.co/nLrKay12E0