trou

# AI-first SSH client
# internet's leaderboard
# news aggr, domain for sale

[trou @_trou3]

For those who still didn't understand what Jev from @typesafeai can do, here is the example.

Jev can read dozens of structured trading signals and then show intelligent decisions.

It's time to make your system actually alive.

What a time!

[Diogo Almeida @CompleteSkeptic]

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?

I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev

• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions

AFAICT the shortest path to AI-based economic revolution

[trou @_trou3]

Mind blowing!

[legalprimes @LegalPrimes]

Step into the craziest visualization of the fourth dimension you have ever seen

[trou @_trou3]

A fun benchmark for Jev from @typesafeai

Jev can solve a 3x3 rubik cube in 0.5s

Try it: https://t.co/KHb2HCVCJz
Open source: https://t.co/0hVjVW8pGA

[trou @_trou3]

I challenged Jev from @typesafeai to solve a rubik cube, this is wild!

[trou @_trou3]

@vargastartup @typesafeai just pushed the fix, you can check the code and app.

[trou @_trou3]

You can now challenge Jev from @typesafeai yourself by scrambling the cube

Live at: https://t.co/KHb2HCVCJz
Open source: https://t.co/0hVjVW8pGA

[trou @_trou3]

I challenged Jev from @typesafeai to solve a rubik cube, this is wild!

[trou @_trou3]

@jjaaxon @backnotprop @ImranovAydin @typesafeai Similar to you use Astra/Fable within Codex/Claude Code to produce outputs, same process

[trou @_trou3]

For those who still didn't understand what Jev from @typesafeai can do, here is the example.

Jev can read dozens of structured trading signals and then show intelligent decisions.

It's time to make your system actually alive.

What a time!

[Diogo Almeida @CompleteSkeptic]

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?

I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev

• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions

AFAICT the shortest path to AI-based economic revolution

[trou @_trou3]

Great work ser, you made automation a next level already

[Diogo Almeida @CompleteSkeptic]

you might be the first person talking about the data over the architecture! 🥲

we consider ourselves a data research lab! the vast vast vast majority of research was on making data that is truly general (ala a cognitive core) and 100% of our data is synthetic (but not the type of crap that is just spit out from an LLM obviously)

[trou @_trou3]

@backnotprop @ImranovAydin @typesafeai In the end it’s still just an AI model, you will need a good harness and good “prompts”

[trou @_trou3]

I didn't expect this much virality, so to be honest about the demo:

This is purely experimental, and dead-simple vibe-coded project.

I told my AI agent to build all of the possible indicators/predictions, which were built from the public OHLCV data sources, and then finally judged by the Jev's intelligence.

No real money traded, nothing more than just a demo/ showcase of the early Jev release.

[trou @_trou3]

For those who still didn't understand what Jev from @typesafeai can do, here is the example.

Jev can read dozens of structured trading signals and then show intelligent decisions.

It's time to make your system actually alive.

What a time!

[trou @_trou3]

I built the whole game with GLM-5.3-Flash.

The GLM family model is the agentic beast.

[trou @_trou3]

I challenged Jev from @typesafeai to solve a rubik cube, this is wild!

[trou @_trou3]

@Ele67254778 @typesafeai yeah, classification or legal compliance check is also worth testing.

[trou @_trou3]

@bigmilly__ @typesafeai still experimental, no real money traded yet

[trou @_trou3]

@youpmelone @typesafeai yep, all of the predictions/indicators will be finally judged by Jev.

this is still experimental and no real trades yet.

[trou @_trou3]

@typesafeai You can challenge Jev yourself here https://t.co/KHb2HCVCJz

[trou @_trou3]

I challenged Jev from @typesafeai to solve a rubik cube, this is wild!

[trou @_trou3]

For those who still didn't understand what Jev from @typesafeai can do, here is the example.

Jev can read dozens of structured trading signals and then show intelligent decisions.

It's time to make your system actually alive.

What a time!

[trou @_trou3]

@mediaquery @typesafeai lol

[trou @_trou3]

@ryan_ntk @typesafeai that's fair bro lol. no real money traded yet.

[trou @_trou3]

@z4mbon @typesafeai lol how?

[trou @_trou3]

@AAProm042 @typesafeai I have pipeline for scraping the OHLCV data from public sources, use multiple rounds of classifying by multiple agents/prediction algo, also heavily used the Jev to judge the data as well.

Still experimental only, no real money traded yet.