Suat Tuncer

[Suat Tuncer @KozanSuat]

@anil_ozturkk @a_erdem4 https://t.co/EodqpVeJSI

[Paarangat @paarangatrai]

this is the easiest way to understand Jev:

LLMs generate answers.

Jev makes decisions.

that sounds like a small difference, but it actually changes the entire use case.

say you give a normal LLM this:

“here’s a user, their account history, payment behavior, support chats, device data, etc.

tell me if this looks risky.”

the LLM might reason through it and return:

“yes, this looks high risk.”

maybe in JSON if you ask nicely.

with Jev, you define the possible decisions upfront:

risk:

* low
* medium
* high

manual review:

* yes
* no

and Jev returns something closer to:

risk = high (96%)
manual review = yes (91%)

that’s basically the product.

it’s not trying to be another ChatGPT.

it’s more like an AI-native if statement.

instead of:

if transaction > $10,000:
review()

you can start thinking more like:

if “does this behavior look suspicious?” > 95%:
review()

and that opens up a pretty interesting category of software.

a few assumptions I had at first that turned out to be wrong:

1. “so it’s just a classifier?”

kind of, but that undersells it.

the input can be messy real-world context, and you can ask multiple typed questions about that state at once.

fraud?
churn?
escalate?
eligible?
priority?

all from the same input.

2. “so it replaces GPT / Claude?”

not really.

I actually think the interesting architecture is:

Jev decides WHAT needs to happen

Claude / GPT reason or generate WHEN deeper intelligence is needed

normal code executes the deterministic stuff.

Jev becomes the routing layer.

3. “it can’t hallucinate?”

this one needs nuance.

if your allowed answers are:

LOW
MEDIUM
HIGH

Jev won’t suddenly invent:

“EXTREMELY HIGH 🚨”

the output structure is constrained.

but it can still be wrong.

HIGH at 92% can still be the wrong decision.

so “no hallucinations” doesn’t mean “always correct.”

4. “why not just force an LLM to return JSON?”

you can.

we already do this everywhere.

but you still deal with generation latency, schema validation, retries, weird outputs, confidence estimation and a lot of glue code.

Jev is designed around the decision itself rather than text generation.

5. “why should I care?”

because most software is ultimately a giant tree of:

if this → do that
if this → route here
if this → escalate
if this → reject
if this → ask a human

Jev is basically asking:

what if those if statements could understand messy human context?

that’s a much more interesting framing than “another AI model.”

I can see this being very useful for:

fraud / risk
support routing
moderation
PR / QA automation
lead scoring
compliance
workflow orchestration
agent routing

especially as the cheap + fast decision layer sitting in front of larger reasoning models.

early tech, obviously.

but the category itself makes a lot of sense.

[Suat Tuncer @KozanSuat]

@Jasons_JaysHub Ahh be kardeşim. Hadi bize babadan dededen miras kaldı. Sen niye yaktin kendini

[Suat Tuncer @KozanSuat]

@grkn Ilya da show yapıyor o zaman abi. Hinton da aynı. Bu tarz şeyler söyleyen herkes showman diyebilir miyiz?

[Suat Tuncer @KozanSuat]

@vahsiminimalizm https://t.co/qAz40HdUWg

[Jacob Coxon @hilbertspaess]

The people building AI earnestly believe that it could kill us all by the end of the decade. This is not a marketing stunt. If anything, many executives and senior researchers will couch their phrasing in the press to sound sensible - but I hear the same people express fear privately. No other human activity poses this level of danger.

[Suat Tuncer @KozanSuat]

@niolataa @evrimagaci Çozume 1 milyon dolar vermeleri ve hak ettikleri reputationi alamamaları haricinde sorun yok

[Suat Tuncer @KozanSuat]

@icesur Türkiye pahalı olum, niye anlamak istemiyorsunuz?

[Suat Tuncer @KozanSuat]

@AprilVontier @arcprize Came here to write this, ty.

[Suat Tuncer @KozanSuat]

@OzgurTastan Tutuklayin olum, alin ifadesini, üniversiteli cocuklari, komiklik yapan cocuklari aliyorsunuz. En içime sinmeyen proje 15 Temmuz diyen bin Ali yi de alin mesela. Biz ne yapalım?

[Suat Tuncer @KozanSuat]

@Avussos @bosunatiklama Olum siz hasta misiniz ya? Sahilde denize girecek yer yok her yer özel işletme. 8-10 bin liraya hem spor hem keyif yapan insanlara mı takildin? Bizden adam olmaz gerçekten

[Suat Tuncer @KozanSuat]

@siyahsancakx Lan essek twitter ahalisi, uber çagirinca ikisi de birbirlerinin isimlerini görüyor. Kurgu bu

[Suat Tuncer @KozanSuat]

@shentific Belediyelere ya da polis teşkilatına ücretsiz versek kullanirlar mı?

[Suat Tuncer @KozanSuat]

@adrianmutu86 @zgr85997103 @CihanaNizam13 1 saniye sonra bir şey yapacağım. Yazilmis yani anladın mı bunu? Heh. Allah bunu biliyor. Yapmama şansım var mı artık? Şu basit mantığı bile kuramayan senin gibi bir sürü var işte. Açta bir iki bir şey oku. Hatta bak ducane hoca çok iyidir

[Suat Tuncer @KozanSuat]

@yunuspaksoy Yaz yerine kışa sabitlemek daha iyi değil mi?

[Burak Kaan Köse @TrayhopeR]

NATO meets Turkish dark humor.

[Suat Tuncer @KozanSuat]

@Lara_Su2008 @Brk59895639 @SportsDigitale Bizim ülkemizde ironi içeren şeyler niye anlaşılmıyor

[Suat Tuncer @KozanSuat]

@inal_____ @aashafe @Mazi_Chinonso1 Essek inal,adam metoforu kastetmiş zaten. Adama niye sovuyorsun. Üstte de rahipler islami kötü göstermek için niye yalan söylüyor diyor

[Suat Tuncer @KozanSuat]

@thejokernba Lan Houston da bok gibi yer, austin, LA, ny falan olsa anlarim da Houston ne ya?

[Suat Tuncer @KozanSuat]

@MehmetakifGm10 @SpaceCityAdam Kardeşim adam güzel bir ironi yapmış Alperen’i övmek için. Sen niye celallendin?

[Suat Tuncer @KozanSuat]

@Stunna999_ Who took us here from 3-0.Ohh, udoka? Or reed? Or kd? You know the answer

[Suat Tuncer @KozanSuat]

@multistanforfun @yenidenclaus @Globalstats11 Senin olmayan beynini sikiyim