"hype-free explanation of jev:
jev does not replace gpt / claude
jev is just a *really* smart switch statement
like if 2016 ml classifiers got 2026 levels of intelligence
it's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate
* = and by new, i mean rebranded
~~~
it needs a predefined set of options and it will tell you which one to take
it cannot:
- write code
- generate natural language
- reason step by step / show its work
- produce any output you didn't define in advance
- pick from more than ~255 options in one shot
but it can:
- classify, route, score, rank
- give confidence
- pick the right branch, tool, model, or sub-agent
- judge / verify / guardrail an llm's output
- label tons and tons of rows
~~~
i'd imagine a lot of workflows that look like:
llm proposes options → jev decides → code executes
and i see this fitting *really* well with code mode and mcp
~~~
implying this will lead to agi seems incredibly far fetched to me, but i don't want to discount the types of applications that this will make possible"
https://x.com/NathanFlurry/status/2100036101809619314
npub10v…afruw
2026-09-16 13:01:22 UTC
Author Public Key
npub10vap6lgajn4j22rpgrq686vsktzmes7jkj7mavwy4yrdfz3hpsnqxafruwPublished at
2026-09-16 13:01:22 UTCEvent JSON
{
"id": "2a259da773c707167ac9e8ccdd7890d42c578db0d898f4989568b65a5f8711ac",
"pubkey": "7b3a1d7d1d94eb25286140c1a3e990b2c5bcc3d2b4bdbeb1c4a906d48a370c26",
"created_at": 1789563682,
"kind": 1,
"tags": [
[
"client",
"Primal Android"
]
],
"content": "\"hype-free explanation of jev:\n\njev does not replace gpt / claude\n\njev is just a *really* smart switch statement\n\nlike if 2016 ml classifiers got 2026 levels of intelligence\n\nit's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate\n\n* = and by new, i mean rebranded\n\n~~~\n\nit needs a predefined set of options and it will tell you which one to take\n\nit cannot:\n\n- write code\n- generate natural language\n- reason step by step / show its work\n- produce any output you didn't define in advance\n- pick from more than ~255 options in one shot\n\nbut it can:\n\n- classify, route, score, rank\n- give confidence\n- pick the right branch, tool, model, or sub-agent\n- judge / verify / guardrail an llm's output\n- label tons and tons of rows\n\n~~~\n\ni'd imagine a lot of workflows that look like:\n\nllm proposes options → jev decides → code executes\n\nand i see this fitting *really* well with code mode and mcp\n\n~~~\n\nimplying this will lead to agi seems incredibly far fetched to me, but i don't want to discount the types of applications that this will make possible\"\n\nhttps://x.com/NathanFlurry/status/2100036101809619314 \n\n",
"sig": "6d77f9877e1b96d4b37100259c0988f59c757faf62a6ff3e12633fbbbfe5410822159f9adea1c8c5909170a1dcaa58854ee7da46aea7c5598cf8e037d24f8849"
}