Loading video...

Video Failed to Load

Go Home

jev _can_ generate text

78,085 views • 1 month ago •via X (Twitter)

36 Comments

typedfemale's profile picture
typedfemale1 month ago

some of these are art

Haoxing Du's profile picture
Haoxing Du1 month ago

aww feels like GPT-2 small is back

Wocean Man's profile picture
Wocean Man1 month ago

omg you should cut text into small packets called tokens, and have a big array where every index represents a possible token, and then jev takes some text in and ranks the most likely next tokens in a token stream. could be revolutionary.

RSC ☀️🌲's profile picture
RSC ☀️🌲1 month ago

Building LLMs from first principles

Dennis Aumiller's profile picture
Dennis Aumiller1 month ago

We're rediscovering 2019 BERT papers from first principles:

andrew blinn's profile picture
andrew blinn1 month ago

this is not real text. only language models have the intentionality to generate real text. these are just sparkling stochastic enums

tender's profile picture
tender1 month ago

once there was an ugly barnacle ahh

Eumemic's profile picture
Eumemic1 month ago

Are you giving it the entire dictionary as options?

Eumemic's profile picture
Eumemic1 month ago

clever

typedfemale's profile picture
typedfemale1 month ago

i had claude try a few different methods (character does work, nor does token because the 256 limit)

Eumemic's profile picture
Eumemic1 month ago

Yeah I tried ASCII and it was horrendous lol

Incorrectish's profile picture
Incorrectish1 month ago

LLMs from first principles?

Strife's profile picture
Strife1 month ago

lmao

AI Psychosis's profile picture
AI Psychosis1 month ago

The only way I could do that was if you had to do a lot more work and then you would be done by yourself I would say I could get Twitter

Ambika Sukla's profile picture
Ambika Sukla1 month ago

Really surprised with the response about Jev which simply brings back how lms were built and trained with tasks - the very days. It really show how little everyone knows about the history of lms.

Ege's profile picture
Ege1 month ago

i hereby tap the sign

Ludvik Koutny's profile picture
Ludvik Koutny1 month ago

It sounds like Trump's brain is running on Jev :D

haider's profile picture
haider1 month ago

This is poetry

Rohan Arun's profile picture
Rohan Arun1 month ago

Cool I created a similar autocomplete the actually accelerates writing based on your past 1000 sentences

emf's profile picture
emf1 month ago

How?

Pillfurd's profile picture
Pillfurd1 month ago

love Jev ok

🇪🇬's profile picture
🇪🇬1 month ago

he speaks like trump

JustViewNews's profile picture
JustViewNews1 month ago

Only 255 words per request 😂. It is caveman speech.

Rasan-al-gaib's profile picture
Rasan-al-gaib1 month ago

people rediscovering that there can be usecases for transformers other than llms will always be funny to me.

mehul's profile picture
mehul1 month ago

this is giving early gpt or even gpt 2

Ahmet Karapinar's profile picture
Ahmet Karapinar1 month ago

@zacharynado tried character doesn’t work and with words you are only limited to the typesafeai’s max choice which is 255

Izem Guendoud's profile picture
Izem Guendoud1 month ago

pretty slow but it’s excellent as a reasoning layer for llm’s.

Skyler Ji's profile picture
Skyler Ji1 month ago

Pressing the middle option for autocomplete on your keyboard will do the same thing

Coderman 🇵🇸's profile picture
Coderman 🇵🇸1 month ago

Trained on Donald Trump speeches?

strider's profile picture
strider1 month ago

this jev is from derek zoolander center for llms who can't read good

Nanne's profile picture
Nanne1 month ago

1. Jev doesn't support input caching yet. 2. Better to give Jev a 'llm_text' option for switching to real LLM.

Rakib's profile picture
Rakib1 month ago

what a horror

0xE  @enol.app's profile picture
0xE  @enol.app1 month ago

Doesn't this show how pointless jev is?

@_@'s profile picture
@_@1 month ago

hmm. needs work

Nanda's profile picture
Nanda1 month ago

It's like making a car sail. Bravo 🍾

w's profile picture
w1 month ago

that output text is giving me some dejavu.......

Related Videos

Jev has been exploding across GitHub since launch, here's what people have already built with it if you have API access and don't know where to start, copy this: jev-trader - real trading bot placing live limit orders on Monad every 300ms block, judged by Jev alone. 1,911 stars jev-ultrafast - browser agent that picks every click itself, only calling a text model when it actually needs to type something. 16,758 stars jev-doom-agent - real Chocolate Doom compiled to WebAssembly, two engines running the same map, Jev picking the tactical macro every frame jev-t-rex-runner - the Chrome dinosaur game you've procrastinated with a hundred times, now played entirely by Jev picking jump, duck, or keep running typesafe-chess - Jev vs a real search engine, two games, colors swapped. the search won both, but overruled Jev's first instinct on roughly half the moves jev-drone - a simulated quadrotor clears a five-station obstacle course by camera alone, Jev judging the situation twice a second tax-doc-classifier - sorts real IRS tax forms with 100% strict accuracy across 261 forms, at roughly $0.001 a page killmyidea - describe your startup idea, Jev scores it from every angle, then hands back kill, fix, or ship jev-curate - streams Parquet and JSONL rows through typed judgments at 1,500+ rows a second, keeping only what clears the bar pg-jev - a PostgreSQL extension that lets you ask your own database tables plain-English questions and get a real answer back none of these ten generate a single word of text. every one of them returns a number against an answer someone already defined full setup below, then run the three-question test from the article before you build an eleventh

Ryven

281,283 views • 1 month ago

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren't sure how to start experimenting with it, just copy this checklist: 1. jev-ultrafast Browser Use's fastest agent. Jev decides the next action and which element to click, and a language model is only called when text has to be typed. 2. typesafe-mario Jev plays Super Mario Bros. from structured emulator state, choosing every action from features pulled out of the game. 3. jev-plays-pokemon Reads Pokémon Red's game state as text, answers typed questions each turn, and lets plain code turn the answers into moves. 4. jev-drone A camera-only autonomous drone in MuJoCo with a Jev judgment model sitting in the control loop at 2.5 Hz. 5. robo-harness A real SO-101 robot arm workbench where Jev picks bounded joint steps from typed candidate actions under a spend budget. 6. fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions, scoring every tool call for whether it is still needed. 7. jev-claude Routes Claude Code's own judgment calls through Jev: typed choices with probabilities at plan approval, on questions, and before risky commands. 8. is-malicious Supply-chain check before you run anything: Jev Noul checks over source and build files, returning the implicated files and lines. 9. sqlite-jev Jev inside SQL. Noul, Choice and Score judgments exposed as SQLite functions, with confidence on every row. 10. jevinci Paints images by having Jev predict every pixel's colour in parallel, with confidence deciding how wide each stroke is drawn. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

Hanako

29,894 views • 1 month ago