Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

jev _can_ generate text

78,085 görüntüleme • 1 ay önce •via X (Twitter)

36 Yorum

typedfemale profil fotoğrafı
typedfemale1 ay önce

some of these are art

Haoxing Du profil fotoğrafı
Haoxing Du1 ay önce

aww feels like GPT-2 small is back

Wocean Man profil fotoğrafı
Wocean Man1 ay önce

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 ☀️🌲 profil fotoğrafı
RSC ☀️🌲1 ay önce

Building LLMs from first principles

Dennis Aumiller profil fotoğrafı
Dennis Aumiller1 ay önce

We're rediscovering 2019 BERT papers from first principles:

andrew blinn profil fotoğrafı
andrew blinn1 ay önce

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

tender profil fotoğrafı
tender1 ay önce

once there was an ugly barnacle ahh

Eumemic profil fotoğrafı
Eumemic1 ay önce

Are you giving it the entire dictionary as options?

Eumemic profil fotoğrafı
Eumemic1 ay önce

clever

typedfemale profil fotoğrafı
typedfemale1 ay önce

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

Eumemic profil fotoğrafı
Eumemic1 ay önce

Yeah I tried ASCII and it was horrendous lol

Incorrectish profil fotoğrafı
Incorrectish1 ay önce

LLMs from first principles?

Strife profil fotoğrafı
Strife1 ay önce

lmao

AI Psychosis profil fotoğrafı
AI Psychosis1 ay önce

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 profil fotoğrafı
Ambika Sukla1 ay önce

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 profil fotoğrafı
Ege1 ay önce

i hereby tap the sign

Ludvik Koutny profil fotoğrafı
Ludvik Koutny1 ay önce

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

haider profil fotoğrafı
haider1 ay önce

This is poetry

Rohan Arun profil fotoğrafı
Rohan Arun1 ay önce

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

emf profil fotoğrafı
emf1 ay önce

How?

Pillfurd profil fotoğrafı
Pillfurd1 ay önce

love Jev ok

🇪🇬 profil fotoğrafı
🇪🇬1 ay önce

he speaks like trump

JustViewNews profil fotoğrafı
JustViewNews1 ay önce

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

Rasan-al-gaib profil fotoğrafı
Rasan-al-gaib1 ay önce

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

mehul profil fotoğrafı
mehul1 ay önce

this is giving early gpt or even gpt 2

Ahmet Karapinar profil fotoğrafı
Ahmet Karapinar1 ay önce

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

Izem Guendoud profil fotoğrafı
Izem Guendoud1 ay önce

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

Skyler Ji profil fotoğrafı
Skyler Ji1 ay önce

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

Coderman 🇵🇸 profil fotoğrafı
Coderman 🇵🇸1 ay önce

Trained on Donald Trump speeches?

strider profil fotoğrafı
strider1 ay önce

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

Nanne profil fotoğrafı
Nanne1 ay önce

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

Rakib profil fotoğrafı
Rakib1 ay önce

what a horror

0xE  @enol.app profil fotoğrafı
0xE  @enol.app1 ay önce

Doesn't this show how pointless jev is?

@_@ profil fotoğrafı
@_@1 ay önce

hmm. needs work

Nanda profil fotoğrafı
Nanda1 ay önce

It's like making a car sail. Bravo 🍾

w profil fotoğrafı
w1 ay önce

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

Benzer Videolar

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 görüntüleme • 1 ay önce

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 görüntüleme • 1 ay önce