Загрузка видео...

Не удалось загрузить видео

На главную

jev _can_ generate text

78,085 просмотров • 1 месяц назад •via X (Twitter)

Комментарии: 36

Фото профиля typedfemale
typedfemale1 месяц назад

some of these are art

Фото профиля Haoxing Du
Haoxing Du1 месяц назад

aww feels like GPT-2 small is back

Фото профиля Wocean Man
Wocean Man1 месяц назад

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.

Фото профиля RSC ☀️🌲
RSC ☀️🌲1 месяц назад

Building LLMs from first principles

Фото профиля Dennis Aumiller
Dennis Aumiller1 месяц назад

We're rediscovering 2019 BERT papers from first principles:

Фото профиля andrew blinn
andrew blinn1 месяц назад

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

Фото профиля tender
tender1 месяц назад

once there was an ugly barnacle ahh

Фото профиля Eumemic
Eumemic1 месяц назад

Are you giving it the entire dictionary as options?

Фото профиля Eumemic
Eumemic1 месяц назад

clever

Фото профиля typedfemale
typedfemale1 месяц назад

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

Фото профиля Eumemic
Eumemic1 месяц назад

Yeah I tried ASCII and it was horrendous lol

Фото профиля Incorrectish
Incorrectish1 месяц назад

LLMs from first principles?

Фото профиля Strife
Strife1 месяц назад

lmao

Фото профиля AI Psychosis
AI Psychosis1 месяц назад

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

Фото профиля Ambika Sukla
Ambika Sukla1 месяц назад

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.

Фото профиля Ege
Ege1 месяц назад

i hereby tap the sign

Фото профиля Ludvik Koutny
Ludvik Koutny1 месяц назад

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

Фото профиля haider
haider1 месяц назад

This is poetry

Фото профиля Rohan Arun
Rohan Arun1 месяц назад

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

Фото профиля emf
emf1 месяц назад

How?

Фото профиля Pillfurd
Pillfurd1 месяц назад

love Jev ok

Фото профиля 🇪🇬
🇪🇬1 месяц назад

he speaks like trump

Фото профиля JustViewNews
JustViewNews1 месяц назад

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

Фото профиля Rasan-al-gaib
Rasan-al-gaib1 месяц назад

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

Фото профиля mehul
mehul1 месяц назад

this is giving early gpt or even gpt 2

Фото профиля Ahmet Karapinar
Ahmet Karapinar1 месяц назад

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

Фото профиля Izem Guendoud
Izem Guendoud1 месяц назад

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

Фото профиля Skyler Ji
Skyler Ji1 месяц назад

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

Фото профиля Coderman 🇵🇸
Coderman 🇵🇸1 месяц назад

Trained on Donald Trump speeches?

Фото профиля strider
strider1 месяц назад

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

Фото профиля Nanne
Nanne1 месяц назад

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

Фото профиля Rakib
Rakib1 месяц назад

what a horror

Фото профиля 0xE  @enol.app
0xE  @enol.app1 месяц назад

Doesn't this show how pointless jev is?

Фото профиля @_@
@_@1 месяц назад

hmm. needs work

Фото профиля Nanda
Nanda1 месяц назад

It's like making a car sail. Bravo 🍾

Фото профиля w
w1 месяц назад

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

Похожие видео

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 просмотров • 1 месяц назад

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 просмотров • 1 месяц назад