Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

jev _can_ generate text

78,085 Aufrufe • vor 1 Monat •via X (Twitter)

36 Kommentare

Profilbild von typedfemale
typedfemalevor 1 Monat

some of these are art

Profilbild von Haoxing Du
Haoxing Duvor 1 Monat

aww feels like GPT-2 small is back

Profilbild von Wocean Man
Wocean Manvor 1 Monat

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.

Profilbild von RSC ☀️🌲
RSC ☀️🌲vor 1 Monat

Building LLMs from first principles

Profilbild von Dennis Aumiller
Dennis Aumillervor 1 Monat

We're rediscovering 2019 BERT papers from first principles:

Profilbild von andrew blinn
andrew blinnvor 1 Monat

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

Profilbild von tender
tendervor 1 Monat

once there was an ugly barnacle ahh

Profilbild von Eumemic
Eumemicvor 1 Monat

Are you giving it the entire dictionary as options?

Profilbild von Eumemic
Eumemicvor 1 Monat

clever

Profilbild von typedfemale
typedfemalevor 1 Monat

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

Profilbild von Eumemic
Eumemicvor 1 Monat

Yeah I tried ASCII and it was horrendous lol

Profilbild von Incorrectish
Incorrectishvor 1 Monat

LLMs from first principles?

Profilbild von Strife
Strifevor 1 Monat

lmao

Profilbild von AI Psychosis
AI Psychosisvor 1 Monat

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

Profilbild von Ambika Sukla
Ambika Suklavor 1 Monat

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.

Profilbild von Ege
Egevor 1 Monat

i hereby tap the sign

Profilbild von Ludvik Koutny
Ludvik Koutnyvor 1 Monat

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

Profilbild von haider
haidervor 1 Monat

This is poetry

Profilbild von Rohan Arun
Rohan Arunvor 1 Monat

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

Profilbild von emf
emfvor 1 Monat

How?

Profilbild von Pillfurd
Pillfurdvor 1 Monat

love Jev ok

Profilbild von 🇪🇬
🇪🇬vor 1 Monat

he speaks like trump

Profilbild von JustViewNews
JustViewNewsvor 1 Monat

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

Profilbild von Rasan-al-gaib
Rasan-al-gaibvor 1 Monat

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

Profilbild von mehul
mehulvor 1 Monat

this is giving early gpt or even gpt 2

Profilbild von Ahmet Karapinar
Ahmet Karapinarvor 1 Monat

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

Profilbild von Izem Guendoud
Izem Guendoudvor 1 Monat

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

Profilbild von Skyler Ji
Skyler Jivor 1 Monat

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

Profilbild von Coderman 🇵🇸
Coderman 🇵🇸vor 1 Monat

Trained on Donald Trump speeches?

Profilbild von strider
stridervor 1 Monat

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

Profilbild von Nanne
Nannevor 1 Monat

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

Profilbild von Rakib
Rakibvor 1 Monat

what a horror

Profilbild von 0xE  @enol.app
0xE  @enol.appvor 1 Monat

Doesn't this show how pointless jev is?

Profilbild von @_@
@_@vor 1 Monat

hmm. needs work

Profilbild von Nanda
Nandavor 1 Monat

It's like making a car sail. Bravo 🍾

Profilbild von w
wvor 1 Monat

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

Ähnliche 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 Aufrufe • vor 1 Monat

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 Aufrufe • vor 1 Monat