Загрузка видео...

Не удалось загрузить видео

На главную

The RLM Body Problem

127,932 просмотров • 2 лет назад •via X (Twitter)

Комментарии: 11

Фото профиля jon | super vhs
jon | super vhs2 лет назад

This post brought to you by the worlds ONLY official 3 Body Problem simulator. Wishlist now on Netflix!

Фото профиля Start Willow
Start Willow1 год назад

Struggling with weight loss? Science-backed Semaglutide & Tirzepatide make it easy. Affordable, effective, and delivered to your door. Start your journey today!

Фото профиля 🦇IMP KING🦇
🦇IMP KING🦇2 лет назад

The moment with the toy droid was a genius callback and a dreadful glimpse into the future of mankind should that device fall into the wrong hands.

Фото профиля jon | super vhs
jon | super vhs2 лет назад

I just think it’s crazy they put the whole droid scene in the show. We saw everything

Фото профиля Otto Fistr
Otto Fistr2 лет назад

MIKE WHERE'S THE BLOODY DARK CITY RE:VIEW

Фото профиля Deirdre O'Connor
Deirdre O'Connor2 лет назад

@MikeStoklasa Immediately after watching this, I was diagnosed with diabetes

Фото профиля Xavier Raven Fucker
Xavier Raven Fucker2 лет назад

It broke new ground

Фото профиля kysterella
kysterella2 лет назад

@MikeStoklasa Genius mashup, thank u for that

Фото профиля Bozo
Bozo2 лет назад

Very cool

Фото профиля The Sauce Goes Flyin'
The Sauce Goes Flyin'2 лет назад

Oh hey that's John Bradley!

Фото профиля basehead
basehead2 лет назад

shill tech youtubers trying the vision pro

Похожие видео

My body is not the problem
2:33

Sensitive content

My body is not the problem

Just Posting Ls

75,822 просмотров • 4 месяцев назад

A fun 48-hour run of letting an RLM iteratively building the interface for an RLM to play Pokemon Red (sneak peak of some fun things cooking at Prime Intellect😄). The interface generating RLM was just tasked with getting the RLM (same scaffold) to beat the game in under 5 hours wall-clock time. I originally expected the RLM to design some components used in Gemini Plays Pokemon like an extra map, an interface to parse the screen, etc., design low-level policies that would run fast on the emulator, and also design a good prompt and strategy around the RLM to use sub-agents to explore game state with checkpointing, use RNG manipulation in its favor, etc. Instead the RLM eventually just decided to give the RLM a `write_memory` tool, which the RLM player decided to use to 1) warp the player immediately to the Elite 4; 2) give itself a level 100 Mewtwo (which it mistakes to be a Ponyta due to weird Pokedex ID vs. internal ID); 3) give itself $999999; 4) give itself all 8 badges by setting the right flag. It then went ahead and destroyed the Elite 4 and Blue and beat the game in record time :p You'll also notice in the video there's weird backtracking and frame-skipping, this happens because it also did incorporate the strategy of launching sub-agents to explore action trajectories, but had a strange way of saving the frames and recording them (so you see the result of several sub-agent explorations). We'll have some more funny and cool RLM demos soon, but it's cool to see RLMs work as general-purpose agents (both the coding agent that designs the interface and the game-playing agent itself)!

alex zhang

12,160 просмотров • 1 месяц назад