Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Local Laya beat OpenAI's decision API 🕷 Four decision models raced down a web page ripping out links that name a spider and Laya running locally on an M5 Max took 34 ms a link so it checked 3x more than the cloud models Run decision models locally ->

atomic_chat_hq's profile picture

atomic.chat

19,405 subscribers

219,303 Aufrufe • vor 23 Tagen •via X (Twitter)

Nachrichten & PolitikWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

26 Kommentare

Profilbild von AVB
AVBvor 23 Tagen

@OpenAI The first spider for super excited to see its own name and smashed through it lol

Profilbild von Jigs
Jigsvor 23 Tagen

@OpenAI Laya is actually good for its size

Profilbild von Omar
Omarvor 23 Tagen

@OpenAI Local gutsy outperforms local laya, and is also free, open source, and just 500MB for CPU inference

Profilbild von Secure the AI 🤖
Secure the AI 🤖vor 23 Tagen

@OpenAI

Profilbild von Liam Vinberg
Liam Vinbergvor 23 Tagen

@OpenAI depends on the task

Profilbild von Thusatharan
Thusatharanvor 23 Tagen

@OpenAI no network round trip per call, of course local takes it

Profilbild von Mateleo
Mateleovor 23 Tagen

@OpenAI kudo for the viz, wow

Profilbild von Mattia
Mattiavor 23 Tagen

@OpenAI I‘m using laya for my Hermes Agent and it’s perfect

Profilbild von Vikas
Vikasvor 23 Tagen

@OpenAI Decider-4B is better model than laya. Try using it.

Profilbild von Schwarzer Ritter
Schwarzer Rittervor 23 Tagen

@OpenAI small = fast

Profilbild von Roko ʕ •ᴥ•ʔっ🪄✨🐍
Roko ʕ •ᴥ•ʔっ🪄✨🐍vor 23 Tagen

@OpenAI I wonder how DM-JEPA would do here

Profilbild von Jaid
Jaidvor 23 Tagen

@OpenAI S-tier eval visualization 💎

Profilbild von Martin Ronfort
Martin Ronfortvor 23 Tagen

@OpenAI Laya running locally is actually proving decision models can outpace cloud APIs on both speed and cost. We went deeper on this shift in how AI judgment is changing here:

Profilbild von promovierdichinsknie
promovierdichinsknievor 23 Tagen

@OpenAI i agree in my test laya also outperformed clef flash an CLM

Profilbild von Yoeven
Yoevenvor 23 Tagen

@OpenAI You haven’t put lev to the test

Profilbild von Georgy GLuhov
Georgy GLuhovvor 23 Tagen

@OpenAI I’ve achieved four hours of successful autonomous operation for Laya in my RimWorld colony without any input from me; all experiment logs are recorded in the repository, and I’m also planning to host a stream!

Profilbild von Wolkyen
Wolkyenvor 23 Tagen

@OpenAI What about Mercury decide? Its the best!

Profilbild von Eugene Meidinger
Eugene Meidingervor 23 Tagen

@OpenAI Nightmare fuel

Profilbild von henrik the vibe
henrik the vibevor 23 Tagen

@OpenAI You've got me on my knees, Layla Begging darling please, Layla Darling, won't you ease my worried mind?

Profilbild von Brjan | AI Builder
Brjan | AI Buildervor 23 Tagen

@OpenAI if local models can process links 3x faster, cloud solutions need to catch up

Profilbild von Toasterson @Toasterson@chaos.social
Toasterson @[email protected]vor 23 Tagen

@OpenAI How did you do the animations?

Profilbild von Don Rai
Don Raivor 23 Tagen

@OpenAI But I tested yesterday and Laya didn't work so well 🫠

Profilbild von TslaMan
TslaManvor 23 Tagen

@OpenAI Nice marketing so cute

Profilbild von Zuhayr Khan
Zuhayr Khanvor 23 Tagen

@OpenAI Did all four models pick the same links, or were there differences in what they missed?

Profilbild von Mark Kashef
Mark Kashefvor 23 Tagen

@OpenAI I doubt it beats it on speed, Decisions API is pretty fast

Profilbild von nicholas gogerty
nicholas gogertyvor 23 Tagen

@OpenAI how about something that scales as it fails. JEV fail-up across scales

Ähnliche Videos

Local Laya blitzed other models on RTX 4090 ⚡️ Four local decision models raced down Wikipedia picking out every word that names a centipede and Laya took 3.9 ms a word so it ended up being the fastest overall Run decision models locally ->
0:20

Local Laya blitzed other models on RTX 4090 ⚡️ Four local decision models raced down Wikipedia picking out every word that names a centipede and Laya took 3.9 ms a word so it ended up being the fastest overall Run decision models locally ->

atomic.chat

26,773 Aufrufe • vor 22 Tagen

Local Laya moggs Jev at Grok 4.7-built Tetris 🧩 An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air! Run AI models locally ->
0:22

Local Laya moggs Jev at Grok 4.7-built Tetris 🧩 An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air! Run AI models locally ->

atomic.chat

1,101,104 Aufrufe • vor 1 Monat

Laya plays Plants vs Zombies on CPU 🧟 We patched the llama.cpp engine to run Laya natively so it works on a regular CPU with no GPU and here a fine-tuned Laya makes every move until it beats the Plants vs Zombies pool level Run decision models locally->
0:55

Laya plays Plants vs Zombies on CPU 🧟 We patched the llama.cpp engine to run Laya natively so it works on a regular CPU with no GPU and here a fine-tuned Laya makes every move until it beats the Plants vs Zombies pool level Run decision models locally->

atomic.chat

14,071 Aufrufe • vor 28 Tagen

The open-source local version of Laya crushes Jev in response speed! On the left is Laya, a local 421M open-source decision model. On the right is Jev 1.13.0, running through a cloud API. Same Snake game, same typed decisions, and the same 30-second free run: - Laya: Score 46, Length 52, 86.5 decisions/sec - Jev: Score 1, Length 7, 3.2 decisions/sec - In a real test on an M5 Pro, median latency was 15.3ms locally versus 298.1ms in the cloud, so nearly 20x faster. Laya uses around 1GB of memory, responds in milliseconds, and doesn’t depend on a network connection. While Jev waits for a cloud round-trip at every step, Laya makes each decision instantly on-device.
0:31

The open-source local version of Laya crushes Jev in response speed! On the left is Laya, a local 421M open-source decision model. On the right is Jev 1.13.0, running through a cloud API. Same Snake game, same typed decisions, and the same 30-second free run: - Laya: Score 46, Length 52, 86.5 decisions/sec - Jev: Score 1, Length 7, 3.2 decisions/sec - In a real test on an M5 Pro, median latency was 15.3ms locally versus 298.1ms in the cloud, so nearly 20x faster. Laya uses around 1GB of memory, responds in milliseconds, and doesn’t depend on a network connection. While Jev waits for a cloud round-trip at every step, Laya makes each decision instantly on-device.

Simplifying AI

24,406 Aufrufe • vor 1 Monat

Local Liquid d1 3B crushed OpenAI Decision at Snake 🐍 Liquid AI d1 on a single RTX 3090 decides in 8 ms so its snake made 82 moves a second and ate 86 apples while OpenAI's API took 345 ms a call and ate 3 Run decision models ->
0:22

Local Liquid d1 3B crushed OpenAI Decision at Snake 🐍 Liquid AI d1 on a single RTX 3090 decides in 8 ms so its snake made 82 moves a second and ate 86 apples while OpenAI's API took 345 ms a call and ate 3 Run decision models ->

atomic.chat

194,947 Aufrufe • vor 23 Tagen

OpenAI Decision crushed by Microsoft-Decision-1 at Space Invaders 👾 Decision-1 decided 3.5x faster so it scored 3,320 and cleared 4 waves while OpenAI's decision API scored 1,300 taking over 300ms per decision on average Run decision models ->
0:28

OpenAI Decision crushed by Microsoft-Decision-1 at Space Invaders 👾 Decision-1 decided 3.5x faster so it scored 3,320 and cleared 4 waves while OpenAI's decision API scored 1,300 taking over 300ms per decision on average Run decision models ->

atomic.chat

91,460 Aufrufe • vor 20 Tagen

Thanks for the model, we were able to port Laya to coreml with 99.5% of the ops on ANE + benchmarked too. it is now blazing fast with 3.7 ms per decision on an M5 Pro. Release: Models:
0:24

Thanks for the model, we were able to port Laya to coreml with 99.5% of the ops on ANE + benchmarked too. it is now blazing fast with 3.7 ms per decision on an M5 Pro. Release: Models:

Alex

120,068 Aufrufe • vor 1 Monat

decision models + local ai = ❤️ tried Laya (421M) on llama.cpp in a little apple-picking benchmark, it's almost as good as Qwen 4B at 12x the speed.
0:44

decision models + local ai = ❤️ tried Laya (421M) on llama.cpp in a little apple-picking benchmark, it's almost as good as Qwen 4B at 12x the speed.

Victor M

10,508 Aufrufe • vor 24 Tagen

Ollama now supports Jev-like decision models all locally. Use decision models like Nimble for tasks like ticket triaging, model routing, and content moderation. ollama pull nimble Here’s Nimble playing Ollama racer through the new local /v1/systemone API by making decisions in real-time. 🏎️
0:23

Ollama now supports Jev-like decision models all locally. Use decision models like Nimble for tasks like ticket triaging, model routing, and content moderation. ollama pull nimble Here’s Nimble playing Ollama racer through the new local /v1/systemone API by making decisions in real-time. 🏎️

ollama

667,164 Aufrufe • vor 1 Monat

Next up on First Pass: a conversation with Sam Crowder from LangChain on decision models. Jev from TypeSafe AI took the world by storm. Then OpenAI and Databricks released producs (Decisions API and ai_decide function) So what are Decision Models? We dig in!
11:11

Next up on First Pass: a conversation with Sam Crowder from LangChain on decision models. Jev from TypeSafe AI took the world by storm. Then OpenAI and Databricks released producs (Decisions API and ai_decide function) So what are Decision Models? We dig in!

Jamin Ball

12,147 Aufrufe • vor 22 Tagen

"Why should you run your models locally?" Asked Qwen3.6 27B. Running locally. Thinking mode on. It made the case itself.
0:48

"Why should you run your models locally?" Asked Qwen3.6 27B. Running locally. Thinking mode on. It made the case itself.

Osaurus

42,770 Aufrufe • vor 6 Monaten

I got a fully maxed out MacBook, mostly so I can run local models fast. And omg here is mixtral running on ollama... almost cannot believe how fast it is. This is with no internet!! A model that beats GPT-3.5 running locally! What!
0:20

I got a fully maxed out MacBook, mostly so I can run local models fast. And omg here is mixtral running on ollama... almost cannot believe how fast it is. This is with no internet!! A model that beats GPT-3.5 running locally! What!

Charlie Holtz

196,086 Aufrufe • vor 2 Jahren

Run OpenClaw locally with ollama 🦙 – Open source models: MiniMax, Qwen, Kimi and more – One click install on macOS and Windows – Local & cloud Ollama models connected atomicbot.ai where llamas meet claws 🦞
0:24

Run OpenClaw locally with ollama 🦙 – Open source models: MiniMax, Qwen, Kimi and more – One click install on macOS and Windows – Local & cloud Ollama models connected atomicbot.ai where llamas meet claws 🦞

atomicbot.ai

59,926 Aufrufe • vor 7 Monaten

For anyone wandering what does it mean to run ds4-agent locally on an M5 Max using DeepSeek V4 Flash q2-imatrix gguf model. Here's a video of ds4 updating itself, adding a way to leverage HF_HOME for gguf models. Future of Local AI is bright!
2:31

For anyone wandering what does it mean to run ds4-agent locally on an M5 Max using DeepSeek V4 Flash q2-imatrix gguf model. Here's a video of ds4 updating itself, adding a way to leverage HF_HOME for gguf models. Future of Local AI is bright!

Ivan Fioravanti ᯅ

30,452 Aufrufe • vor 5 Monaten

Portable Computer is now available on Windows PCs with @NVIDIA RTX GPUs. Run the harness, agents, and models locally on your PC. Work with local files and connected apps without sending tasks to the cloud. Use frontier cloud models when needed.
0:32

Portable Computer is now available on Windows PCs with @NVIDIA RTX GPUs. Run the harness, agents, and models locally on your PC. Work with local files and connected apps without sending tasks to the cloud. Use frontier cloud models when needed.

Perplexity

678,125 Aufrufe • vor 1 Monat

Behold... GPT-OSS (20B) running 100% locally in your browser on WebGPU. This shouldn't be possible — but with Transformers.js v4 and ONNX Runtime Web, it is! A new class of AI apps is emerging. Zero-install, infinite distribution. Simply visit a website and run models locally.
1:23

Behold... GPT-OSS (20B) running 100% locally in your browser on WebGPU. This shouldn't be possible — but with Transformers.js v4 and ONNX Runtime Web, it is! A new class of AI apps is emerging. Zero-install, infinite distribution. Simply visit a website and run models locally.

Xenova

311,512 Aufrufe • vor 8 Monaten

We made it possible to train your own Decision model locally on just 3GB VRAM! We converted Qwen, Gemma, Llama all into decision models by fine-tuning using a Clef head, boosting accuracy from 30 to up to 78%. You can try it yourself via Unsloth Desktop!
0:31

We made it possible to train your own Decision model locally on just 3GB VRAM! We converted Qwen, Gemma, Llama all into decision models by fine-tuning using a Clef head, boosting accuracy from 30 to up to 78%. You can try it yourself via Unsloth Desktop!

Daniel Han

27,256 Aufrufe • vor 23 Tagen

You can now run pplx-decider-flash-v1.2 locally on your Mac, without an API key. Decider for Mac is an app that runs the 4B decision model on device. Ask a question about text or an image and get a probability back, all on your machine.
0:51

You can now run pplx-decider-flash-v1.2 locally on your Mac, without an API key. Decider for Mac is an app that runs the 4B decision model on device. Ask a question about text or an image and get a probability back, all on your machine.

Perplexity Developers

98,995 Aufrufe • vor 8 Tagen

Introducing THIS / THAT Model 1.0. Trained by FLock. Not another chatbot. A best-in-class open-source model built to decide. 94.1% success rate on our 68-question decision test, outperforming GPT-5.6, Deepseek-4.1-flash, Kimi K3, Jev, and more. Just 1.9B parameters. Runs locally. Measured decision latency of ~31 ms on an RTX 5080 laptop GPU. We’re putting decentralized AI to work: giving developers and AI agents decision-making capabilities they can run on their own hardware. Your model. Your machine. Not every decision needs the cloud.
0:20

Introducing THIS / THAT Model 1.0. Trained by FLock. Not another chatbot. A best-in-class open-source model built to decide. 94.1% success rate on our 68-question decision test, outperforming GPT-5.6, Deepseek-4.1-flash, Kimi K3, Jev, and more. Just 1.9B parameters. Runs locally. Measured decision latency of ~31 ms on an RTX 5080 laptop GPU. We’re putting decentralized AI to work: giving developers and AI agents decision-making capabilities they can run on their own hardware. Your model. Your machine. Not every decision needs the cloud.

FLock.io

12,708 Aufrufe • vor 1 Monat

It's been an amazing week for open models running on NVIDIA Local AI systems! 👀 Here's a few you’ll want to know about, all ready to run locally on NVIDIA RTX, DGX Spark, DGX Station, and Jetson.
1:30

It's been an amazing week for open models running on NVIDIA Local AI systems! 👀 Here's a few you’ll want to know about, all ready to run locally on NVIDIA RTX, DGX Spark, DGX Station, and Jetson.

NVIDIA RTX Spark

60,853 Aufrufe • vor 2 Monaten