Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Fine-tuned Laya (421M parameters) Deduplicate/Aggregate vulnerability findings from Nuclei, Burp Suite, WPScan, etc... Running it locally, $0 inference cost 🤯 🟢 green = same finding 🔴 red = different finding

theMiddle

1,094 subscribers

17,594 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

3 Comments

Shebiiiii1 month ago

Can you share more details? Is it open source, and what are your system specifications?

Malik dishan1 month ago

Can u explain bit more about this

BugVulture1 month ago

How can we demo

Related Videos

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->

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 views • 29 days ago

Chris Travis - Green & Red 🟢🔴

Chris Travis - Green & Red 🟢🔴

CHRIS TRAVIS

48,313 views • 3 years ago

Finding out cost of outfits on the red carpet of the TGMAS🔥

Finding out cost of outfits on the red carpet of the TGMAS🔥

KSS

124,682 views • 5 months ago

Background agents running your calendar locally with LFM2.5-2.6B. Inference is free, so you can burn >1M tokens/hr at no marginal cost.

Background agents running your calendar locally with LFM2.5-2.6B. Inference is free, so you can burn >1M tokens/hr at no marginal cost.

Maxime Labonne

18,257 views • 2 months ago

PLTR green. NVDA red. Same war. Same futures. Different regime.

PLTR green. NVDA red. Same war. Same futures. Different regime.

Eric Jackson

20,245 views • 8 months ago

The craziest part of this video is finding out regular frisbees now cost $10 🤯

The craziest part of this video is finding out regular frisbees now cost $10 🤯

CCP IS ASSHOE

14,687 views • 8 months ago

🔴 Red light 🟢 Green light 🐻 Nighty night bears

🔴 Red light 🟢 Green light 🐻 Nighty night bears

Ponke

71,840 views • 1 year ago

The process of finding Gold from yellow rocks in the river, Finding a gold nugget worth $6500 🤯

The process of finding Gold from yellow rocks in the river, Finding a gold nugget worth $6500 🤯

Aﻥas🍷

10,825 views • 2 months ago

What are people whining about? I'm finding it absolutely fine.

What are people whining about? I'm finding it absolutely fine.

KSR

90,128 views • 3 years ago

Now you can hide all the annoying headers and stay focused on GET/POST parameters Thank you Burp Suite #BugBounty

Now you can hide all the annoying headers and stay focused on GET/POST parameters Thank you Burp Suite #BugBounty

H4x0r.DZ 🇰🇵

16,241 views • 1 year ago

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.

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 views • 1 month ago

The Hillbillies finding different ways to say the same things 🔥 TT: Jah Talks Music

The Hillbillies finding different ways to say the same things 🔥 TT: Jah Talks Music

kendrick Lyrics

49,710 views • 8 months ago

inference on your head mistral 7b (4bit quantized) running locally on apple vision pro

inference on your head mistral 7b (4bit quantized) running locally on apple vision pro

Joseph Semrai

239,991 views • 2 years ago

The Hyperpop Collection drops today. Choose your track: 🔴 Techno Red 🟢 Remix Green 🔵 Rhythm Blue Available now, direct from PlayStation:

The Hyperpop Collection drops today. Choose your track: 🔴 Techno Red 🟢 Remix Green 🔵 Rhythm Blue Available now, direct from PlayStation:

PlayStation

406,441 views • 7 months ago

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 ->

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

219,303 views • 24 days ago

The cost of finding an emotionally intelligent man

The cost of finding an emotionally intelligent man

De Christian Life

162,627 views • 1 year ago

Still finding videos like these on my phone from Sunday 😮‍💨🔴

Still finding videos like these on my phone from Sunday 😮‍💨🔴

Chloe bloxam

30,358 views • 1 year ago

🔴 Red flag or Green flag 🟢: 🇰🇿 Bibisara Assaubayeva edition! #FIDE #Chess #WomenInChess

🔴 Red flag or Green flag 🟢: 🇰🇿 Bibisara Assaubayeva edition! #FIDE #Chess #WomenInChess

International Chess Federation

11,036 views • 5 months ago

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 ->

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 views • 1 month ago