Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Here’s Deepseek r1 1.5B thinking through a problem — it’s comparable to 4o and Claude 3.5 Sonnet in a number of domains like math. Except… it’s a 1.5B model… and can run on virtually any hardware. Truly a huge efficiency leap.

localghost's profile picture

Aaron Ng

35,863 subscribers

564,677 Aufrufe • vor 1 Jahr •via X (Twitter)

BildungKunstWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

it's crazy what a 1.5B model can do these days! "VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium." runs perfectly on device!
0:18

it's crazy what a 1.5B model can do these days! "VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium." runs perfectly on device!

Maziyar PANAHI

202,350 Aufrufe • vor 8 Monaten

Llama 4 seems to actually be a poor model for coding. Scout (109B) and Maverick (402B) underperform 4o, Gemini Flash, Grok 3, DeepSeek V3 and Sonnet 3.5/7 on the Kscores benchmark which tests on coding tasks like this. ELO-maxxing on LMarena doesn’t create the best models.
0:11

Llama 4 seems to actually be a poor model for coding. Scout (109B) and Maverick (402B) underperform 4o, Gemini Flash, Grok 3, DeepSeek V3 and Sonnet 3.5/7 on the Kscores benchmark which tests on coding tasks like this. ELO-maxxing on LMarena doesn’t create the best models.

Deedy

252,791 Aufrufe • vor 1 Jahr

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.
0:17

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.

Santiago

1,224,059 Aufrufe • vor 1 Jahr

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:
0:17

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

Sean Strong

115,687 Aufrufe • vor 9 Monaten

Free 3.5 to a random like and RT! Pick any flavor It’s been a min. SN: this raspberry uncrustable taste amazing 🔥🔥🔥
0:14

Free 3.5 to a random like and RT! Pick any flavor It’s been a min. SN: this raspberry uncrustable taste amazing 🔥🔥🔥

10 toes 🏃🏾‍♂️💰

72,456 Aufrufe • vor 10 Monaten

I’m not saying an open-source model you can run on consumer hardware is better than ChatGPT, just that sometimes it’s worth trying both. Prompt: “A zebra with a volcanic eruption in the background.”
0:11

I’m not saying an open-source model you can run on consumer hardware is better than ChatGPT, just that sometimes it’s worth trying both. Prompt: “A zebra with a volcanic eruption in the background.”

Victor M

105,329 Aufrufe • vor 7 Monaten

💬 "It’s a beautiful day, especially for me, because that’s a big number and it’s a huge privilege to be where I am." Mikel Arteta reflects on returning to winning ways in the Premier League 👇
0:17

💬 "It’s a beautiful day, especially for me, because that’s a big number and it’s a huge privilege to be where I am." Mikel Arteta reflects on returning to winning ways in the Premier League 👇

Arsenal

131,454 Aufrufe • vor 1 Jahr

Qwen has just released a model on par with GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details below
0:15

Qwen has just released a model on par with GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details below

Paul Couvert

504,191 Aufrufe • vor 11 Monaten

This is what it’s like to charge a Tesla Semi with a Megacharger. The chargers can deliver up to 1.2 MW (1,200 kW) of power, and functions basically like any other Tesla Supercharger. It’s just massive.
0:19

This is what it’s like to charge a Tesla Semi with a Megacharger. The chargers can deliver up to 1.2 MW (1,200 kW) of power, and functions basically like any other Tesla Supercharger. It’s just massive.

Nic Cruz Patane

181,017 Aufrufe • vor 11 Monaten

Announcing Bespoke-MiniChart-7B, a new SOTA in chart understanding for models of comparable size on seven benchmarks, on par with Gemini-1.5-Pro and Claude-3.5! 🚀 Beyond its real-world applications, chart understanding is a good challenging problem for VLMs, since it requires both mathematical as well as visual reasoning. 1/n🧵
0:14

Announcing Bespoke-MiniChart-7B, a new SOTA in chart understanding for models of comparable size on seven benchmarks, on par with Gemini-1.5-Pro and Claude-3.5! 🚀 Beyond its real-world applications, chart understanding is a good challenging problem for VLMs, since it requires both mathematical as well as visual reasoning. 1/n🧵

Bespoke Labs

19,871 Aufrufe • vor 1 Jahr

It’s a skill honed by decades of looking at a word and then thinking, “🤔 Hmm. I bet I can more than double or even triple the number of times that letter should appear.”
0:17

It’s a skill honed by decades of looking at a word and then thinking, “🤔 Hmm. I bet I can more than double or even triple the number of times that letter should appear.”

Parry Shen

10,855 Aufrufe • vor 1 Jahr

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.
0:14

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.

Sundar Pichai

864,176 Aufrufe • vor 1 Jahr

Claude Fable 5 is our first generally available Mythos-class model. It ships with new safety classifiers that may flag certain prompts in dual-use domains like cyber and bio. We've added fallbacks: a refused request retries on Claude Opus 4.8 instead of dead-ending.
0:15

Claude Fable 5 is our first generally available Mythos-class model. It ships with new safety classifiers that may flag certain prompts in dual-use domains like cyber and bio. We've added fallbacks: a refused request retries on Claude Opus 4.8 instead of dead-ending.

ClaudeDevs

463,707 Aufrufe • vor 1 Monat

One moment it’s calmly perched on bamboo, the next—thud. A quick pause, a small shake, and it’s back to eating like it’s part of the routine.
0:12

One moment it’s calmly perched on bamboo, the next—thud. A quick pause, a small shake, and it’s back to eating like it’s part of the routine.

China Perspective

12,389 Aufrufe • vor 6 Monaten

Throwback to everyone being curious about why Asa picked the number 37 on her jersey and nails Asa : It’s a number I like 37 is the number of weeks I spent in my mother’s belly 😭
0:16

Throwback to everyone being curious about why Asa picked the number 37 on her jersey and nails Asa : It’s a number I like 37 is the number of weeks I spent in my mother’s belly 😭

🐈‍⬛

42,341 Aufrufe • vor 2 Monaten

Math says the Big Bang made matter and antimatter in equal halves. They should have erased each other into light, leaving no one to see it. And yet, you exist, because nature miscounted by one part in a billion. Math says nothing forbids a particle from outrunning light. The equations hand it an imaginary mass and let it through. And yet, in a century of looking, not one has ever shown up. Math says you can have a north without a south. Break a magnet, isolate the pole. And yet break it a trillion times, you get a trillion little magnets, each with both ends intact. The universe reads the math and decides what it’s willing to be.
0:19

Math says the Big Bang made matter and antimatter in equal halves. They should have erased each other into light, leaving no one to see it. And yet, you exist, because nature miscounted by one part in a billion. Math says nothing forbids a particle from outrunning light. The equations hand it an imaginary mass and let it through. And yet, in a century of looking, not one has ever shown up. Math says you can have a north without a south. Break a magnet, isolate the pole. And yet break it a trillion times, you get a trillion little magnets, each with both ends intact. The universe reads the math and decides what it’s willing to be.

Kekius Maximus

13,362 Aufrufe • vor 1 Monat

Uh chat wtf Because IF it’s legit and someone caught that on camera and it’s near identical to the cover art of David Fronings book. It’s gonna be a huge W.
0:15

Uh chat wtf Because IF it’s legit and someone caught that on camera and it’s near identical to the cover art of David Fronings book. It’s gonna be a huge W.

Tom Hudson

40,200 Aufrufe • vor 1 Monat