Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

I built an o1 alternative, that is: 1) Fully transparent, visually trackable 2) Infinitely recursive 3) Self-healing, with tests at every step 4) Capable of using a Python interpreter It performs shockingly well, check it out! 🧵Code + performance on popular reasoning problems

pranavmarla's profile picture

trees of thought is in ny

2,806 subscribers

187,883 görüntüleme • 1 yıl önce •via X (Twitter)

EğitimOyunBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

showme is live! It is an O1 alternative, that is 1) Fully transparent, visually trackable 2) Infinitely recursive 3) Self-healing, with tests at every step 4) Capable of using a Python interpreter 🧵 Explanations, examples and comparisons (1/7)
0:17

showme is live! It is an O1 alternative, that is 1) Fully transparent, visually trackable 2) Infinitely recursive 3) Self-healing, with tests at every step 4) Capable of using a Python interpreter 🧵 Explanations, examples and comparisons (1/7)

trees of thought

37,177 görüntüleme • 1 yıl önce

Introducing o1 web crawler 🕸️ It crawls entire websites with OpenAI’s new o1 reasoning model and . Just state an objective and it will navigate + return the requested data in a JSON schema. Check it out:
0:17

Introducing o1 web crawler 🕸️ It crawls entire websites with OpenAI’s new o1 reasoning model and . Just state an objective and it will navigate + return the requested data in a JSON schema. Check it out:

Eric Ciarla (hiring)

397,759 görüntüleme • 1 yıl önce

Google has just launched an AI feature capable of planning, reasoning and searching the web. All this is done in a single prompt using Deep Research. This is literally the first reasoning model that has access to the internet. Game-changer. How to use it below 🧵
0:14

Google has just launched an AI feature capable of planning, reasoning and searching the web. All this is done in a single prompt using Deep Research. This is literally the first reasoning model that has access to the internet. Game-changer. How to use it below 🧵

Paul Couvert

298,310 görüntüleme • 1 yıl önce

🧵 Photos → Creative Code using Gemini I built an experiment that turns photos into interactive p5xjs sketches using Gemini 2.0 Flash. Unlike UI generators, this creates code that mimics the *behavior* of what's in the image - like smoke swirling or ripples spreading. Check out this sunset + smoke simulation
0:10

🧵 Photos → Creative Code using Gemini I built an experiment that turns photos into interactive p5xjs sketches using Gemini 2.0 Flash. Unlike UI generators, this creates code that mimics the *behavior* of what's in the image - like smoke swirling or ripples spreading. Check out this sunset + smoke simulation

Trudy Painter

155,027 görüntüleme • 1 yıl önce

Makes Pandas 20x Faster using FireDucks... ...by changing JUST ONE LINE of code. Pandas has a few limitations: - a single-core computation. - creates bulky DataFrames. - always follows an eager execution mode (every op triggers immediate computation), which is why it cannot prepare a smart execution plan that optimizes the entire sequence of operations. FireDucks is a heavily optimized alternative with exactly the same API as Pandas’ that addresses these. There are three ways to use it: 1) Load the extension: %𝐥𝐨𝐚𝐝_𝐞𝐱𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬; 𝗶𝗺𝗽𝗼𝗿𝘁 𝗽𝗮𝗻𝗱𝗮𝘀 𝗮𝘀 𝗽𝗱 2) Import FireDucks instead of Pandas: 𝐢𝐦𝐩𝐨𝐫𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬 𝐚𝐬 𝐩𝐝 3) If you have a Python script, execute is as follows: 𝗽𝘆𝘁𝗵𝗼𝗻3 -𝗺 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝗽𝗮𝗻𝗱𝗮𝘀 𝗰𝗼𝗱𝗲.𝗽𝘆 Done! ✅ Check this out👇
0:12

Makes Pandas 20x Faster using FireDucks... ...by changing JUST ONE LINE of code. Pandas has a few limitations: - a single-core computation. - creates bulky DataFrames. - always follows an eager execution mode (every op triggers immediate computation), which is why it cannot prepare a smart execution plan that optimizes the entire sequence of operations. FireDucks is a heavily optimized alternative with exactly the same API as Pandas’ that addresses these. There are three ways to use it: 1) Load the extension: %𝐥𝐨𝐚𝐝_𝐞𝐱𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬; 𝗶𝗺𝗽𝗼𝗿𝘁 𝗽𝗮𝗻𝗱𝗮𝘀 𝗮𝘀 𝗽𝗱 2) Import FireDucks instead of Pandas: 𝐢𝐦𝐩𝐨𝐫𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬 𝐚𝐬 𝐩𝐝 3) If you have a Python script, execute is as follows: 𝗽𝘆𝘁𝗵𝗼𝗻3 -𝗺 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝗽𝗮𝗻𝗱𝗮𝘀 𝗰𝗼𝗱𝗲.𝗽𝘆 Done! ✅ Check this out👇

Akshay 🚀

73,967 görüntüleme • 1 yıl önce

Fun fact: Most games try to avoid transparencies because it can tank performance and lead to render issues with effects. The common solution? Really thin dithering! The jar on the left is using dithering while the jar on the right is actually transparent. 🧵(1/2)
0:10

Fun fact: Most games try to avoid transparencies because it can tank performance and lead to render issues with effects. The common solution? Really thin dithering! The jar on the left is using dithering while the jar on the right is actually transparent. 🧵(1/2)

Fabraz: Demon Tides & Bubsy 4D

2,541,636 görüntüleme • 2 yıl önce

Want to code using GPT-4? We made an IDE built for programming alongside it Try out the public beta here:
0:14

Want to code using GPT-4? We made an IDE built for programming alongside it Try out the public beta here:

Aman Sanger

514,311 görüntüleme • 3 yıl önce

I built an iOS-style modal sheet with React Aria Components and Framer Motion! It uses gesture-driven animations to feel super smooth and natural on touch devices. It's a surprisingly small amount of code too. Check it out! 🤩
0:14

I built an iOS-style modal sheet with React Aria Components and Framer Motion! It uses gesture-driven animations to feel super smooth and natural on touch devices. It's a surprisingly small amount of code too. Check it out! 🤩

Devon Govett

182,609 görüntüleme • 3 yıl önce

Today, we launch YouAgent, an AI agent with code execution for more accurate answers to complex math and science questions. Unlike other consumer chat engines that cannot do reliable, multiple-step reasoning, it will also compute your mortgage accurately ;) A🧵 >
0:17

Today, we launch YouAgent, an AI agent with code execution for more accurate answers to complex math and science questions. Unlike other consumer chat engines that cannot do reliable, multiple-step reasoning, it will also compute your mortgage accurately ;) A🧵 >

Richard Socher

468,283 görüntüleme • 2 yıl önce

is an amazing admin dashboard! 1. Open Source (Free) 2. Customizable 3. Beautiful Check it out!
0:19

is an amazing admin dashboard! 1. Open Source (Free) 2. Customizable 3. Beautiful Check it out!

Marko Denic

169,114 görüntüleme • 1 yıl önce

is an amazing admin dashboard! 1. Open Source (Free) 2. Customizable 3. Beautiful Check it out!
0:19

is an amazing admin dashboard! 1. Open Source (Free) 2. Customizable 3. Beautiful Check it out!

Marko Denic

21,091 görüntüleme • 20 gün önce

The Dream 7B (diffusion reasoning language model) is OUT! 🚨 I built a demo so you can test it out (and check the diffusion process live) 𖣯🔍
0:10

The Dream 7B (diffusion reasoning language model) is OUT! 🚨 I built a demo so you can test it out (and check the diffusion process live) 𖣯🔍

apolinario (poli)

35,679 görüntüleme • 1 yıl önce

OpenAI’s new o1 models are available in Cursor! We’ve found o1 to be excellent at well-specified, reasoning-intense problems. We still recommend sonnet/4o for most tasks. We’re initially rolling out the models with usage-based pricing but will iterate as rate limits increase.
0:13

OpenAI’s new o1 models are available in Cursor! We’ve found o1 to be excellent at well-specified, reasoning-intense problems. We still recommend sonnet/4o for most tasks. We’re initially rolling out the models with usage-based pricing but will iterate as rate limits increase.

Cursor

479,578 görüntüleme • 1 yıl önce

It was worth every step of the 3 1/2 hour hike up
0:12

It was worth every step of the 3 1/2 hour hike up

Ski Life

25,369 görüntüleme • 8 ay önce

Display a video on an interactive map 🗺️ with #MapLibre and #Leafmap. Check it out: Map: GitHub: Notebook: #geospatial #opensource #dataviz #python
0:12

Display a video on an interactive map 🗺️ with #MapLibre and #Leafmap. Check it out: Map: GitHub: Notebook: #geospatial #opensource #dataviz #python

Qiusheng Wu

34,823 görüntüleme • 2 yıl önce

I optimized my rasterization code and was able to get ~2200 polygons rendering in real-time in my toy programming language. This is running in an interpreter using a single thread. The fact that it's flat shaded, not textured, makes it not too hard to get good performance.
0:17

I optimized my rasterization code and was able to get ~2200 polygons rendering in real-time in my toy programming language. This is running in an interpreter using a single thread. The fact that it's flat shaded, not textured, makes it not too hard to get good performance.

Maxime Chevalier

27,873 görüntüleme • 9 ay önce

Step 1. Get a gong for stream ✅ Step 2. Smash it so hard while using the "Bad mic" to break eardrums ✅✅💥 Step 3. ... Step 4. Profit ItsJabo ??
0:10

Step 1. Get a gong for stream ✅ Step 2. Smash it so hard while using the "Bad mic" to break eardrums ✅✅💥 Step 3. ... Step 4. Profit ItsJabo ??

Twitch UK & Ireland

23,693 görüntüleme • 1 yıl önce

I lead written socials at Lovable and today I built an AI clone of myself with Lovable and our new Slack connector. It proactively monitors relevant sources and reaches out to me when it finds an opportunity. I can also tag it with a post idea, and it will help write it. The coolest part is that it improves over time as I give it feedback! Below is how I built it.
0:15

I lead written socials at Lovable and today I built an AI clone of myself with Lovable and our new Slack connector. It proactively monitors relevant sources and reaches out to me when it finds an opportunity. I can also tag it with a post idea, and it will help write it. The coolest part is that it improves over time as I give it feedback! Below is how I built it.

Henrik

14,388 görüntüleme • 4 ay önce