sagarthacker118's profile picture.

Sagar Thacker

@sagarthacker118

Sagar Thacker reposted

Sonnet 4.5 + MCP + n8n = AI Content Infrastructure that replaces $12K+/month ghostwriters... The 3-layer system that cloned my writing voice and generated 25M organic views → No more 2-3 week turnarounds for 5 basic posts → No more robotic AI that screams "ChatGPT wrote this"…


Sagar Thacker reposted

WE'RE HIRING FOUNDING ENGINEERS AT WTF. We’re building one of the most exciting projects yet at WTF, something that will shape us as a brand, as a platform, and (hopefully) create a far wider impact with and for the youth of India. The core team will work directly with me and a…


Sagar Thacker reposted

New post re: Devin (the AI SWE). We couldn't find many reviews of people using it for real tasks, so we went MKBHD mode and put Devin through its paces. We documented our findings here. Would love to know if others have had a different experience. answer.ai/posts/2025-01-…

HamelHusain's tweet image. New post re: Devin (the AI SWE).  We couldn't find many reviews of people using it for real tasks, so we went MKBHD mode and put Devin through its paces.

We documented our findings here.  Would love to know if others have had a different experience.

answer.ai/posts/2025-01-…

Sagar Thacker reposted

I will teach Large Language Model Systems again in Spring 2025. (11868 for CMU folks) The course syllabus (tentative) is online at llmsystem.github.io/llmsystem2025s… CMU ppl are welcome to enroll. For others, I will release the materials online. Or apply to CMU LLM/GenAI certificate program

llmsystem.github.io

LLM Systems | Large Language Model Systems

Description will go into a meta tag in


Sagar Thacker reposted

NVIDIA's $7B Mellanox acquisition was actually one of tech's most strategic deals ever. The untold story of the most important company in AI that most people haven't heard of 1/12

deedydas's tweet image. NVIDIA's $7B Mellanox acquisition was actually one of tech's most strategic deals ever.

The untold story of the most important company in AI that most people haven't heard of

1/12

Sagar Thacker reposted

LoRA Learns Less and Forgets Less: When I saw a new, comprehensive empirical study of Low-Rank Adaptation for finetuning LLMs, I had to read it! Here are the main takeaways. This study aimed to compare LoRA to full finetuning on two different target domains: programming and…

rasbt's tweet image. LoRA Learns Less and Forgets Less: When I saw a new, comprehensive empirical study of Low-Rank Adaptation for finetuning LLMs, I had to read it! Here are the main takeaways.

This study aimed to compare LoRA to full finetuning on two different target domains: programming and…

Sagar Thacker reposted

RELEASE DAY After almost 10 years of hard work, tireless research, and a dive deep into the kernels of computer science, I finally realized a dream: running a high-level language on GPUs. And I'm giving it to the world! Bend compiles modern programming features, including: -…


Sagar Thacker reposted

ChatGPT can now remember information across chats:

Memory is now available to all ChatGPT Plus users. Using Memory is easy: just start a new chat and tell ChatGPT anything you’d like it to remember. Memory can be turned on or off in settings and is not currently available in Europe or Korea. Team, Enterprise, and GPTs to come.



Sagar Thacker reposted

Our computer vision textbook is released! Foundations of Computer Vision with Antonio Torralba and Bill Freeman mitpress.mit.edu/9780262048972/… It’s been in the works for >10 years. Covers everything from linear filters and camera optics to diffusion models and radiance fields. 1/4

phillip_isola's tweet image. Our computer vision textbook is released!

Foundations of Computer Vision
with Antonio Torralba and Bill Freeman
mitpress.mit.edu/9780262048972/…

It’s been in the works for >10 years. Covers everything from linear filters and camera optics to diffusion models and radiance fields.

1/4

Sagar Thacker reposted

Foundation models are well-established in vision and language, but time series forecasting has lagged behind - it still relies on dataset-specific models. Meet Lag-Llama: the first open-source foundation model for time series forecasting!

arjunashok37's tweet image. Foundation models are well-established in vision and language, but time series forecasting has lagged behind -  it still relies on dataset-specific models.

Meet Lag-Llama: the first open-source foundation model for time series forecasting!

Sagar Thacker reposted

CUDA-MODE Lecture 3: Getting Started with CUDA Video: youtu.be/o3mWH7RqAos?si… Notebook: github.com/cuda-mode/lect… 🏎️Cuda intro for everyone with a Python background! @jeremyphoward builds the kernels 1:1 in python first (with blockIdx & threadIdx) ->then converts them to cuda C.


Sagar Thacker reposted

CUDA-MODE 3: Getting Started With CUDA How do you actually write a kernel and call it from Python? How do you test and debug your code? Speaker: @jeremyphoward Sat, Jan 27 12:00 PM PST (Bay Area) / 9:00 PM CET (Berlin) Live on discord: discord.gg/MF3xaGeKf6?eve…

neurosp1ke's tweet image. CUDA-MODE 3: Getting Started With CUDA

How do you actually write a kernel and call it from Python? How do you test and debug your code?

Speaker: @jeremyphoward
Sat, Jan 27
12:00 PM PST (Bay Area) / 9:00 PM CET (Berlin)

Live on discord: discord.gg/MF3xaGeKf6?eve…

Sagar Thacker reposted

🧑‍🔬👷 The LLM Course is now complete! I added the LLM Engineer Roadmap, a list of high-quality resources to build LLM-powered applications and deploy them. 💻 LLM Course: github.com/mlabonne/llm-c…

maximelabonne's tweet image. 🧑‍🔬👷 The LLM Course is now complete!

I added the LLM Engineer Roadmap, a list of high-quality resources to build LLM-powered applications and deploy them.

 💻 LLM Course: github.com/mlabonne/llm-c…
maximelabonne's tweet image. 🧑‍🔬👷 The LLM Course is now complete!

I added the LLM Engineer Roadmap, a list of high-quality resources to build LLM-powered applications and deploy them.

 💻 LLM Course: github.com/mlabonne/llm-c…

Sagar Thacker reposted

TikTok presents Depth Anything Unleashing the Power of Large-Scale Unlabeled Data paper page: huggingface.co/papers/2401.10… demo: huggingface.co/spaces/LiheYou… Depth Anything is trained on 1.5M labeled images and 62M+ unlabeled images jointly, providing the most capable Monocular Depth…


Sagar Thacker reposted

We've just open-sourced two tools we use for large-scale data processing and large-scale model trainings: - datatrove – all things webscale data processing: deduplication, filtering, tokenization – github.com/huggingface/da… - nanotron – all things 3D parallelism: lightweight and…


Sagar Thacker reposted

This is a really neat website with useful information to compare vector databases. All the information is in one place, searchable, and you can add filters by the dimension you care about. Very comprehensive and super useful!

omarsar0's tweet image. This is a really neat website with useful information to compare vector databases. 

All the information is in one place, searchable, and you can add filters by the dimension you care about. 

Very comprehensive and super useful!

Sagar Thacker reposted

I've read a ton of research papers this year. And to conclude this eventful year in AI, I've compiled a selection of 10 noteworthy papers from 2023 that I am discussing in my new article: magazine.sebastianraschka.com/p/10-ai-resear… To get a sneak peak, I'm covering: - insights into LLM training…


Sagar Thacker reposted

Getting there slowly! Join us to build the best Hindi/Hinglish Open LLM collaboratively. If you want to collaborate, join hinglish-training channel on Hugging Face Discord 💥 This model was finetuned on hindi/hinglish data using mistral as base model using AutoTrain, without…

abhi1thakur's tweet image. Getting there slowly! Join us to build the best Hindi/Hinglish Open LLM collaboratively. If you want to collaborate, join hinglish-training channel on Hugging Face Discord 💥 This model was finetuned on hindi/hinglish data using mistral as base model using AutoTrain, without…

Sagar Thacker reposted

Alibaba releases DreaMoving demo on Hugging Face A Human Video Generation Framework based on Diffusion Models demo: huggingface.co/spaces/jiayong…


Sagar Thacker reposted

Exploiting Novel GPT-4 APIs paper page: huggingface.co/papers/2312.14… Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, real-world APIs are often more…

_akhaliq's tweet image. Exploiting Novel GPT-4 APIs

paper page: huggingface.co/papers/2312.14…

Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, real-world APIs are often more…

United States Trends

Loading...

Something went wrong.


Something went wrong.