aicoding_'s profile picture. Computer Vision Engineer currently working as a Machine Learning Engineer.

http://github.com/coding-ai

http://patreon.com/aicoding

Andrea | 🇸🇪🇪🇸🇻🇪

@aicoding_

Computer Vision Engineer currently working as a Machine Learning Engineer. http://github.com/coding-ai http://patreon.com/aicoding

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

Introducing Critique Fine-Tuning (CFT): a more effective SFT method for enhancing LLMs' reasoning abilities. 📄 Paper: arxiv.org/pdf/2501.17703 CFT is simple: instead of training models to directly answer questions, we train them to critique noisy answers. What's fascinating is…

xiangyue96's tweet image. Introducing Critique Fine-Tuning (CFT): a more effective SFT method for enhancing LLMs' reasoning abilities.
📄 Paper: arxiv.org/pdf/2501.17703
CFT is simple: instead of training models to directly answer questions, we train them to critique noisy answers.

What's fascinating is…

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

Run DeepSeek-R1 (671B) locally on @OpenWebUI - Full Guide No GPU required. Using our 1.58-bit Dynamic GGUF and llama.cpp. Tutorial: docs.openwebui.com/tutorials/inte…

UnslothAI's tweet image. Run DeepSeek-R1 (671B) locally on @OpenWebUI - Full Guide

No GPU required.
Using our 1.58-bit Dynamic GGUF and llama.cpp.

Tutorial: docs.openwebui.com/tutorials/inte…

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

You don't need a reasoning model like R1 or o3, just use this .cursorrules with Claude Sonnet to add a thinking step, works 100x better.

illyism's tweet image. You don't need a reasoning model like R1 or o3, just use this .cursorrules with Claude Sonnet to add a thinking step, works 100x better.

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

🔥 o3-mini-high beats deepseek r1 and o1-pro! in a p5.js challenge! 03-mini result is so good that deserves a video on its own. deepseek r1 (bad result) and o1-pro (better) in comments below. Prompt in last comment. 1/4


Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

Transformers can overcome easy-to-hard and length generalization challenges through recursive self-improvement. Paper on arxiv coming on Monday. Link to a talk I gave on this below 👇 Super excited about this work!

DimitrisPapail's tweet image. Transformers can overcome easy-to-hard and length generalization challenges through recursive self-improvement. 

Paper on arxiv coming on Monday.
Link to a talk I gave on this below 👇

Super excited about this work!
DimitrisPapail's tweet image. Transformers can overcome easy-to-hard and length generalization challenges through recursive self-improvement. 

Paper on arxiv coming on Monday.
Link to a talk I gave on this below 👇

Super excited about this work!
DimitrisPapail's tweet image. Transformers can overcome easy-to-hard and length generalization challenges through recursive self-improvement. 

Paper on arxiv coming on Monday.
Link to a talk I gave on this below 👇

Super excited about this work!

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

o3-mini is out! smart, fast model. available in ChatGPT and API. it can search the web, and it shows its thinking. available to free-tier users! click the "reason" button. with ChatGPT plus, you can select "o3-mini-high", which thinks harder and gives better answers.


Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

what up guys, I made a one-page comparison of MHA and MLA from @deepseek_ai for those who skipped the DS-V2 paper. pls correct me if I'm wrong.

SeunghyunSEO7's tweet image. what up guys, I made a one-page comparison of MHA and MLA from @deepseek_ai  for those who skipped the DS-V2 paper. 
pls correct me if I'm wrong.

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

📚🤖 Advanced RAG + Agents Cookbook A comprehensive open-source guide delivering production-ready implementations of cutting-edge RAG techniques with AI agents. Built with LangChain and LangGraph, it features advanced implementations like Hybrid, Self, and ReAct RAG. Learn…

LangChainAI's tweet image. 📚🤖 Advanced RAG + Agents Cookbook

A comprehensive open-source guide delivering production-ready implementations of cutting-edge RAG techniques with AI agents. Built with LangChain and LangGraph, it features advanced implementations like Hybrid, Self, and ReAct RAG.

Learn…

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

Fuck it, today we're open-sourcing the codebase used to train SmolVLM from scratch on 256 H100s🔥 Inspired by our team's effort to open-source DeepSeek's R1 training, we are releasing the training and evaluation code on top of the weights 🫡 Now you can train any of our…

andimarafioti's tweet image. Fuck it, today we're open-sourcing the codebase used to train SmolVLM from scratch on 256 H100s🔥
Inspired by our team's effort to open-source DeepSeek's R1 training, we are releasing the training and evaluation code on top of the weights 🫡
Now you can train any of our…

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

OpenAI o3-mini System Card

_akhaliq's tweet image. OpenAI o3-mini System Card

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

Letter-dropping physics comparison: o3-mini vs. deepseek-r1 vs. claude-3.5 in one-shot - which is the best? Prompt: Create a JavaScript animation of falling letters with realistic physics. The letters should: * Appear randomly at the top of the screen with varying sizes * Fall…


Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

AI Agents for Computer Use This report provides a comprehensive overview of the emerging field of instruction-based computer control, examining available agents – their taxonomy, development, and resources.

omarsar0's tweet image. AI Agents for Computer Use

This report provides a comprehensive overview of the emerging field of instruction-based computer control, examining available agents – their taxonomy, development, and resources.

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

Gemini 2.0 doesn’t get nearly enough credit. I just dumped all my workers-qb source code into it, hit it with a simple, humble prompt, and boom => it one-shotted the docs. Not just good docs, way better than what I had before, packed with examples. Kinda insane.


Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

OpenAI o3-mini just one shotted this prompt: write a script for 100 bouncing yellow balls within a sphere, make sure to handle collision detection properly. make the sphere slowly rotate. make sure balls stays within the sphere. implement it in p5.js


Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

Finished a run (R1 style) GRPO on Qwen-2.5-0.5B (base model) yield +10 accuracy points on GSM8K. Literally just works. Base model scores 41.6% as reported on qwen paper vs 51%~ GRPO

abacaj's tweet image. Finished a run (R1 style) GRPO on Qwen-2.5-0.5B (base model) yield +10 accuracy points on GSM8K. Literally just works. Base model scores 41.6% as reported on qwen paper vs 51%~ GRPO

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

for people learning gpu programming and especially triton should check out liger kernel by linkedin it was released last year and built on top of triton to provide pre-optimized, ready-to-use implementations gpu optimization techniques specifically tailored for llm training

doesdatmaksense's tweet image. for people learning gpu programming and especially triton should check out liger kernel by linkedin

it was released last year and built on top of triton to provide pre-optimized, ready-to-use implementations gpu optimization techniques specifically tailored for llm training

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

Excited to announce text-to-api.ai A website that turns any website into a get API with @firecrawl_dev /extract endpoint. Data on the web has never been more accessible! Thanks to @Dev__Digest, for starting this fabulous trend. Check out his GitHub repo below!


Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

OpenAI o3-mini is a good model, but DeepSeek r1 is similar performance, still cheaper, and reveals its reasoning. Better models will come (can't wait for o3pro), but the "DeepSeek moment" is real. I think it will still be remembered 5 years from now as a pivotal event in tech…


Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

OpenAI’s o3-mini is here - a significant jump forward from o1-mini Initial results (full benchmarking coming soon): ➤ Artificial Analysis Quality Index of 89, matching DeepSeek R1 and just below o1 ➤ Cheaper - $1.1/$4.4 input/output pricing per million tokens, lower than many…

ArtificialAnlys's tweet image. OpenAI’s o3-mini is here - a significant jump forward from o1-mini

Initial results (full benchmarking coming soon):
➤ Artificial Analysis Quality Index of 89, matching DeepSeek R1 and just below o1
➤ Cheaper - $1.1/$4.4 input/output pricing per million tokens, lower than many…
ArtificialAnlys's tweet image. OpenAI’s o3-mini is here - a significant jump forward from o1-mini

Initial results (full benchmarking coming soon):
➤ Artificial Analysis Quality Index of 89, matching DeepSeek R1 and just below o1
➤ Cheaper - $1.1/$4.4 input/output pricing per million tokens, lower than many…
ArtificialAnlys's tweet image. OpenAI’s o3-mini is here - a significant jump forward from o1-mini

Initial results (full benchmarking coming soon):
➤ Artificial Analysis Quality Index of 89, matching DeepSeek R1 and just below o1
➤ Cheaper - $1.1/$4.4 input/output pricing per million tokens, lower than many…

Andrea | 🇸🇪🇪🇸🇻🇪 รีโพสต์แล้ว

When working with o1/o3 models, I always have this feeling that I'm leaving a lot on the table with my prompting. Creating a long sequence of prompts for regular LLMs is good practice. This is because you don't want to overload what an LLM can process (or it'll lead to…

IntuitMachine's tweet image. When working with o1/o3 models, I always have this feeling that I'm leaving a lot on the table with my prompting.  Creating a long sequence of prompts for regular LLMs is good practice. This is because you don't want to overload what an LLM can process (or it'll lead to…

United States เทรนด์

Loading...

Something went wrong.


Something went wrong.