Andrea | 🇸🇪🇪🇸🇻🇪 @aicoding_

Computer Vision Engineer currently working as a Machine Learning Engineer. https://t.co/xLVKLO30rv https://t.co/DiKrU5Eya5 youtube.com/channel/UC8FB3… Joined July 2016

Tweets

209
Followers

453
Following

126
Likes

7

Xiang Yue @xiangyue96

7 months ago

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…

11 72 313 23K 232

Download Image

Unsloth AI @UnslothAI

7 months ago

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…

16 185 858 67K 816

Download Image

ILIAS ISM @illyism

7 months ago

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.

83 283 5K 555K 11K

Download Image

Ivan Fioravanti ᯅ @ivanfioravanti

7 months ago

🔥 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

72 136 1K 462K 671

Download Video

Dimitris Papailiopoulos @DimitrisPapail

7 months ago

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!

19 148 1K 166K 926

Download Image

Sam Altman @sama

7 months ago

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.

2K 2K 27K 3.2M 3K

Seunghyun Seo @SeunghyunSEO7

7 months ago

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.

4 52 373 39K 327

Download Image

LangChain @LangChainAI

7 months ago

📚🤖 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…

5 161 712 61K 796

Download Image

Andi Marafioti @andimarafioti

7 months ago

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…

34 217 1K 98K 919

Download Image

AK @_akhaliq

7 months ago

OpenAI o3-mini System Card

13 72 368 47K 102

Download Image

Han Xiao @hxiao

7 months ago

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…

161 272 3K 603K 2K

Download Video

elvis @omarsar0

7 months ago

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.

15 143 665 65K 770

Download Image

Gabriel Massadas @G4brym

7 months ago

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.

31 64 732 115K 502

Download Video

AK @_akhaliq

7 months ago

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

142 432 4K 814K 2K

Download Video

anton @abacaj

7 months ago

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

41 111 1K 107K 661

Download Image

Antaripa Saha @doesdatmaksense

7 months ago

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

9 65 640 33K 579

Download Image

Caleb Peffer (Hiring!) @CalebPeffer

7 months ago

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!

38 204 2K 234K 4K

Download Video

Lex Fridman @lexfridman

7 months ago

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…

1K 1K 14K 1.5M 2K

Artificial Analysis @ArtificialAnlys

7 months ago

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…

24 64 413 79K 128

Download Image

Carlos E. Perez @IntuitMachine

7 months ago

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…