My previous submission, months ago with transformers.agents on GPT-4o scored a bit over 40% ont the same benchmark. We've been a long way since then with smolagents!
MACHINE LEARNING
-
Top Strategic Technology Trend for 2025 by Gartner
By
–
Top Strategic #Technology Trend for 2025
by @Gartner_inc #ArtificialIntelligence #MI #MachineLearning #Tech #Technology cc: @chr1sa @karpathy @marcusborba -
Neural Networks, Data, and GPUs Enable Modern AI Revolution
By
–
Very honored by this recognition, along with the fellow recipients. The convergence of Neural Network algorithms, Data and GPU chips has enabled the (re)birth of modern AI, so that this powerful technology can help empower people and enhance our lives and work.
-
Blockchain and AI: The Convergence of Two Transformative Technologies
By
–
Where Blockchain Meets AI: Exploring The Convergence Of Technologies
#blockchaintechnology #blockchains #blockchainrevolution @demishassabis @Ronald_vanLoon @TamaraMcCleary @geoffreyhinton @goodfellow_ian @jeffdean @erikbryn http://
ow.ly/IYy030sJE9B -
Hugging Face Releases Open Deep Research Agent Framework
By
–
Our blog post: https://
huggingface.co/blog/open-deep
-research
… Code here: https://
github.com/huggingface/sm
olagents/tree/main/examples/open_deep_research
… -
DABStep: Challenging Benchmark for LLM Data Analysis
By
–
Can state of the art AI LLM models solve today real world data analysis problems? Well unfortunately it seems like no. DABStep: A new extremely challenging benchmark for model training teams
-
AmbiStack System Uses AI and Reinforcement Learning for Package Placement
By
–
Great summary Lukas! The new AmbiStack system uses @AmbiRobotics’ PRIME-1 Generative AI model trained on 20,000 hours of real robot data for perception and a Reinforcement Learning model for highly efficient package placing (a 3D variant of playing Tetris;). https://t.co/DxPmvXuQuM
— Ken Goldberg (@Ken_Goldberg) 4 février 2025Great summary Lukas! The new AmbiStack system uses @AmbiRobotics
’ PRIME-1 Generative AI model trained on 20,000 hours of real robot data for perception and a Reinforcement Learning model for highly efficient package placing (a 3D variant of playing Tetris;). -
Andrew Ng Speaking at INTERRUPT Conference on LangChain
By
–
A year ago, I had the honor of doing a DeepLearning course on LangChain with @AndrewYNg It will be an even bigger honor to have him speak at INTERRUPT this May He's one of the best educators of our generation, no better time to learn from him Tickets: https://
interrupt.langchain.com -
Reinforcement Learning Advances Robotics to New Heights
By
–
Reinforcement learning takes #Robotic to the next levels
— Ronald van Loon (@Ronald_vanLoon) 4 février 2025
by @IntEngineering
#AI #ArtificialIntelligence #Robotics #Tech #Technology #Innovation
cc: @marcusborba @amuellerml @bernardmarr pic.twitter.com/NvYq96WFdIReinforcement learning takes #Robotic to the next levels
by @IntEngineering #AI #ArtificialIntelligence #Robotics #Tech #Technology #Innovation cc: @marcusborba @amuellerml @bernardmarr -
Synthetic Data and AI Protect Right Whales from Boat Strikes
By
–
What does #SyntheticData have to do with balancing commerce and conservation? See how SAS combined this #GenerativeAI tech with Machine Learning to help #DataForGood partner Fathom Science validate its efforts to protect right whales from boat strikes.