AI Research Posts

🦸🏻#11: How Do Agents Plan and Reason?

How AI agents plan and reason: chain-of-thought, ReAct, hierarchical planning, neuro-symbolic AI, and DeepSeek R1's RL approach — with practical examples

What Is Mixture-of-Mamba and How Does It Work?

Mixture-of-Mamba (MoM) brings modality-aware sparsity to Mamba SSM, cutting FLOPs by up to 75% while improving accuracy across text, image, and speech tasks.

🌁#88: Can DeepSeek Inspire Global Collaboration?

we highlight the overlooked impact of DeepSeek’s surprise release on countries like Korea, Japan, and those in Europe and what it might mean for the global open-source community

🦸🏻#10: Does Present-Day GenAI Actually Reason?

Can present-day GenAI actually reason? We break down ~30 modes of human thinking, which ones LLMs reproduce, and where AI reasoning still falls short

Why NVIDIA Blackwell on CoreWeave [💡Webinar ]

Unlock the full potential of your AI innovations

What are Chain-of-Agents and Chain-of-RAG?

CoRAG and Chain-of-Agents are two upgrades to standard RAG: one masters multi-hop reasoning, the other handles extremely long contexts. Compare both

🌁#87: Why DeepResearch Should Be Your New Hire

– this new agent from OpenAI is mind blowing and – I can't believe I say that – worth $200/month

How to Fine-tune DeepSeek with Reinforcement Learning [webinar]

What is test-time compute and how to scale it?

We dive into test-time compute and discuss five+ open-source methods for its effective scaling for deep step-by-step models' reasoning.

🌁#86: Four Freedoms of Open AI

– what are they? Defining the future

eBook: Mastering AI Agents

Learn how to create powerful, reliable AI agents with Galileo's in-depth eBook

LLM Prompt Optimization Techniques: The Four Pillars

Prompt optimization techniques for LLMs: expansion, decomposition, disambiguation, and abstraction, plus automated optimizers like DSPy, GEPA, and MIPROv2.