Developers and customers building production AI agents need higher token efficiency, lower latency, and more reliable performance. Our Flash series of models is built to meet the sweet spot of efficiency and quality to enable scaling agentic workflows. Building on Gemini 3.5 Flash, we’re introducing new Gemini models: 3.6 Flash: Our workhorse model that delivers …
model predicts the missing column of any table, zero-shot, the way a language model completes text. On the main community benchmark, every single-model entry above the best tuned gradient-boosted tree is now one of these. This post explains what they are, verifies the strongest one with unrestricted open weights on my own hardware, and maps …
Tabular LLMs: An Introduction to the Foundation Models That Predict Your Spreadsheet Read More »
Contents# Introduction# 1. Tool Use and the Model Context Protocol# 2. Memory and Context Engineering# 3. Planning and Reasoning Loops# 4. Multi-Agent Orchestration# 5. Evaluation, Observability, and Guardrails# Wrapping Up # Introduction If you ask a chatbot to find you a hotel in London, it will give you a list of names and let you do the rest. If you ask an …
5 Key Concepts Behind Agentic AI Every Engineer Must Understand Read More »
Scientists today face challenges of extraordinary scale and complexity. From shaping and simulating the intricate dynamics of fusion plasma, to exploring the vast search space of new materials, to making sense of the exabytes of data pouring out of the world’s most advanced experimental facilities. The demands on modern research are unprecedented. Frontier AI can …
Contents1. The number you should not trust2. Agent skills are a new software supply chain3. How SkillSpector scans a skill3.1 Two kinds of check run in parallel3.2 A fourth pass decides what is real3.3 How the score is calculated4. How SkillSpector compares to other tools5. Testing setup5.1 The three skills, and why I picked them5.2 …
Contents# Introduction# 1. Harvard’s CS50: Introduction to AI with Python# 2. Google’s Machine Learning Crash Course# 3. fast.ai’s Practical Deep Learning for Coders# 4. The Hugging Face NLP Course# 5. ndrej Karpathy’s Neural Networks: Zero to Hero# Wrapping Up # Introduction The barrier to entry for learning artificial intelligence has never been lower, but the signal-to-noise ratio has never been worse. With …
5 Free Courses to Go From AI Beginner to Practitioner Read More »
ContentsThe ScenarioThe data sourceDo it in Power QueryThis is not practicalDo it in DAXConclusionReferences The Scenario to report on seat ownership. Each seat in the office building must be assigned to an organisational unit (OU). There is a list of all seats, and the owning OU should be set for each seat. But some seats …
Automatically Assign a Category to Uncategorized Rows in Power Query and DAX Read More »
The European Commission’s latest draft guidelines provide much-needed clarity on how organizations should classify high-risk AI systems under Article 6 of the EU AI Act. However, they also raise an important question for enterprises: could your existing AI systems already be considered high-risk without you realizing it? The answer may depend on more …
Could Your AI Systems Already Be High-Risk Under the EU AI Act? Read More »
, I will give my first impressions of the newest OpenAI model, GPT-5.6. The model was released a few days ago, and I’ve gotten the chance to test it extensively since the release and compare it against other models such as GPT-5.5, Opus 4.8, and Fable 5. I’ll give my judgment on the model, share …
Contents# Introduction# AI Agents for Beginners (Microsoft)# Hugging Face AI Agents Course# Building Effective Agents (Anthropic)# Multiagent Systems (Shoham & Leyton-Brown)# Google & Kaggle Agents Whitepaper Series# Where to Go Next # Introduction Everyone is building agents. Far fewer people can explain, precisely, why their agent loops forever, ignores a tool it was given, or confidently reports success on a task it …
