标签：#AI

With this new update, Google is expanding AI Mode beyond answering questions and into completing tasks across the apps they use regularly.

Companies coming to market are raising money at fastest pace this century.

You're paying $10 to $20 a month for Copilot. You don't have to. A 2024-era laptop can run a coding model good enough for autocomplete, refactors, and "explain this function" entirely offline. No API key, no telemetry, no per-token bill. Here's the exact 2026 setup I run on a 16GB machine. Why local in 2026 Two years ago, local coding models were a toy. The autocomplete was slow and the suggestions were noise. That changed. qwen2.5-coder and deepseek-coder-v2 are genuinely useful now, and the tooling caught up: Ollama serves them, Continue.dev wires them into your editor, and the whole thing runs on hardware you already own. The pitch is simple: Free. No subscription, no usage caps. Private. Your proprietary code never leaves the machine. This matters if you work on smart contracts or anything under NDA. Offline. Works on a plane, in a basement, behind a corporate firewall. The tradeoff is quality and latency. We'll be honest about both. Pick a model (and match it to your RAM) This is the decision that makes or breaks the experience. Pick a model your machine can actually hold in memory, or it spills to disk and crawls. # Fast, fits anywhere (8GB+) ollama pull qwen2.5-coder:1.5b # ~1.0GB ollama pull qwen2.5-coder:3b # ~1.9GB # The sweet spot for most laptops (16GB) ollama pull qwen2.5-coder:7b # ~4.7GB # Quality tier, needs headroom (32GB+ comfortable) ollama pull deepseek-coder-v2 # ~8.9GB (16b MoE) ollama pull qwen2.5-coder:14b # ~9.0GB ollama pull qwen2.5-coder:32b # ~20GB Rough rule: the model file size is the floor, then add a few GB for context and the OS. A 4.7GB model on a 16GB machine is comfortable. A 20GB model on the same machine is not. Model Size RAM I'd want Use it for qwen2.5-coder:1.5b 1.0GB 8GB Autocomplete, fast iteration qwen2.5-coder:7b 4.7GB 16GB Daily driver: chat, refactors, explain deepseek-coder-v2 8.9GB 32GB Harder reasoning, multi-file context qwen2.5-coder:32b 20GB 64GB Near-cloud quality, if you have the RAM deepseek-coder-v2 is a 16b m

DoorDash is opening a limited beta of dd-cli, a command-line tool that lets developers and AI agents search stores, build carts, and place orders from the terminal, marking another step toward software designed for AI agents instead of just humans.

When people think about data centers, they usually think about servers, GPUs, electricity, and AI. Very few people think about water. That realization is what led me to start building AquaStat . Why AquaStat? Modern data centers consume significant amounts of water for cooling. Depending on the technology, climate, and workload, water usage can vary dramatically from one facility to another. Finding reliable information about that usage, however, is often difficult. Some facilities voluntarily publish sustainability reports. Others release only limited information. In many cases, information is scattered across government documents, environmental reports, local news articles, permits, or community discussions. I wanted to build a platform that could organize this information into something developers, researchers, journalists, and the public could actually use. What AquaStat Is AquaStat is an API-first platform focused on collecting, organizing, and analyzing information related to data center water usage. The long-term vision includes: A developer-friendly REST API OpenAPI documentation API key management A desktop control center A command-line interface Historical tracking Source attribution for collected information Transparent methodologies A modern TypeScript ecosystem Rather than hiding calculations, I want AquaStat to explain where information comes from and how conclusions are reached whenever possible. Technical Goals I'm designing AquaStat around several principles: API First Everything should be accessible through documented APIs before being exposed through a graphical interface. Strong Documentation Documentation should be treated as part of the product, not an afterthought. Reproducible Calculations Whenever AquaStat estimates or derives values, the methodology should be understandable and repeatable. Modern Tooling The project uses a modern TypeScript stack with an emphasis on maintainability, testing, and developer experience. Challenges One of the b

Welcome to Day 4! Today is all about clean architecture, dependency isolation, and modern Python tooling. You will learn how to structure your files, control execution flows, use modern tools like uv to manage virtual environments at lightning speed, and organize a codebase like a professional software engineer. 🚀 1. Modules & Packages 📦 Module: A single .py file containing variables, functions, or classes you want to reuse. Package: A directory of modules. __init__.py : Runs automatically when a package is imported, allowing you to expose a clean top-level API and hide internal folder nesting. Absolute Import: Imports specifying the full path from the project root ( from app.core import analyze ). Preferred by PEP 8 . Relative Import: Imports relative to the current file using dots ( from .utils import clean ). Single dot . is current folder; double dot .. is parent folder. A. Core Modules & Packages 🌱 Easy Starter Example Creating a basic module and importing it: # file: calculator.py (Our module) def add ( a , b ): return a + b # file: main.py (Importing our module) import calculator print ( calculator . add ( 5 , 3 )) # Output: 8 🏛️ Real-World Example: Database Package API Exposing internal package functions cleanly using __init__.py : # Project Layout: database/ ├── __init__.py ├── auth.py (defines login_user()) └── query.py (defines fetch_data()) # database/__init__.py # Expose functions relative to this folder so users don't need deep imports from .auth import login_user from .query import fetch_data # main.py # Clean absolute package import for the end-user from database import login_user , fetch_data login_user ( " admin " , " password123 " ) B. Built-In vs. Third-Party Modules Built-In: Included with Python out-of-the-box (e.g., os , sys , json ). Third-Party: Built by the community and installed from PyPI (e.g., requests , rich ). 🌱 Easy Starter Example import math # Built-in math operations print ( math . sqrt ( 25 )) # Output: 5.0 # import requests # Th

You may have heard that OpenAI released its first piece of hardware this week. You may not have heard about the ChatGPT basketball.

Exposing your data over MCP is the easy part. Designing a tool an agent uses well is the hard part. An agent can only use a tool it can read, so the work is shaping the tool for how the model calls it, not just for the human looking at the result. These are the techniques behind @bonnard/mcp-charts and the visualize tool. Discovery-first, so the agent stops guessing An agent that guesses your schema writes wrong queries. So the first tool the agent meets is a discovery tool. It calls visualize_read_me to load the chart options, the tool schema, and worked examples before it ever calls visualize , and an explore_schema tool to learn your tables and columns before it writes SQL. The agent reads, then acts. A small set of purpose-built tools The temptation is one tool per metric, or a single tool that takes arbitrary SQL and hopes. Both fail: too many tools blow the agent's attention budget; one firehose tool gives it no guardrails. Bonnard ships a small set, discover, query, visualize, each with a narrow, obvious job. The agent picks the right one because there are few of them and each does one thing. // a small, purpose-built set, not one tool per metric server . registerTool ( " explore_schema " , { /* list tables + columns */ }, listSchema ); addCharts ( server , { runSql }); // registers visualize_read_me + visualize Compact, honest responses A tool that returns 10,000 raw rows poisons the context window and the agent's next decision. Bonnard's responses are sized for a model to read: Row caps with a completeness flag. Results are capped and tagged partial or complete , so the agent knows whether it is looking at everything. Partial-result warnings. When results are capped, the response says so and tells the agent not to sum or average the visible rows, use a measure instead. Summaries over dumps. The chart comes back with a compact text summary the model can reason over, not just an image it cannot read. Errors that guide the next action A bare "error: invalid co

Most teams connecting AI agents to their data warehouse start with text-to-SQL. The agent generates SQL from natural language, runs it against the warehouse, and returns results. It works until it doesn't: hallucinated JOINs, inconsistent aggregations, no access control, no audit trail. There's a better approach. Define your business metrics in a semantic layer, expose them via MCP (Model Context Protocol), and let any AI agent query governed definitions instead of raw tables. Then add one tool so the agent can chart the result in Claude or ChatGPT. This tutorial shows how to set it up in under 30 minutes. Why does text-to-SQL break in production? The agent sees column names but not business logic. It doesn't know that your company excludes refunds from revenue. It doesn't know that status = 'completed' means something different in orders than in subscriptions . It doesn't know that marketing and finance defined "active user" differently three years ago and never reconciled. So the agent writes plausible SQL and returns plausible numbers. Ask the same question twice with different phrasing and you get different answers. Ask two different agents and you get two different numbers. Neither matches the number your finance team reports. Beyond consistency, there's no row-level security. No multi-tenancy. No audit trail showing which agent queried what, when, and for whom. In production, with real customers, that's a non-starter. Text-to-SQL gives you speed. It doesn't give you trust. What is the semantic layer approach? Instead of letting agents write arbitrary SQL, define your metrics once in YAML: cubes, measures, dimensions, access rules. Then expose those definitions via MCP so agents query governed metrics, not raw tables. The difference: every agent gets the same answer because the metric definition is fixed. total_revenue isn't a column the agent interprets. It's a pre-defined calculation with agreed-upon filters and aggregations. When your finance team updates th

Drawing on more than a decade spent helping build some of the world's most influential AI systems, including research that later informed the development of ChatGPT, Andrew Dai explains why he believes visual AI is one of the next major frontiers in artificial intelligence.

The startup, founded in 2021, lets enterprise customers use smartphones to scan and spot vehicle damage.

Maybe just sing a silly song in a voice note instead?

A smart speaker won't save OpenAI.

While everyone in AI is chasing "superintelligence," Alexandre LeBrun, CEO of Yann LeCun’s world model startup, AMI Labs, dismisses the word.

Daniel Solove argues in the Wall Street Journal (alternate link ) that giving people control of their personal data is not an effective way to regulate privacy in this era. Instead, we need to hold companies accountable for their actions, similar to what we do with food and drug companies. Measures such as rigorous data minimization, fiduciary duties, liability for negligent or reckless technological design, liability for algorithms that cause harm, and multi-stakeholder review of technologies will be far more effective. Paper .

The FT reports Kimi K3 will be the largest open AI model from China, with a parameter count between 2 trillion and 3 trillion.

I've been hearing the word "harness" thrown around a lot lately. I assumed it just meant "the IDE" or...

The deal, which was rumored to be in the works last year, marks an important step for Apple's AI ambitions in a key market.

1Password has launched a new browser integration for Claude that allows the Anthropic chatbot to access stored security credentials like usernames and passwords. The 1Password for Claude feature means that users can authorize Claude to complete multi-step tasks like booking travel and managing online accounts on their behalf without having to manually input their login […]

Why this matters Let’s be real — most of us don’t struggle because we “can’t code”. We struggle because: we waste time on repetitive tasks we get stuck on small bugs we context-switch too much we overthink simple problems That’s where AI actually helps. Not as a replacement — but as a performance multiplier . 🤖 First, what AI is actually good at AI is not magic. But it’s really good at: generating boilerplate explaining errors suggesting improvements summarizing docs speeding up repetitive work 👉 Basically: saving your mental energy ⚡ 1. Write code faster (without burning out) Instead of writing everything from scratch: // prompt idea " create a custom React hook for localStorage " You get a solid starting point instantly. 👉 You still review it 👉 You still understand it 👉 But you don’t waste time writing boilerplate 🐞 2. Debug faster Instead of Googling for 20 minutes: Error: Cannot read property 'map' of undefined You ask AI: 👉 It explains the issue 👉 suggests fixes 👉 shows edge cases Example mindset shift Before: search → open 5 tabs → read → test → maybe fix Now: ask → get explanation → apply → move on 🧠 3. Learn way faster AI is like having a senior dev on demand. You can ask: “Explain React Server Components simply” “When should I use memo?” “What’s wrong with this pattern?” 👉 Instant explanations 👉 Real examples 👉 No fluff 🔄 4. Automate boring tasks Things you shouldn’t waste time on: writing regex generating types creating repetitive components converting data formats 👉 AI handles these in seconds 📚 5. Write better documentation Most devs hate writing docs. AI helps you: generate README files write comments document APIs 👉 Your project becomes easier to understand 👉 Your team moves faster 🧩 6. Break down complex problems Instead of getting stuck: "build a dashboard with auth, charts, and API integration" Ask AI to break it down: 👉 smaller steps 👉 clear structure 👉 less overwhelm ⚡ 7. Stay focused (this is underrated) Biggest hidden benefit: 👉 less context swi