cd/sources/read-auto-discovered· home› sources› Read (auto-discovered)
cat /sources/read-auto-discovered.feed | wc -l → 16

Read (auto-discovered)

articles 16 domain read.lukeburgis.com → feed RSS
13:31
2026-09-22
read.lukeburgis.com
ai-tools

The Vibe Coder’s Guide to Deployment

Technically.dev published the fourth installment of its six-part "Software Engineering for Vibe Coders" series, a guide explaining what happens when AI-built apps move from localhost to production, sp…

13:33
2026-09-15
read.lukeburgis.com
ai-products

What’s Google doing with AI?

Google unveiled the Gemini Enterprise Agent Platform at its Cloud Next keynote, replacing Vertex AI, which had served as its AI platform since 2023, as part of a full-stack cloud AI strategy spanning …

13:45
2026-09-01
read.lukeburgis.com
artificial-intelligence

How to use open-weight AI models

A new guide explains how to run open-weight AI models, covering model selection criteria such as parameter count, quantization, context window, reasoning variants, and tool calling, with examples like…

12:45
2026-08-25
read.lukeburgis.com
developer-tools

Software Eng for Vibe Coders: Databases + Storage

Railway sponsored a six-part series, 'Software Engineering for Vibe Coders,' which in its second part explains that databases are like spreadsheets with stricter rules, and that large files like image…

13:15
2026-08-18
read.lukeburgis.com
artificial-intelligence

What's going on with open-weight models?

Open-weight AI models from companies like Qwen and Moonshot have improved dramatically over the past two years, yet most users still rely on closed models from Anthropic and OpenAI due to their polish…

12:31
2026-08-11
read.lukeburgis.com
developer-tools

Software Eng for Vibe Coders: On Frontends + Backends

Technically launched a six-part series, "Software Engineering for Vibe Coders," to teach non-engineers how frontends and backends work and how apps can break as they scale. The first installment expla…

12:45
2026-08-09
read.lukeburgis.com
artificial-intelligence

Dispatch: Kimi K3 licensing, Liquid AI, and stacked PRs on GitHub

Moonshot AI released the weights for its Kimi K3 model with 2.8 trillion parameters and a 1M token context window under a new Kimi K3 License, which allows inference providers like Modal, Baseten, Fir…

13:35
2026-08-06
read.lukeburgis.com
artificial-intelligence

How do "computer use" agents work?

Computer use agents, which let large language models operate a full computer through screenshots, clicks, and keystrokes, remain challenging to build, as the OSWorld benchmark shows. Introduced by Ant…

14:15
2026-07-21
read.lukeburgis.com
artificial-intelligence

What's Harness Engineering?

AI models are becoming a commodity, making the software harness that wraps around them the key differentiator for real-world work, according to a technical analysis by Technically. A harness adds tool…

14:30
2026-07-14
read.lukeburgis.com
artificial-intelligence

What does Turbopuffer do?

Turbopuffer, a search engine built on object storage like AWS S3, claims to be 10x cheaper than traditional vector databases by pulling data into RAM only when needed, and has reportedly crossed $100M…

14:31
2026-06-25
read.lukeburgis.com
artificial-intelligence

Everything is a Pipeline

A technical writer argues that diverse technical systems—from data engineering pipelines to RAG-based AI products—share a common underlying structure, using stages of refinement to transform raw input…

14:30
2026-06-18
read.lukeburgis.com
artificial-intelligence

What are code sandboxes?

Code sandboxes are isolated computing environments that allow developers to run untrusted code, such as code generated by large language models, without risking security breaches or data loss. They ar…

14:31
2026-06-04
read.lukeburgis.com
ai-agents

How my non-engineering team at Sentry learned to ship

Sentry's non-engineering team migrated 2,500 marketing pages from a Content Management System to a Git repository using Claude Code and Git, despite most team members having no coding experience four …

03:34
2026-05-30
read.lukeburgis.com
ai-tools

2026 vibe coding tool comparison

Technically tested four leading vibe coding tools — Replit, v0, Lovable, and Bolt — to determine the best platform for building a business app in 2026. Replit emerged as the most feature-rich and powe…

12:15
2026-05-14
read.lukeburgis.com
ai-startups

What’s a Package Manager?

Anthropic and OpenAI have acquired package manager companies Bun and Astral respectively, signaling growing interest from frontier AI labs in these software development tools. Package managers are pro…

13:31
2026-04-30
read.lukeburgis.com
artificial-intelligence

AI, tractors, and the productivity paradox

Economists and technologists are questioning why massive investments in artificial intelligence have not yet produced measurable productivity gains, echoing a similar "productivity paradox" observed w…