Por que coisas como TypeSafe IA não me interessam
Por que coisas como TypeSafe IA não me interessam#inteligencia-artificial#agentes-de-codigo#llms16 de setembro de 2026 · 💬 Participe da DiscussãoSe t
Por que coisas como TypeSafe IA não me interessam#inteligencia-artificial#agentes-de-codigo#llms16 de setembro de 2026 · 💬 Participe da DiscussãoSe t
The product of four consecutive Fibonacci numbers equals the product of two consecutive integers. For example, 3 × 5 × 8 × 13 = 39 × 40. I ran across
Global Admins and external users now have another five months before Microsoft switches off its SMS and voice authentication service. The original ver
The long wait (what am I talking about, it feels like I got the acceptance email just yesterday!) is finally over and the HELish Summit 2026 is tomorr
TL;DR Hybrid cloud becomes difficult to operate when several platforms appear to own the same lifecycle, identity, or policy decision. Define the resp
An application no longer needs broad access to Microsoft 365 group properties just to build a group picker or check a groups membership. Microsoft jus
On learning programming in an age of LLMs by Mark Seemann Open answers to a reader's letter. A reader recently wrote me a long letter with lots of que
TL;DR An AI agent is not dependable simply because it can reason, call tools, and retry. It needs a feedback architecture that connects an approved go
DevframeOne Definition, One Standard Handler, Many AdaptersAdapters as ConveniencesVisual and AgenticBuilt-in PluginsData InspectorTerminalsAccessibil
15th September 2026 Tool Gemini Live audio Google released Gemini 3.8 Live and 3.8 Live Extended Thinking today - two new speech-to-speech models that
The previous post looked at how to interpret cosine similarity, or equivalently angles between word vectors. In a high-dimensional space, randomly cho
Important for programmers to remember Posted on September 15, 2026 by Jesse Liberty No one ever wanted a ⅛ inch drill bit. What they want is a ⅛ inch
Novo LLM Benchmark v4: retestando TODOS os principais LLMs (Parte 1)#benchmarks-de-llm#llms#agentes-de-codigo15 de setembro de 2026 · 💬 Participe da
Novo LLM Benchmark v4: retestando 39 LLMs (Parte 2)#benchmarks-de-llm#llms#agentes-de-codigo15 de setembro de 2026 · 💬 Participe da DiscussãoSe tem p
Sponsor: Do you build complex software systems? See how NServiceBus makes it easier to design, build, and manage software systems that use message que
Learn how to prevent silent database value truncation in ColdFusion by adding boot-time assertions in Application.cfc for MySQL datasources.
METR's chart has an axis nobody used to plot: how long a task an AI agent can finish on its own. The doubling time is 7 months, traced from GPT-2 thro
Analysis of Apple's 'Surprise and Shine' event, covering iPhone 18 Pro, AirPods 5, Apple Watch Series 12/Ultra 4, and Tim Cook to John Ternus transition.
With our annual OS reviews out of the way, Federico and I will be covering our favorite indie apps that take advantage of Apple’s latest OS features.
Machine learning represents words as vectors and measures the similarity of words by the angles between the vectors. For vectors x and y, where θ is t