AI — Page 24

Loop Engineering: Building AI Agents That Improve Themselves

LangChain's Sydney Runkle outlines a four-loop framework for building reliable AI agents. The ideas are older than the branding suggests — and that's the point.

Man with concerned expression next to broken laptop with red X, illustrating consequences of AI decision-making in product…

How Ramp Rebuilt Its Product Org Around AI

AI. Dev Kapoor3 months ago· 9 min read

How Ramp Rebuilt Its Product Org Around AI

Ramp's CPO Geoff Charles explains the DRI model, creative destruction culture, and why 22 PMs at 1,600 people might actually be the right ratio.

Futuristic autonomous building with tank-like treads and glowing blue tech displays, businessman pointing at cityscape at…

Replit's Self-Driving Company Blueprint Explained

AI. Dev Kapoor3 months ago· 6 min read

Replit's Self-Driving Company Blueprint Explained

Replit CEO Amjad Masad says AI agents tripled engineering output without hurting quality. Here's what the "self-driving company" model actually requires.

Man in glasses holding glowing green Nvidia GPU chip with "100X BETTER Autonomous AI" text overlay

Nvidia Cosmos 3 Edge Brings AI Inference to Robots

AI. Dev Kapoor3 months ago· 7 min read

Nvidia Cosmos 3 Edge Brings AI Inference to Robots

Nvidia's Cosmos 3 Edge runs AI directly inside robots and cameras—no cloud required. Here's what the announcement actually means, and what's still just a pitch.

Running the Mythos Coding Model Locally with llama.cpp

Yuki Okonkwo·3 months ago

AI. Yuki Okonkwo3 months ago· 6 min read

Running the Mythos Coding Model Locally with llama.cpp

The Mythos Enhanced Coding Model can now run locally via llama.cpp and Pi. Here's what that setup actually means for developers and the broader local AI shift.

Green network diagram with system monitoring nodes and "FT TECH" branding discussing AI's role in predictive problem…

AI Observability Cuts Telecom Faults by 50 Percent

AI. Bob Reynolds3 months ago· 7 min read

AI Observability Cuts Telecom Faults by 50 Percent

A New Zealand telco reports cutting IT incidents by 50% using AI-driven observability. Here's what that claim actually means—and what it doesn't.

Two giant mechas face off against a night sky with silhouetted figures below, featuring a silver robot on the left and red…

Kimi K3 Benchmarks vs. Real-World Performance

Kimi K3 Benchmarks vs. Real-World Performance

Moonshot's Kimi K3 posts frontier-class benchmarks, but early testing reveals real gaps in reliability, speed, and cost. Here's what the numbers actually show.

Split-screen comparison showing a single character in a loop versus multiple characters connected in a network graph…

Graph Engineering Explained: Beyond Loop-Based AI Agents

AI. Bob Reynolds3 months ago· 7 min read

Graph Engineering Explained: Beyond Loop-Based AI Agents

Graph engineering adds parallel multi-agent coordination to AI workflows. Here's what it actually means, when it matters, and when it's just more plumbing.

Two men pointing at a tweet from Nate Herk stating "The only kind of AI businesses actually buy" against a blue background

Selling AI Is a Storytelling Problem, Not a Tech One

Selling AI Is a Storytelling Problem, Not a Tech One

Nate B. Jones argues that AI sales stall because of weak storytelling, not weak tools. Here's what that means for agencies, operators, and C-suites.

Concerned man in glasses with hand to face against red digital security background with padlock and AI app icons,…

Kimi K3 Exposes the Real Cost of Open-Weight AI

AI. Dev Kapoor3 months ago· 8 min read

Kimi K3 Exposes the Real Cost of Open-Weight AI

Moonshot's Kimi K3 is a genuinely impressive open-weight model—and a direct challenge to every assumption the OSS AI community has built its narrative on.

A dark background with white text reading "This Is" and a yellow highlighted box saying "Huge," accompanied by a Docker…

Running Parallel AI Coding Agents Without Chaos

AI. Bob Reynolds3 months ago· 7 min read

Running Parallel AI Coding Agents Without Chaos

Running multiple Claude Code sessions in parallel creates real coordination problems. Here's the infrastructure stack that actually prevents them from breaking each other.

A cartoon king character with a blue whale crown laughs against a black background with text promoting faster computation…

DeepSeek's DSpark Squeezes More from Every GPU

Marcus Chen-Ramirez·3 months ago

DeepSeek's DSpark Squeezes More from Every GPU

DeepSeek's DSpark paper shows how smarter token verification—not more hardware—can deliver 50% to 661% throughput gains on frontier AI models.

EU AI Act: How to Tell If Your AI Is High-Risk

AI. Marcus Chen-Ramirez3 months ago· 6 min read

EU AI Act: How to Tell If Your AI Is High-Risk

The EU AI Act's high-risk classification isn't just about what your AI does—it's about how it's deployed. Here's what organizations need to understand now.

AI Agents That Fix Slow Code Before You Notice

AI. Bob Reynolds3 months ago· 9 min read

AI Agents That Fix Slow Code Before You Notice

May Walter of Hud built an AI agent that hunts production performance problems weekly and hands engineers verified fixes. Here's what that actually looks like.

Five men's headshots in a grid with "This Changes Everything" text and names including Emad Mostaque, labeled as a…

Kimi K3 and the Open-Weight AI Shakeup

AI. Dev Kapoor3 months ago· 8 min read

Kimi K3 and the Open-Weight AI Shakeup

Moonshot AI's Kimi K3 tops the AI performance frontier as a fully open-weight model. What it means for US labs, compute policy, and who builds what next.

Man with shocked expression surrounded by glowing design tool icons including animation, mobile app design, UI mockups,…

Claude Design's Major Upgrade, Assessed Honestly

AI. Bob Reynolds3 months ago· 9 min read

Claude Design's Major Upgrade, Assessed Honestly

Claude Design has expanded well beyond its original five templates. Here's what the updated platform can actually do—and where the real limits still sit.

AI Coding Tools and the Developer Skills Trade-Off

Marcus Chen-Ramirez·3 months ago

AI. Marcus Chen-Ramirez3 months ago· 6 min read

AI Coding Tools and the Developer Skills Trade-Off

New research shows AI coding tools may improve productivity while quietly eroding developer skills. What does the data actually say—and who should be worried?

Connecting MCP Servers to Claude: What It Means

Marcus Chen-Ramirez·3 months ago

AI. Marcus Chen-Ramirez3 months ago· 6 min read

Connecting MCP Servers to Claude: What It Means

MCP servers let Claude reach beyond the chat window into files, databases, and live systems. Here's what that connectivity actually looks like—and why it matters.

Man in glasses smiling next to medical scan images comparing diagnostic CT with AI-generated PET scan results, branded "AI…

AI Agents for Science Hit a Wall: the Hypothesis Problem

AI Agents for Science Hit a Wall: the Hypothesis Problem

Sina Shahandeh of Radicait explains why AI agents plateau on real scientific tasks — and the structural fix he's using to unstick them.

Red "IT'S ABSURD" text above four circular AI model logos (GLM 5.2, Grok 4.5, Fable 5, GPT-5.6-Sol) on black background

GPT-5.6 Sol, Fable 5, Grok 4.5, GLM 5.2 Compared