Skip to content

Search

ESC

All Posts

22 posts
Stylised cross-section of a xenon time projection chamber with a single bright recoil flash, electrons drifting up to a second flash at the liquid surface, and a dashed incoming particle labelled WIMP?
20 min

LZ Caught One Event It Can't Explain. Is It Dark Matter?

A mile underground, LUX-ZEPLIN logged a single 248 keV recoil that no background it has studied can explain. What the 2.6-sigma hint means, and what it doesn't.

Read
Diagram of one glowing model core splitting into two labelled deployments: Fable 5.1 behind a shield marked safeguards on and generally available, and Mythos 5.1 behind a padlock marked invite only, Project Glasswing
30 min

Claude Fable 5.1: One Model, Two Names, Three Breaking Changes

Anthropic's Fable 5.1 ships with 75% cheaper cache reads, a safeguards layer your code must handle, and API changes that break history-editing harnesses.

Read
Stylized neon toothbrush with a camera lens firing a jet at the gap between two teeth framed by a viewfinder
9 min

Dyson CameraJet: A £420 Toothbrush With Computer Vision

Dyson's first toothbrush pairs a 100,000-pixel camera with machine learning to spot gaps and jet mouthwash at them. How it works, and how rivals compare.

Read
Diagram of stateless MCP: self-contained requests flowing through a load balancer to interchangeable server instances, with a session box crossed out
6 min

MCP Grows Up: What's Changing in the 2026-07-28 Spec

The biggest MCP revision since launch goes stateless, formalizes extensions, hardens OAuth, and deprecates three core features. What matters in production.

Read
Stylized lightning bolt over a dark dotted grid, representing the Zig programming language
6 min

Zig in 2026: Colorless Async I/O and the Road to 1.0

Zig 0.16 lands colorless async I/O, 30ms incremental rebuilds, and a maturing toolchain. What changed, what broke, and how close 1.0 really is.

Read
Dynamic workflows diagram: a prompt fans out to parallel agent() calls, passes an adversarial verify gate, then converges to a single synthesized result
23 min

Inside Claude Code's Dynamic Workflows

Claude Code can now write its own multi-agent harness — fanning out subagents, verifying their work, and returning one answer. A sourced deep dive.

Read
HTTP/2 Bomb banner: one connection firing thousands of tiny frames into a server whose memory overflows
22 min

HTTP/2 Bomb: Remote Memory-Exhaustion DoS (CVE-2026-49975)

A single HTTP/2 connection from a home laptop can pin tens of gigabytes of server RAM in seconds. How the AI-discovered HTTP/2 Bomb works and how to defend.

Read
CVE-2026-44578 banner: Next.js WebSocket SSRF security advisory
26 min

CVE-2026-44578: Next.js WebSocket SSRF

High-severity (CVSS 8.6) SSRF in the Next.js WebSocket upgrade handler lets unauthenticated attackers proxy GETs to internal services on port 80.

Read
Stack of npm packages with a compromised, cracked package leaking corruption in the middle
10 min

TanStack npm Supply Chain Attack: Detect, Fix, and Recover

On May 11, 2026, attackers published 84 malicious versions across 42 @tanstack/* npm packages. Here is how to detect compromise and recover safely.

Read
Supply chain attack warning with broken chain links
5 min

LiteLLM Supply Chain Attack: How to Check If You're Affected

Malicious LiteLLM versions were published to PyPI on March 24, 2026. Here's what happened, how to check if you're affected, and what to do.

Read
A developer workspace with AI coding tools
2 min

Getting Started with AI-Assisted Development

A practical guide to using AI coding tools effectively in your development workflow.

Read
Futuristic developer workspace with AI assistants
5 min

The Next Generation of Developer Tools

How AI-native IDEs, agentic workflows, and autonomous coding are reshaping software development.

Read
Safety system architecture with monitoring dashboard
4 min

Engineering Responsible AI Systems

Practical techniques for building AI systems with bias detection, safety guardrails, and monitoring.

Read
Training loss curve visualization
4 min

Fine-Tuning Models for Your Domain

When and how to fine-tune language models using LoRA, including dataset preparation and evaluation.

Read
Agent architecture flowchart diagram
4 min

Designing AI Agent Architectures

Patterns for building reliable AI agents with tool use, memory, and multi-step reasoning capabilities.

Read
Server hardware with GPU computing setup
4 min

Running AI Models Locally: A Complete Guide

How to run open-source LLMs on your own hardware using Ollama, llama.cpp, and quantized models.

Read
Test suite dashboard with AI insights
3 min

AI-Powered Testing: Beyond Unit Tests

How AI transforms software testing with automated test generation, property testing, and intelligent fuzzing.

Read
Data pipeline architecture diagram
3 min

Building RAG Systems from Scratch

A step-by-step guide to building retrieval-augmented generation systems with vector databases.

Read
CI/CD pipeline visualization with AI integration
3 min

Automated Code Review with AI

How to integrate AI-powered code review into your CI/CD pipeline for consistent quality checks.

Read
Code editor with AI prompt patterns
3 min

The Developer's Guide to Prompt Engineering

Practical prompt patterns and techniques for building reliable AI-powered features in production.

Read
Abstract neural network visualization
4 min

How Large Language Models Actually Work

A clear explanation of transformer architecture, attention mechanisms, and tokenization for developers.

Read