The FDE Coach blog · new articles every day
Practical guides for engineers who ship AI.
Step-by-step builds with free AI tools, what just shipped in AI and why it matters, and Forward Deployed Engineer playbooks on interviews, pay and client work.
What just shipped in AI, and why it matters for engineers.
Page 5 of 11
AI News
Why Go Is Uniquely Suited for AI-Assisted Code Generation and Maintenance
Google's analysis reveals Go's design makes it the ideal target for AI code generation. We break down why idiomatic simplicity beats cleverness for LLMs and how FDEs can exploit this for maintenance.
8 min read
AI News
H3-metal: Running Minimax-H3 Natively on Apple Silicon GPUs
H3-metal brings lightning-fast Minimax-H3 inference directly to Apple Silicon GPUs. Here’s why this matters for engineers, how to run it today, and what it means for on-device AI.
12 min read
AI News
A Working Engineer's Pattern for Using LLMs to Learn Complex Technical Topics
Stop memorizing. Start interrogating. A practical, repeatable 5-phase pattern for using LLMs to deconstruct complex technical topics, build mental models, and debug your own understanding—without hallucinating your way to production.
9 min read
AI News
How Attackers Extract Step-by-Step Reasoning from Closed-Source LLM APIs
A new attack steals the full chain-of-thought from proprietary models like GPT-4o and Claude. We break down the extraction technique, why it matters for Forward Deployed Engineers shipping LLM features, and how to experiment with it today.
10 min read
AI News
Needle2 Squeezes an Agentic LLM into 14MB for Phones, Wearables, and Robots
Needle2 packs a 4-bit quantized 3.8B parameter agent into 14MB, running on-device at 4 tokens/sec. Here's why it matters for engineers building private, offline AI features.
9 min read
AI News
Ante Packs a Full Coding Agent into a Single Binary That Runs 100% Offline
Ante is a single-binary coding agent that runs completely offline on your laptop. No API keys, no cloud, no GPU required. Here's why that matters for engineers shipping behind firewalls.
9 min read
AI News
Claude Code Auto Mode Is Now Default: What Changes for Your Agentic Workflow
Claude Code flipped Auto Mode to default. Here's what that means for engineers who ship: how to use it, when to trust it, and why it changes the FDE toolkit.
11 min read
AI News
Docker Sandboxes Give AI Agents a Disposable Runtime Without Trashing Your Host
Docker Sandboxes wrap each AI agent task in an ephemeral container, letting your code run wild without nuking your machine. Here's how they work, why FDEs should care, and how to wire them into your workflow today.
10 min read
AI News
Muse Glimmer: Run a 30B Agent Model on Your Laptop
Meta’s Muse Glimmer packs a 30B-parameter agent model that runs locally on a laptop. We break down what it is, why it changes the game for FDEs, and how to try it today.
9 min read
AI News
OpenChamber Rethinks the IDE as an Agent-Native Workspace Beyond the Chat Sidebar
OpenChamber is a new agentic development environment that treats AI agents as first-class citizens in the workspace, not just chat sidebar add-ons. Here's why that matters for engineers shipping production code.
9 min read
AI News
Triton Brings DX11 to QEMU: A Practical Leap for Windows Dev Environments on Mac/Linux
Triton is a new open-source DirectX 11 driver for QEMU, enabling GPU-accelerated Windows VMs on Apple Silicon and Linux. Here's why it matters for engineers, how to try it, and a balanced look at the state of virtualized graphics.
10 min read
AI News
AI Bots Are DDoSing Bug Trackers: How to Protect Your Public Dev Infrastructure
Scraper bots are crashing critical public dev infrastructure like Gentoo's Bugzilla. Learn how to harden your own services against AI-driven overload with rate limiting, caching, and architecture patterns that work.
11 min read
AI News
Claude Can Now Message Other Claude Sessions: A New Primitive for Agent Orchestration
Anthropic's cross-session messaging lets Claude sessions talk to each other. Here's why this primitive matters for forward-deployed engineers orchestrating complex, multi-agent workflows.
10 min read
AI News
The Real Cost of Copilot: Stop Bleeding Money on AI-Generated Boilerplate
AI coding tools promise speed but often deliver a tax: over-generated boilerplate that inflates codebases, slows CI, and burns credits. Learn the real cost and how to stop it.
10 min read
AI News
Why LLMs Can't Break AES: The Cryptographic Wall Transformers Can't Climb
An engineer's deep dive into why large language models fail against AES encryption. We unpack the fundamental mathematical mismatch between stochastic parrots and deterministic bit-flipping, and what it means for security architecture.
8 min read
AI News
Dissecting vLLM: How PagedAttention and Continuous Batching Maximize Throughput
Unpack the engineering behind vLLM's high-throughput LLM serving. We dissect PagedAttention's virtual memory trick and continuous batching's iteration-level scheduler to show why naive static batching is dead.
9 min read
AI News
Rosenbridge: The x86 Hardware Backdoor That Changes How We Trust Silicon
A deep dive into the Rosenbridge hardware backdoor hiding in x86 CPUs: how it works, why it redefines supply-chain security, and what it means for engineers who ship real products.
10 min read
AI News
WeatherNext: DeepMind's AI Cyclone Forecaster and What It Means for Engineers
DeepMind's WeatherNext model achieves state-of-the-art cyclone forecasting. We break down the architecture, why it's a scientific ML milestone, and how engineers can start prototyping with diffusion models today.
9 min read
AI News
GPT‑5.6 Sol & Luna Rollout: What Engineers Need to Know
OpenAI just upgraded GPT‑5.6 Sol and expanded Luna to free users. We break down the performance gains, the free-tier strategy, and how engineers can leverage these models today.
9 min read
AI News
AI Psychosis: When LLM Hallucinations Become a Leadership and Product Risk
LLM hallucinations aren't just funny errors—they're a systemic product risk. Learn why engineers call it 'AI psychosis,' how it threatens user trust, and practical mitigation patterns.
8 min read
AI News
LLMs Can't Jump: The Spatial Reasoning Ceiling for Vision Models
Vision-language models ace object detection but fail hard on spatial reasoning. We break down the 'Can't Jump' paper, why your RAG or robotics pipeline breaks, and how to engineer around it.
9 min read
AI News
Kitesurf: Running Agent-First Browsers Inside V8 Isolates for Secure Automation
Cloudflare's Kitesurf runs headless browsers inside V8 isolates, not containers. Here's the engineering breakdown, why it matters for secure automation, and how to try it.
9 min read
AI News
Oracle Bans AI Code in OpenJDK: The Legal and Quality Calculus for Engineers
Oracle bans AI-generated code from OpenJDK, prioritizing legal integrity and deterministic quality over LLM speed. Here's the technical breakdown of why the calculus matters for forward-deployed engineers.
7 min read
AI News
Databricks Cut AI Coding Costs 70%: The Engineer's Playbook for Cheaper LLMs
Databricks slashed AI coding costs by 70% without losing quality. Here is the technical breakdown of routing, caching, and small fine-tuned models that working engineers can apply today.
9 min read
259 articles and counting