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 10 of 11
AI News
What AI Did to StackOverflow: Visualizing the Impact on Engineering Communities
StackOverflow's traffic graph tells a brutal story about AI coding assistants. We analyze the data, explain why Forward Deployed Engineers must adapt, and show you how to survive the shift.
7 min read
AI News
GPT-5.6 Closes a 30-Year Gap in Convex Optimization with a Prompt
GPT-5.6 didn't just compute—it reasoned about a 30-year-old convex optimization conjecture and closed it with a clever prompt. Here's what happened, why it matters for engineers building real systems, and how to apply this pattern today.
10 min read
AI News
Anatomy of a Misfeature: What Claude Code Teaches Us About AI Tooling UX
Claude Code shipped a file permission dialog that trained users to click 'Yes' without reading. Here's the engineering anatomy of that misfeature, why it matters for Forward Deployed Engineers, and how to fix it.
9 min read
AI News
Kimi K3 Tops Frontend Code Arena: How Browser Agents Are Actually Scored
Kimi K3 just hit #1 in the Frontend Code Arena with 1679 points. Here's what the score means, how the Elo system works for AI agents, and why it matters for engineers building production-grade frontend automation.
10 min read
AI News
LLM Networking with MikroTik: Automating RouterOS via Natural Language
Explore how to bridge LLMs and MikroTik RouterOS to build, validate, and deploy network configs using plain English. A practical guide for engineers and FDEs.
7 min read
AI News
Train a Gen AI Kick Drum Model on a Linux Box with 6GB VRAM
Forget the A100 cluster. Using latent diffusion and clever memory optimizations, you can train a generative kick drum model on a dusty GTX 1060. Here's the audio engineering breakdown.
8 min read
AI News
The Memory Heist: How Prompt Injection Leaks Claude's Persistent Memory
A security researcher tricked Claude into leaking its 'deepest, darkest secrets' via prompt injection. We break down the attack, why persistent memory is a juicy target for engineers, and how to think about LLM security.
9 min read
AI News
Soofi S: A Truly Open 30B Model That Tops Multilingual Benchmarks
The German AI consortium's Soofi S is a 30B open model topping English and German benchmarks. We break down the architecture, why it matters for engineers, and how to run it today.
9 min read
AI News
Schema Harness Hit ~99% on Arc-AGI-3 Without Giant LLMs – Here's How
Schema Harness cracked Arc-AGI-3 with near-perfect accuracy using structured reasoning, not massive models. Learn the architecture, why it matters for engineers, and how to run it locally.
8 min read
AI News
Training a Meta-RL Agent to Train Other Models for Under $1.3K
A solo engineer built a meta-reinforcement learning agent that trains child models, all for ~$1.3K in compute. Here's the architecture, why it matters for FDEs, and how to run it today.
10 min read
AI News
Deja Vu: SSH-Synced Agent Memory for Self-Hosted Coding Workflows
Deja Vu gives coding agents persistent memory by syncing a SQLite database over SSH. Here's how it works, why it matters for self-hosted AI workflows, and how to wire it up today.
12 min read
AI News
Classical ML vs. Neural Detectors: Spotting LLM Text Like an Engineer
Forget the AI detector snake oil. We break down a practical approach using classical machine learning to catch LLM-generated text, why it outperforms neural networks, and how to build your own.
8 min read
AI News
LM Studio Bionic: Running AI Agents with 100% Local Open Models
LM Studio Bionic lets you build and run AI agents entirely on local, open-weight models. No cloud APIs, no data leakage. Here's how it works, why it matters for forward-deployed engineers, and a hands-on guide to getting started.
9 min read
AI News
Kimi K3: What Open-Source Frontier Models Reveal About RL Scaling for Reasoning
Moonshot AI's Kimi K3 hits the open-source scene with frontier-level reasoning. We dissect its RL scaling recipe, multimodal MoE architecture, and what it means for engineers shipping real products.
9 min read
AI News
Inkling Open-Weights: What a New Contender Means for the Model Landscape
Thinking Machines just dropped Inkling, an open-weights model built for reasoning. We cut through the noise to show engineers what actually changed, how to run it locally, and where it fits in your stack.
10 min read
AI News
Inside Grok Build: Why xAI Open-Sourcing Its Agent Toolkit Matters
xAI just open-sourced Grok Build, the internal orchestrator behind their agent workflows. Here's the engineering breakdown: what it is, why it flips the script on agent design, and how to run it locally today.
9 min read
AI News
The Memory Heist: How Indirect Prompt Injection Extracts Claude's Persistent Context
A walkthrough of indirect prompt injection against Claude's persistent memory, why it's a critical vector for forward-deployed engineers, and how to exploit and mitigate it in production LLM pipelines.
12 min read
AI News
Running a 26B LLM on a 13-Year-Old CPU: The Inference Optimization Stack
How Neomind Labs coaxed 5 tokens/sec from Gemma 4 26B on an ancient Xeon with no GPU. We break down the quantization, caching, and kernel stack that makes it possible—and what FDEs should steal from it.
12 min read
AI News
Why DSLs Are the Missing Link for Production-Grade LLM Applications
LLMs are probabilistic, but production systems demand determinism. Learn how Domain-Specific Languages bridge the gap, turning unreliable natural language into structured, verifiable outputs that forward-deployed engineers can actually ship.
8 min read
AI News
Linux 0.11 in Idiomatic Rust: Booting a Memory-Safe Kernel
A developer rewrote Linux 0.11 in idiomatic Rust, booting it in QEMU. We dissect the architecture, why memory safety in kernel space matters for FDEs, and how to run it today.
8 min read
AI News
George Hotz on LLMs: Loving the Tool, Hating the Hype—An Engineer's Reality Check
George Hotz just dropped a raw, engineer's take on LLMs: love the utility, hate the hype. We break down his post, why it matters for FDEs, and how to build useful things without drinking the AGI Kool-Aid.
9 min read
AI News
Cursor 0-Day: Why Full Disclosure Became the Only Defense for Dev Tools
A critical Cursor IDE vulnerability exposed how agentic tools can be hijacked. We break down the attack, why it matters for forward-deployed engineers, and how to harden your local dev environment today.
9 min read
AI News
Coding Agents That Plan Ahead: What Anticipatory Reasoning Means for Engineers
New research shows LLM coding agents don't just react—they plan ahead. We break down the paper's findings on anticipatory reasoning, why it matters for building reliable agentic systems, and how to try it today.
11 min read
AI News
OpenAI Codex Encrypts Sub-Agent Prompts: A Hard Look at Agent Security
Codex now encrypts sub-agent prompts, closing a critical side-channel. Here's why it matters for agentic architectures, how to test it, and the real-world implications for FDEs building secure systems.
9 min read
259 articles and counting