I measured burned-in subtitle removal with PSNR. The failures are the interesting part.
Most "remove burned-in subtitles" tutorials end at a before/after. The after always looks fine as a...
Tutorials
Your AI agent says "done". Here is what I check before I believe it
⭐ GitHub: github.com/grloper/plumbgraph · open source (Apache-2.0) · by @grloper ...
We're Building AI to Replace Ourselves. What's the Plan?
Weren't we supposed to be replaced by AI by now? Or at least work less? AI agents were supposed to...
Your AI's code is "almost right". Here are 7 ways it fools you, and the 30-second check for each
The worst AI code isn't the code that crashes. Code that crashes, you notice. The worst one looks...
I ran free Claude Code with Ollama on a mini PC and a Mac M3: what actually runs, why 4 of 5 tests failed, the real wait times, and when it is worth it.
I asked Claude Code for a tiny Python file: one function, a few asserts. Nine minutes later, the...
The Tests Pass and the Code Looks Great: 6 Things I Check in AI-Generated Code Before Merging
AI-generated code has a particular way of failing. It does not look broken. It is neatly formatted,...
RAG evals that fail CI: a 30-question golden set caught 3 of 4 retrieval regressions
Originally published on RecallRun, where the full scripts and raw output are attached. How do you...
Parallel AI Coding Agents in Git Worktrees: How to Stop the Collisions
Run three AI coding agents on one machine, each in its own git worktree, and the code stays separate....
AI + Design #2: My AI Review Team Gave It 93. I Gave It 70.
Four AI reviewers, seven rounds, and a brand page they agreed beat its reference. Then I actually looked at it. What went wrong with the scoring.
9 Codex Config Keys to Set Before Your Coding Agent's First Long Task
Nine Codex config settings for a long unattended run, from approvals and network to AGENTS.md limits and secrets in the agent's shell.
I Changed One Model Pin and Ten Test Results Went Stale
From the agentdrill v0.1.0 release, part of agentic-suite: open-source, harness-agnostic security...
Five Companies to Evaluate for Connected AI Workflows: An Engineering Comparison
Connecting an AI agent to several applications creates an integration problem before it creates an...
How I Clone My Own Voice on a Laptop With No GPU (Qwen3-TTS)
Key takeaways A laptop with no GPU can run Qwen3-TTS voice cloning. Expect 3 to 6 seconds of...
I Built a RAG Assistant That Explains Your Electricity Bill — Without Letting the AI Invent Numbers
Pakistani electricity bills are hard to read even when you're technical. The total jumps month to...
How to Fix a Windows 11 Bootable USB That Is Not Booting on Lenovo X390 Yoga
Introduction Have you ever created a bootable Windows 11 USB using Rufus, only to discover that your...
Chat memory as a 41.9 MB file: building on MemT-1.0-Nano's save and reload
MemT-1.0-Nano folds past turns into a fixed-size memory you can save. What a developer decides, where it breaks, and what to measure.
Shipping Software with AI Agents: How I Built a 48-Rule Scanner in 2 Days (and What 3 Audit Teams Found)
I am a head teacher by day and a solo developer by night. Last week I shipped a real tool — a 48-rule...
Part 4: The Alert That Could Never Fire
Since the first week of this project, observability/prometheus/alerts.yml has contained this: -...
Designing a real AI kill switch: capability absence vs middleware gates
"Which guardrail framework should I use?" is the wrong question for a kill switch. The best...
My n8n Invoice Extractor Got 9 of 42 Totals Wrong. The Validation Node That Caught All 9
An invoice extractor that's right most of the time is worse than useless if you can't tell which...
India's EKA-1 and Dhīr Want AI That Works Offline, in 22 Languages — Explained Honestly
Most AI models assume you are online, speaking English, and running on someone else's cloud. India's...
Preventing Cache Stampedes Caused by Synchronized Redis TTL Expirations: Architecture and Jitter Implementation Patterns
Preventing Cache Stampedes Caused by Synchronized Redis TTL Expirations: Architecture and...
When an AI Agent Uses Your Account, Who Actually Approved the Action?
Imagine opening a business dashboard and finding this record: Refund request: R-204 Approved by:...
Deleting the File Didn't Revoke the Key: How LiteLLM 1.107.0 Shipped Malware
LiteLLM's postmortems trace 1.107.0 to an admin key deleted from a public repo in May but never revoked. The chain, and the git and gh habits that break it.