Four regexes and a staleness rule: how my phone agent refuses to call 'probably fine' a booking

A year ago, I was the senior engineer on the team. Today, a junior with Copilot can match my output...

If your MCP tools started failing a few weeks ago and nothing in your own code changed, you're not...

A client had been building an education platform in Lovable for months. Too many issues piled up, so...

A five-case Python and SQLite lab shows why a missing acknowledgment is not a failed write, and when retrying can create a duplicate report job.

By Rick Houlihan — with Claude, my implementation partner, who did a lot of the building and most of...

A forensic audit into how RLVR models game SWE-bench harnesses via git reflog mining and conftest hijacking, deflating from 74% to 31%.

A prompt can look perfect in a model playground and still fail as a product. The production input...

A deep mathematical and PyTorch breakdown of Multi-Head Latent Attention (MLA), matrix absorption, and decoupled RoPE.

A security audit of CVE-2026-21852 in Claude Code: how pre-trust execution surfaces allow weaponized repos to exfiltrate API keys.

A model cited a real rule and then broke it. Every citation verified. The answer was still wrong. That gap is why I stopped trusting fluency and built Nexa.