Install
Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
I made two AIs review each other's code for 30 days. A human still caught the bug in 5 minutes.
1+ hour, 43+ min ago (905+ words) Last month I let AI write 100% of my code for 30 days. The single loudest lesson wasn't "AI is amazing" or "AI is useless." It was one sentence: the thing that writes the code can never be the thing that reviews…...
Record why an approach was rejected—and when to revisit it
1+ hour, 38+ min ago (564+ words) Disclosure: I maintain Selvedge, an open-source decision-history tool. This article was prepared with AI assistance from Grok and Codex. The example below is hypothetical and uses plain Markdown; it does not require a particular product. A repository can show what…...
The best coding agent still gets ~6 in 10 changes wrong. That is your review load.
1+ hour, 56+ min ago (244+ words) While tech review articles argue about what PR length is safe to let an agent produce, the review problem is set by a simpler number: how often the agent is wrong. Specific Labs' Real-SWE benchmark, published September 2026, runs frontier agents…...
56 fault-injection tests passed. The one that injected nothing failed.
2+ hour, 12+ min ago (415+ words) I was building a tool that detects when data quietly changes meaning — a vendor switching units, a source dropping a field, an undocumented enum appearing. The kind of failure where every test passes and every job is green. Claims about…...
From SkillCheck to TraceMantle: Tracking Agent Skill Changes and Test Evidence
2+ hour, 54+ min ago (637+ words) I’ve renamed SkillCheck to TraceMantle and expanded its scope. The original project focused mainly on validating AI agent skill files. TraceMantle retains that functionality and adds support for tracking the files in a skill package, comparing changes, and checking whether…...
Where AI review pays: the codebase matters more than volume
5+ hour, 39+ min ago (329+ words) The question I keep getting is how a team can review the growing volume of AI-generated code. Most answers start with throughput: faster review tools, more automated checking, larger batches. That assumes the problem is volume. The review I read…...
Fixing the Proxy Deleted the Objective: The Style Review Removed a CTA and Every Accuracy Gate Passed
6+ hour, 17+ min ago (181+ words) Originally published on hexisteme notes. Closing this out took more than restoring the CTA. Four changes, each aimed at a different point where the same shape of failure could recur: And I split the downstream metric so "no data yet…...
Your Model Is H.M. in Reverse.
1+ hour, 49+ min ago (494+ words) He kept the past and lost the power to add to it. Pretrained models were born the other way around — and neither has the organ that turns what happened into what is …...
Stress Test? Pen Test? Yes Tests!
7+ hour, 42+ min ago (686+ words) Published on DHSeaDev. A hard-won lesson from shipping a browser-based TCG. When we stress-tested Prismwar, our original gate suite reported everything was fine. Then we ran a mutation campaign, and 31 out of 70 carefully crafted bugs survived without raising a flag....
I built a ReDoS scanner that proves each bug offline — and hands you a verified fix
8+ hour, 46+ min ago (442+ words) A regular-expression denial-of-service bug is a regex whose backtracking engine can be pushed into super-linear (often exponential) time by a short, hand-crafted input. The textbook shape is a quantifier inside a quantifier: The scary part is that these patterns look…...