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, 58+ 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…...
The best coding agent still gets ~6 in 10 changes wrong. That is your review load.
2+ hour, 11+ 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…...
From SkillCheck to TraceMantle: Tracking Agent Skill Changes and Test Evidence
3+ hour, 8+ 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…...
The Model Wrote the Right Rule and My Replay Rejected It: The Extraction-vs-Replay Split
8+ hour, 27+ min ago (528+ words) CauterRule is an open-source sidecar that learns standing rules from repeated agent failures. It extracts lessons from trajectories, replay-tests them, and tries to separate reusable guidance from noisy overgeneralization. For two releases we treated "the pass rate is low" as…...
My checker blamed the other tool, and the defect was in the one doing the blaming
10+ hour, 1+ min ago (601+ words) A verifier went red and named a neighbouring tool as the cause. Three of eight rows could not be matched, and the reason code said the rows had the wrong shape. Two things were wrong with that. The neighbouring tool…...
Postman Collection to MCP: From Requests to MCP Tools
11+ hour, 1+ min ago (720+ words) A Postman collection can be a surprisingly useful starting point for an MCP server. Many teams have Postman collections before they have polished OpenAPI documentation. The collection already contains working requests, paths, query parameters, headers, bodies, example responses, and authentication…...
We Measured 31,074 Commits Looking for the AI Cleanup Tax. It Isn’t There.
7+ hour, 14+ min ago (698+ words) Agent-authored commits pull a human back to the same file 73.3% of the time within 7 days. Human commits: 71.0%. 11 repos, measured 12 Sep 2026....
Pin the Oracle Bundle Before the Agent Percentage
11+ hour, 40+ min ago (1526+ words) A coding-agent percentage is not a measurement until dataset, oracle, metrics, and environment pin are frozen as one bundle. Naked success rates behave like product screenshots because later readers cannot reconstruct the track beneath the stopwatch. The method below treats…...
When Free Inference Should Not Back an MCP Tool
11+ hour, 39+ min ago (524+ words) MCP makes that freeze easy to miss. A local function wrapped as a tool looks like a polite helper in a sidebar. After a second client generates a stub against the schema, the helper is an unofficial API. Free inference…...
Is Your Project Actually Working, or Are You Just Getting Lucky?
7+ hour, 21+ min ago (274+ words) Health-Checking Node.js Repositories with RepoDoctor A Node.js project might run smoothly on your local machine. But what happens when …...