GuidesAI Code Review Tools: What the Diff Cannot Contain
76 modules, 169 import edges. A third of them can be reviewed from the diff alone. Nine of them cannot be reviewed from a diff at all.
Aug 2211 min read
CATEGORY · 16 ARTICLES
Guides
Articles
Guides
GuidesAI Debugging Tools: 2 of 10 Failures Print Nothing
Ten seeded faults, every one a failure this project actually hit. Three produce no message for any debugger to read.
Aug 2211 min read
GuidesAI Pair Programming: 57 Human Turns, 2,650 Actions
We counted every turn in the sessions that built this site. The median run between two human sentences is 30 tool calls; the longest is 236.
Aug 2212 min read
GuidesBest AI Model for Python: 46% of the Evidence Is Django
SWE-bench Verified counted from the dataset rather than the paper. Every gold patch but one edits Python, which makes the leaderboard a Python leaderboard and almost nothing else.
Aug 1912 min read
GuidesHow AI Coding Agents Work: Model Plus Harness
One question, one model, two configurations. Removing the harness cost the right answer and 72% of the loaded context, and the loop sent the transcript three times over.
Aug 1913 min read
GuidesContext Window in AI Coding: What Actually Fills It
Nine files from one repository, measured by differencing two headless turns. The folklore constant undercounts every one of them, and the session was 31,979 tokens deep before anyone typed.
Aug 1812 min read
GuidesSWE-bench Explained: What the Score Actually Measures
The filter that builds SWE-bench keeps roughly 2.5% of the pull requests it sees. Point it at your own repository and you learn more than the leaderboard will tell you.
Aug 1712 min read
GuidesAI Coding Tools for Teams: Security, Compliance, and Rollout
Zero data retention, content exclusion, SOC 2. Every one of these controls has a documented gap, and the gap is in the vendor's own docs. Here's what to read before you buy seats.
Aug 314 min read