TypeSafe's routing verdict hinges on the price ratio
A Source Audit of Diogo Almeida’s TypeSafe coding-agent notes and a PDF built from them: the routing break-even, a withdrawn token statistic, and what the synthesis smoothed over.
Fodev JEO
LATEST INVESTIGATIONS
Source audits & field notes
mini-AGI's forgetting fix is measured on reading, not on chat
A Source Audit of mini-AGI: the no-forgetting result comes from a 0.1x trunk rate on a corpus probe, while chat learning is on by default and unmeasured.
GameDevBench's 68.8% top score is the only strictly confined row
A Source Audit of GameDevBench’s leaderboard: the new top row ran inside the strict bubblewrap box added on September 1, while the other 17 rows predate that box.
Jev shrinks the browser-agent decision loop for faster actions
A Source Audit of Jev Ultrafast and Jev Desktop: the indexed action space, the narrow matched speed result, and the boundary between faster decisions and unproven end-to-end gains.
The Sealed Lighthouse Passed 52 Checks Without Proving Fun
A D-074 audit separates engine conformance from player claims: 52/52 core checks and a 4/4 extension passed, while player benefit remains unmeasured.
MEX on macOS Broke Before Project Memory Even Loaded
A Source Audit of a real mex command collision, the resolver that fixed it, and a stale graph coordinate that only a clean rebuild exposed.
open-code-review protects Octave only if you type a space
Alibaba’s open-code-review sniffs .m files to separate Objective-C from MATLAB. Five of its twelve signals begin with #, which Octave also treats as a comment character.
Orca's privacy page survives 82 of its 83 telemetry events
Source Audit of stablyai/orca at 0d23ea6: the telemetry page’s enum-only claim holds across every event schema except one free-form field that can carry home-directory paths.
Moli's efficiency map blends two runs its own bench keeps apart
Source Audit of lexmount/moli at d56bbd7: the README’s Lexbench figures describe Moli 0.1.1 in a 1.1.7 tree, and its efficiency map joins two runs the benchmark keeps apart.
CodeBurn's $15 hard cap denies tools when it could stop Claude
Source Audit of getagentseal/codeburn at 3684f1d: the README says the hard cap stops the session; Claude Code hooks offer continue:false for that, the guard sends a per-tool deny.
인기 태그
Search article titles, categories, and tags. Full text is searched when needed.
Type to search articles.