AWS Strands harness benchmarked against Claude Code and Codex on identical models using official data. Covers cost gaps, model swapping, and unprompted shell execution risks.
Tested on M5Stack CoreS3: routed Claude Code, Codex, and Antigravity completion hooks to StackChan via Tailscale. Fixed audio stutter by raising I2S speaker buffer to 1024.
Diffusers merged our fix for the Qwen-Image 2.1 TaylorSeer and KV cache collision in under 4 days. Notes on AI contribution guidelines, reproduction steps, and test design.
Parsed Codex CLI and Claude Code session logs on an M4 Mac mini to track subagent state, time, and tokens. In a 6.5-hour session, the parent waited 68% of the time on children; across 30 days, Codex subagents spent only 5% of active time on tools and 95% waiting on model responses.
16GB M4 Mac mini test of QwenLM's Qwen-MM-Plugins core. Claude Code adds a plugin_ prefix that breaks --allowedTools, codex exec rejects MCP calls by default. PDF, STL and video read with no API key.
Claude Code's isolation: 'worktree' subagents were fixed for reaching into the parent checkout four times, across releases from 2.1.203 to 2.1.222, with the documented scope shifting each time. I lay out what git -C, GIT_DIR, and destructive git commands each broke, from the official release notes.
Aug 4, 2026: the keyv worm hit 12 unrelated orgs in 3h43m, and the poisoned builds carried valid GitHub Actions provenance. Why rotating credentials first is the thing that triggers the payload.
1,560 edit pairs mined from Claude Code logs, 622 posts scanned with Sonnet, ModernBERT-ja-130m trained on a 16GB M4 Mac mini: zero false positives, 60% recall.
Claude Code sometimes emits a stray court token and raw <invoke> as plain text instead of running Read/Edit/Bash — a malformed tool call that never executes. How to tell it from a hung shell or a 'could not be parsed' error, on long Opus 4.8 sessions.
The May 19 Mini Shai-Hulud wave compromised 314 npm packages under @antv via the `atool` maintainer account. After rolling back lockfiles, payload entry points stay behind in .claude/settings.json SessionStart hooks, .vscode/tasks.json folderOpen tasks, systemd user services, and .github/workflows/codeql.yml. Concrete IoCs and the gh-token-monitor wipe ordering before rotation.
Tested MinishLab/semble on a 1595-md Astro blog: warm bm25 returns symbol definitions in 0.84s, hybrid mode loses `seasonalBanner` to the article corpus.
