» Tag
ai
1016 postsWhat Bun's Rapid Rust Rewrite With AI Teaches Engineers
How Bun rewrote 535K lines of Zig to Rust using 64 parallel AI agents and Anthropic's Fable model in just days.
ExploitGym Benchmark Tests If AI Agents Can Build Real Exploits
ExploitGym benchmarks whether AI agents can convert 869 real-world security bugs into working, code-execution-achieving exploits.
Mozilla Report: Open-Source AI Wins Tokens, Lags in Production
Mozilla's 2026 report shows open-source AI models leading in token volume but trailing closed models in production deployment.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comThe four hidden causes behind an AI agent's vanishing memory writes
Four distinct causes make AI agent memory writes vanish silently: key mismatches, compaction drops, lost-update races, and stale-read writes.
Source review of 200 self-hosted AI tools finds 78 leak tenant data
A source review of 200+ self-hosted multi-tenant AI/SaaS tools found 78 with cross-tenant data leaks via unguarded read endpoints, 31 filed as CVEs.
When AI Writes Most of the Code, Peer Review Must Be Redesigned
As AI agents write and review most production code, traditional PR-approval compliance controls no longer reflect reality—here's what should replace them.
Claude Code Review Token Bills Cut 8-49x With Tree-sitter Call Graphs
A Tree-sitter call-graph blast-radius technique cuts Claude Code review token bills 8-49x, plus three traps that can silently erase the savings.
Handbook.md benchmark shows AI agents struggle to follow long policies
Handbook.md benchmark reveals that AI agents often fail to follow long standing policy documents in realistic enterprise tasks.
Cracken Launches Blacksea, an Open-Source Honeypot for AI Attackers
Cracken releases Blacksea, an open-source honeypot that baits LLM-driven attackers into executing code on their own machines for attribution.
I Tested 11 Claude Code PPTX Skills With AI Subagents — Results
Eleven Claude Code PPTX skills tested by AI subagents reveal which produce real editable tables versus fake shape-based ones.