LLM Engineering •
How to Compare LLM Architectures: 16 Models, One File Each
Compare LLM architectures fast: GQA cuts KV cache 8x on Llama 3 70B, MLA cuts it 93.3% on DeepSeek-V2. One PyTorch repo shows why, file by file.
8 min read
Read more →
AI Coding Agents & DX •
Rust LLM Policy: Use AI to Review, Not to Create
The Rust LLM policy bans AI-created code and prose but allows AI review, analysis, and bug-finding. Here's the exact rule, why it works, and how to copy it.
10 min read
Read more →
AI Security •
Fake CVE Reports: 54 of 55 SQLite Advisories Were AI Slop
Fake CVE reports are now cheaper to write than to disprove. JFrog found 54 of 55 SQLite advisories fabricated by an LLM. How to spot them before you patch.
11 min read
Read more →
LLM Engineering •
Kimi K3 vs Claude Fable 5: When the Open Model Is Worth the Switch
Kimi K3 beats Claude Fable 5 on cost by a wide margin and loses on agentic tasks. The benchmarks that decide it, and how to run K3 where it actually wins.
6 min read
Read more →
AI Engineering •
How to Build Enterprise-Grade AI Agents for Free (MaxKB, 2026)
How to build enterprise-grade AI agents for free in 2026: a hands-on MaxKB + local LLM guide to RAG precision, security, and $0 API cost.
10 min read
Read more →
AI Coding Agents & DX •
How to Switch Between Multiple Claude Code Accounts Without Re-Logging In (claude-swap Guide)
claude-swap is an open-source CLI that switches Claude Code accounts in seconds — no browser re-login. How it works, how to use it, and what it misses.
15 min read
Read more →
AI Security •
Claude Code Leak 2026: What Escaped and What Didn't
The Claude Code leak of March 31, 2026, explained: what the source-map exposure revealed, Anthropic's DMCA sweep, and the fallout.
8 min read
Read more →
LLM Engineering •
DeepSeek V4 vs US AI Models: Benchmarks, Architecture, and What It Means for the Industry
DeepSeek V4 is expected in early March 2026. Here is what is confirmed, what remains unverified, and how it challenges U.S. AI rivals.
10 min read
Read more →
AI Coding Agents & DX •
Qwen3-Coder: Run an 80B-Parameter LLM on Your Desktop
Qwen3-Coder runs 80B parameters on a desktop with only 3B active per token — and plugs into Claude Code. Why the cloud-only era of AI coding is ending.
16 min read
Read more →
AI Coding Agents & DX •
AGENTS.md Files Don't Work the Way You Think — A 138-Repo Study
A 138-repo study: AGENTS.md files hurt performance by 2-3% and raised costs 20%+. What the research found — and what actually works instead.
12 min read
Read more →
AI Security •
AI Agent Attacks Developer After Matplotlib PR Rejection — Full Story
The first documented AI agent attack on an open-source maintainer: rejected on a matplotlib PR, the bot published a hit piece. Full story and lessons.
10 min read
Read more →