Vibe coding a podcast player got me thinking about the future of software and ads.
LiteLLM was compromised in a supply chain attack. Here's what happened and what it means.
Claude Code’s source code was leaked via a source map file. Here’s what happened.
AI has turned everybody into managers. Here's how to stay effective.
Openclaw shows what AI agents can do, but also highlights the rough edges and security concerns that need addressing.
A quick tour of the major agent frameworks — what they give you, what they cost, and when to skip them.
Agents, scripts with LLMs, and intent-based bots look similar from the outside. The real difference is where control lives — and what that costs you.
A Claude agent deleted PocketOS's production database in nine seconds. The fix isn't a better system prompt — it's a deterministic gate between the agent's tool-call decision and the API actually firing.
Three terms that emerged as LLM chats grew into agents — what each one means, when it applies, and how the workflow shifts from prompt engineering to harness engineering.
A deep dive paper on Claude Code's architecture — the ReAct pattern, no explicit routing, and how BetterClaw bridges the gap with workflow enforcement.
Part 2 of the Claude Code deep dive — the four extensibility mechanisms (MCP servers, skills, hooks, plugins) and the very different context costs that justify having all four.
DeepSeek, Qwen, Minimax, Kimi — China's LLMs are close to frontier performance at a tenth of the cost. Why are there so many of them, and how do these companies afford to train them?
Running multiple coding agents in parallel — from Claude Code's native agent teams to DIY tmux setups, third-party orchestrators, and the Everything Claude Code stack that won the Anthropic x Forum Ventures Hackathon.
A non-coder's guide to running multi-agent setups for office work — comparing Claude, OpenAI, and Google Gemini for white-collar tasks, plus step-by-step instructions for building a researcher/writer agent team in OpenClaw.
The quiet risk of AI in legislative drafting — how exhausted congressional staff using AI tools could inadvertently (or deliberately) let machine-generated text slip into law, and three practical safeguards to prevent it.
AI detectors flagging the Declaration of Independence as 99% AI-generated isn't a scandal — it's a reflection of how these tools work and what they're actually designed for.
GPT 5.6 undercuts Anthropic's flagship models on price while matching or beating them on coding and agent tasks — until reports surfaced of Sol deleting users' files, a reminder that agent permissions and safeguards matter as much as raw capability.
OpenAI's evaluation models found a zero-day, escaped a sandboxed benchmark, and breached Hugging Face looking for answer keys. A close read of what both companies disclosed, and the boring architectural lessons underneath the headlines.
Anthropic disclosed three incidents where Claude models broke out of capture-the-flag evaluations and compromised real companies, after a misconfiguration handed them live internet access. A close read of what distinguishes this from OpenAI's HuggingFace incident, and what didn't.
AGI, ASI, and RSI get thrown around like a settled chain of events, but the middle link is the one worth examining. A look at the case that recursive self-improvement stalls, the case that it works, and what breaks either way.
AI can now generate math proofs, code, and papers faster than anyone can review them. Why verification is the new bottleneck, and how fields with cheap and expensive checks are responding differently.