Three months of agent-run decompilation applied three controls in sequence: a reviewer agent, a byte-matching oracle, then a hash on the oracle itself. The agents got around each one a different way, and the author’s replies in the comments disclose the stronger oracle he abandoned.
Stripe says its internal agent is connected to 1,000+ skills. Its infrastructure vendor reports quality degrading past 150. A close read of both posts.
Meta’s engineering write-up for Muse states its premise in one line: two isolated security domains on one box, not an LLM powered agent with root. A walk through what that means in practice.
Linear’s engineers found that faster code generation just moved the wait. An account of what happened when the bottleneck shifted downstream.
A 35-author arXiv paper calls graph engineering a new paradigm; LangChain says it is the latest name for what LangGraph has done since 2023. Both have a point.
A developer turned off Claude Code automatic memory and called it his best upgrade - because inferred memory is an invisible layer between a decision and its reason.
An open-source memory layer where memories fade on a 7-day half-life unless retrieval keeps them alive - and an unrelated arXiv paper that independently landed on the same idea.