AI assistants recommend packages they know, not the simplest solution. For a new generation of builders, that default is creating dependency footprints that more experienced developers would never accumulate.
Photo: CHUTTERSNAP
Anthropic's Managed Agents API handles sandboxed execution, persistent state, long-running sessions, and multi-agent coordination so teams don't have to build that infrastructure themselves.
Six months after saying he didn't use AI for coding, DHH runs multiple agents simultaneously and calls it wearing a mech suit.
MegaTrain trains 100B+ parameter models on a single GPU by treating GPU as a transient compute engine and storing model state in CPU host memory.
Anthropic launched Project Glasswing, using Claude Mythos Preview to scan foundational open source software for zero-day vulnerabilities, already finding thousands of high-severity flaws in the Linux kernel, OpenBSD, and FFmpeg.
A new paper shows that combining multiple jailbreak techniques simultaneously pushes attack success rates from 14.3% to 71.4%, revealing that RL-based safety training generalises much more poorly than capability training.
Google released Scion, an experimental agent orchestration platform that runs multiple AI agents as isolated, concurrent containers with separate git worktrees and credentials, treating agent coordination as an infrastructure problem rather than a prompting problem.
Retrieval-augmented generation solves a knowledge access problem. Most teams reaching for it are trying to solve an output reliability problem. Those are different problems with different solutions, and confusing them is expensive.
Two separate pressures — sophisticated supply chain attacks and AI-generated contribution noise — are converging on the same person: the individual maintainer holding up infrastructure that millions of projects depend on.
What GraphRAG is, why vector search alone falls short, and when you'd actually reach for it.