ai agents
Joshua Morris (opens on the publisher’s site)
joshuamorris.info
-
Anthropic used Claude to make Claude about three times faster. The interesting part is who decides which of those changes are worth keeping.
-
Apple's Xcode 27.2 project format is JSON, smaller, and meant for people and coding agents to edit, with an open-source library instead of guessed parsers.
-
The interesting part of Claude Opus 5.5 is how long it can stay useful on a problem: hours of context, tools, corrections, and supervision.
-
Calif found a WeChat VoIP memory bug and, with AI, turned it into a zero-click worm that spread between phones while they were still ringing.
-
AI Agents Found an Abandoned Wiki and Turned It Into a Message Board (opens on the publisher’s site)
Researchers found roughly 18,000 posts that appear to have been written by internal OpenAI agents on an abandoned German wiki they used as a message board.
-
More than 100 organizations signed an open letter calling for stronger cyber defense as AI-enabled attacks grow—and for agent identities that are traceable and accountable.
-
Terminal-Bench-Science 0.1 grades agents on researcher-contributed workflows, not textbook Q&A—and the best system still only clears about 30% of tasks.
-
Laude’s Headlong keeps an agent thinking continuously from a small Bash harness. Shared memory enables persistence—and almost no confidentiality between users.
-
Microsoft’s Flint is an open-source visualization language that lets AI agents describe charts through a smaller human-editable spec—compiling to multiple renderers and Excel while keeping semantic types and MCP tooling in the loop.
-
Jim Nielsen on why AI agents should not get a private machine entrance to the web—arguing agent investment should fix semantics and accessibility for humans first, not invent a first-class path for models alone.
-
Reward Hacking in the Wild catalogs 3,607 user-reported incidents where AI agents optimized for apparent success—overeagerness, destructive actions, test tampering, and more—arguing constrained credentials and verification matter more than better prompting alone.
-
Alexandra Klepper introduces WebMCP, a proposed standard for sites to expose structured tools to AI agents in the open browser tab—arguing explicit, inspectable actions beat brittle screenshot-and-click automation, with a sharper security boundary when agents act inside authenticated sessions.
-
Letting an AI sign in through a full user account is the wrong direction. Give agents their own revocable tokens with limited permissions instead of sharing personal passwords and sessions.