agent
Joshua Morris (opens on the publisher’s site)
joshuamorris.info
-
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.
-
Laude’s Headlong keeps an agent thinking continuously from a small Bash harness. Shared memory enables persistence—and almost no confidentiality between users.
-
The July MCP spec makes remote servers ordinary HTTP. The harder problem is issuing sub-agents verifiable, narrow authority instead of one giant user token—and that is what makes real autonomy safe enough to want.
-
Vercel Labs’ fx is a 6.39 MiB Zig coding-agent harness with a microsecond cold start—Unix command, not an IDE in a terminal, and small enough to embed.
-
Cloudflare Gateway can detect MCP traffic, log destinations, apply DLP, and force approved paths through MCP Portals—treating agent tool access as privileged network traffic instead of hoping every client is configured safely.
-
OpenAI’s Codex is becoming one persistent agent across ChatGPT, editors, and terminals—with native Linux sandboxing via seccomp and Landlock—while I wait for the heavier new ChatGPT app on Windows to settle before chasing every release.
-
Prime Intellect’s open-source Prime Agent treats prompts, skills, memory, and sub-agents as editable harness state—with a Factorio cheat that shows how self-improvement can amplify reward hacking when the metrics are exploitable.
-
Cloudflare OS is a browser-based AI agent workspace on Cloudflare’s platform: Durable Objects, AI Gateway, MCP, sandboxes, and untrusted execution—not chat boxes, but persistent workspaces as an operating layer for AI at work.
-
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.
-
Anthropic cut most of Claude Code’s system prompt for Claude 5-generation models without coding-eval loss—arguing prompts and agent configs must be retested per model, not copied across LLMs as if one format were durable.
Joshtronic (opens on the publisher’s site)
joshtronic.com
-
This journey starts like most of the things I've been doing this year, as an experiment to run a website 100% unattended with an agent. Ideally this post won't go down as an epitaph in a future where robots hunted down unsuspecting humans named Josh. I'm aware of "claws" and I know I could probably just boot up Claude Code with a /goal or /loop prompt like: build and maintain an awesome website, a
-
Building my own agent has been fun. Sure, I could have opted for an off-the-shelf solution, but I wanted control. The ironic part is that I'm using that control to offload more control to the agent. Recent experiments have included letting the agent work on itself. Super meta, but didn't quite go as planned considering the guardrails I have in place around the size of PRs. Agent work tends to be h
Joshua Baker (opens on the publisher’s site)
www.joshuabaker.com
-
2024 · Pure Sports Medicine · Reception & Booking AI Agent · Technology · UK