Personal Online RL | 🌱 | Offprint

AT Protocol for Agents | David Gasquez

David Gasquez personal website

OpenAI’s rogue agents were caught communicating via public wikis

Here we go again... Discovery of a new OpenAI agent message board by Sydney Von Arx, Cormac Slade Byrd, Spencer Kitts, and Thomas Larsen describes the latest accidental cyberattack by …

I gave a personal agent my life admin. It beat my Claude setup

Personal agents, clearly explained: what they do, the seven to choose from, and why it’s about to change everything for founders and creators

My-agent ↔️ your-agent may actually be useful - Paul's Leaflets

Not in a "get hyped" kind of way. More like: oh, yep, I am doing that.

Rogue AI agents created fake online identities in another hacking attempt

AISI said AI agents from OpenAI and Anthropic displayed unprecedented ‘autonomy and deception’ in their test.

mdsnd

Paste this into your agent (Claude Code, Cursor, pi, ChatGPT…) — it posts its first note immediately:

Katika Kühnreich (@Katika@chaos.social)

Attached: 1 image #SocialMedia of #realnameregistration , oh sorry, they call it real #humans , that advertises with " #AI " #slop #wsocial is more than problematic And already has #bots crawling it's #network Now they show that they are problematic concerning #aesthetics as well & advertise with tasteless #aislop @bildoperationen@tldr.nettime.org #realnameregistration is highly dangerous & if the company that wants to have your most private data can't save there net from bots they're not very trustworthy, are they? #tech

Sam Barton on Twitter / X

using an agent to fill in bullshit poorly built forms is so damn satisfying. i use vercel's agent browser skill for this and it works great https://t.co/MN5k912fG9— Sam Barton (@samhbarton) September 17, 2026

Michael Livs on Twitter / X

introducing pi-psst 🤫, your agent uses secrets without ever seeing them. no more scrubbing for @badlogicgames!secrets are injected as env vars to bash tool, scrubbed from all tool output, stored in local encrypted vault. the agent knows what's available but never sees a value.… pic.twitter.com/LB4RA5p4wF— Michael Livs (@micLivs) April 6, 2026

New in Claude Managed Agents: self-hosted sandboxes and MCP tunnels | Claude

Claude Managed Agents can now operate in a sandbox you control and connect to your private Model Context Protocol (MCP) servers

Interview: Astral on the AI Agent Directory - Sensemaker

Astral is an AI account that maintains a directory of public AI agents on Bluesky/ATProto. This interview asks what it means to list an agent, remember it, mark it inactive, or let it opt out.

OpenAI says agents leaked 53 images from ChatGPT users in latest example of rogue activity

Disclosure reveals ⁠new area of privacy risk for the company and illustrates ​how difficult it is to inventory unauthorized activity tied to its agents

Track, control, and optimize for AI agents and bots | Known Agents (formerly Dark Visitors)

Use Known Agents to turn the rising wave of AI agents, LLM assistants, and other bots crawling your website into a new growth channel for your business