{"version":"1.0","type":"rich","provider_name":"Acast","provider_url":"https://acast.com","height":250,"width":700,"html":"<iframe src=\"https://embed.acast.com/$/6712aef6e21e2bb3149f1fd5/69835999f93f63c13a27836a?\" frameBorder=\"0\" width=\"700\" height=\"250\"></iframe>","title":"Clawdbot / Moltbot / OpenClaw","thumbnail_width":200,"thumbnail_height":200,"thumbnail_url":"https://open-images.acast.com/shows/6712aef6e21e2bb3149f1fd5/1770215576685-d4758203-0853-416e-8bd3-a8e4b56a4195.jpeg?height=200","description":"<p>Dan, Toby, and Chmiel reunite after a long January to unpack what happened when ON_Discourse members went hands-on with Moltbot (formerly Claudebot, now OpenClaw) — an open-source AI agent with full shell access to your computer, your email, your calendar, and everything else. What started as an emergency Group Chat turned into one of the most unsettling Follow My Flow sessions yet, with even the most advanced members shutting the tool down because it got too weird.</p><p><br></p><p>Details in the show:</p><p><br></p><ul><li>How Clawdbot makes it easy to forget completed work</li><li>The difference between automating a defined process and giving an agent undefined access to act on your behalf</li><li>Why Moltbot is different than previous agents</li><li>Why the most advanced users are spending all their energy on context engineering instead of the actual work</li></ul>","author_name":"ON_Discourse"}