{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Real Estate AI Nerds","title":"Voice Agents, AI Adoption and Local Models | Real Estate AI Nerds Ep. 3","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/45cf9226\"></iframe>","width":"100%","height":180,"duration":2950,"description":"In episode 3, Patrick Ferry, Rob Talbot and Wally Malesh compare how they are using voice agents, deciding when paid AI tools earn their keep, and exploring local models. They share practical experiments, including Rob's birthday bot, Wally's price-reduction reports and listing-appointment research.\nReal Estate AI Nerds is a recurring conversation about what AI is actually changing in residential real estate. Patrick Ferry, Rob Talbot, Wally Malesh and Jerimiah Taylor compare notes on tools, experiments, workflows, failures, risks and practical plays—without pretending the technology is more mature than it is.\nIN THIS EPISODE\nPatrick Ferry — Host | Strategic Advisor, AI, Digital Authority & Real Estate Innovation\nRob Talbot — Business Builder & Systems Operator | Brokerage Leadership, Partnerships + Applied AI\nWally Malesh, MBA — Business Advisor & \"Business Compounder\" | Leadership, P&L, Systems + Scale\nCHAPTERS\n00:00 Welcome to episode 3\n00:17 The ChatGPT voice commercial\n03:09 Voice agents that actually do the work\n06:32 From read-only to \"just do it\": earning AI's trust\n08:13 When a leader only has ChatGPT on his phone\n10:08 Wally's first demo: \"Tell me about this property\"\n11:39 AI as a \"very articulate Google search\"\n13:40 Anthropic's AI jobs report\n14:52 From listing books to AI\n17:27 The $20, $100 and $200 AI tool stack\n18:57 Earn your upgrade and measure the ROI\n19:35 Free vs. paid: memory and the second brain\n20:37 Open source, open weight and Chinese models\n21:57 Why the big brands still do the heavy lifting\n23:42 Upload speed and home AI\n26:54 Token costs and where compute is heading\n27:52 Running local models like Qwen3\n28:51 Hermes Agent: give AI its own computer\n31:25 Everyday tasks vs. advanced reasoning\n33:15 Automate vs. augment\n36:19 Local models as an ownership strategy\n38:51 Use case: Rob's 30-minute birthday bot\n41:57 Use case: Wally's automated price-reduction reports\n46:22 Use case: auto-researching listing appointments\n47:25 Getting...","thumbnail_url":"https://img.transistorcdn.com/8ZM48Yz4DFCIQDIr5xFCVwr_hgyCiZE629z63opDHHQ/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjhk/MmM0M2MxZDFmNmVi/OTgwNjU1MWYyZGY4/OTk4OC5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}