CODING EPISODE: Big Pickling a Homepage

CODING EPISODE: Big Pickling a Homepage

JR and the Foz vibe up a homepage using nothing but their wits and a massively subsidized earth shattering infrastructure to inference ideas into magic. Big Pickle and Nematron collide to make Haskell magic on today's episode.

Off the Rails on a Crazy Train

JR and The Foz wax analytic about the gap in the tracks as the industry races towards a funky future. Let the Chaos Magick Continue! 00:00 - Intro 01:04 - On today's episode 01:51 - Zuck's Clone Wars 05:17 - Bakery update! 07:46 - Lovable's SecOps Sucks 12:32 - Cursor + Railway DB Delete! 21:45 - That's a wrap! Zuckerberg Clone Wars: * One for the staff: https://finance.yahoo.com/sectors/technology/articles/mark-zuckerberg-building-ai-clone-093500829.html [https://finance.yahoo.com/sectors/technology/articles/mark-zuckerberg-building-ai-clone-093500829.html] * One for Mark: https://www.wsj.com/tech/ai/mark-zuckerberg-is-building-an-ai-agent-to-help-him-be-ceo-eddab2d5 [https://www.wsj.com/tech/ai/mark-zuckerberg-is-building-an-ai-agent-to-help-him-be-ceo-eddab2d5] Also, Zuck's tracking every click: https://x.com/GergelyOrosz/status/2046705305778618613?s=20 [https://x.com/GergelyOrosz/status/2046705305778618613?s=20] Original Lovable data access post: https://x.com/weezerOSINT/status/2046170666131669027 [https://x.com/weezerOSINT/status/2046170666131669027] * Business insider article on Lovable incident: https://www.businessinsider.com/lovable-security-access-vibe-coding-projects-risk-2026-4 [https://www.businessinsider.com/lovable-security-access-vibe-coding-projects-risk-2026-4] * Actual lovable docs: https://docs.lovable.dev/features/project-visibility [https://docs.lovable.dev/features/project-visibility] Original PocketOS founder Jer Crane's post: https://x.com/lifeof_jer/status/2048103471019434248 [https://x.com/lifeof_jer/status/2048103471019434248] * Also, I guess he found a reporter: https://www.tomshardware.com/tech-industry/artificial-intelligence/claude-powered-ai-coding-agent-deletes-entire-company-database-in-9-seconds-backups-zapped-after-cursor-tool-powered-by-anthropics-claude-goes-rogue [https://www.tomshardware.com/tech-industry/artificial-intelligence/claude-powered-ai-coding-agent-deletes-entire-company-database-in-9-seconds-backups-zapped-after-cursor-tool-powered-by-anthropics-claude-goes-rogue]

The Great Claude Shakedown

Episode 8 - JR and Foz talk about bakeries, Trendslop, and The Great Claude Shakedown™ of 2026! 00:00 - Intro 02:00 - On today's episode 04:34 - Bakery update! 11:32 - Trendslop 12:22 - JR and Foz plan the final episode 13:03 - Moar Trendslop 17:18 - The Great Claude Shakedown™ 23:52 - Outro Trendslop Article: https://hbr.org/2026/03/researchers-asked-llms-for-strategic-advice-they-got-trendslop-in-return [https://hbr.org/2026/03/researchers-asked-llms-for-strategic-advice-they-got-trendslop-in-return]

Jovovich Driven Development

EPISODE 7: MEMORY PALACES, SECURITY HELL, AND THE SLOW COLLAPSE OF SOCIETY This week on Yelling at Robots, JR and Foz dive headfirst into the cheerful little topic of AI security doom — with a brief stop at Milla Jovovich apparently becoming an AI memory systems founder. They unpack Mem Palace, a celebrity-adjacent AI memory project that sent Twitter into a frenzy, then quickly into forensic open-source critique mode. From there, things get only more uplifting: a deep discussion of Google’s AI Agent Traps paper, which catalogs a truly inspiring number of ways agents can be manipulated, poisoned, tricked, socially engineered, and generally turned into chaos goblins. Then it’s on to Anthropic’s Mythos, a giant unreleased model allegedly trained at absurd cost and now pointed at ancient security vulnerabilities hiding in foundational software. The mood throughout can best be described as: “stay frosty, we’re all cooked.” A light, breezy episode for anyone interested in: agents, exploits, celebrity AI launches, model psychosis, and the general erosion of psychic stability. This summary was SOOOOO generated by AI. Original Milla Post: https://x.com/bensig/status/2041384157595725999?s=20 [https://x.com/bensig/status/2041384157595725999?s=20] Mempalace github repo: https://github.com/MemPalace/mempalace [https://github.com/MemPalace/mempalace] AI Agent Traps: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6372438 [https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6372438] Mythos System Card (All 245 pages, jfc!): https://www-cdn.anthropic.com/08ab9158070959f88f296514c21b7facce6f52bc.pdf [https://www-cdn.anthropic.com/08ab9158070959f88f296514c21b7facce6f52bc.pdf] Security expert Low level learning (his name is Ed): https://lowlevel.tv/ [https://lowlevel.tv/]

Claude Code's Own Goal

JR and The Foz dig deep on Easter Sunday in to the claude code own goal of publishing their agent harness, the dangers of slopsquatting and the rising tide of local models. Anthropic Leak * What happened: https://medium.com/@anhaia.gabriel/claude-codes-entire-source-code-was-just-leaked-via-npm-source-maps-here-s-what-s-inside-eb9f6a1d5ccb [https://medium.com/@anhaia.gabriel/claude-codes-entire-source-code-was-just-leaked-via-npm-source-maps-here-s-what-s-inside-eb9f6a1d5ccb] * Choufan Shou (person who found the leak): https://x.com/Fried_Rice [https://x.com/Fried_Rice] * Claw Codes Codes: https://claw-code.codes/ [https://claw-code.codes/] Simon Wardley: https://swardley.medium.com/ [https://swardley.medium.com/] Slopsquatting: https://www.mend.io/blog/the-hallucinated-package-attack-slopsquatting/ [https://www.mend.io/blog/the-hallucinated-package-attack-slopsquatting/] Ginger Bill's Package Managers Are Evil: https://www.gingerbill.org/article/2025/09/08/package-managers-are-evil/ [https://www.gingerbill.org/article/2025/09/08/package-managers-are-evil/] Gemma 4 (Google's smaller edge models): https://deepmind.google/models/gemma/ [https://deepmind.google/models/gemma/] Google's paper on reducing memory footprint: https://research.google/blog/turboquant-redefining-ai-efficiency-with-extreme-compression/ [https://research.google/blog/turboquant-redefining-ai-efficiency-with-extreme-compression/]