Show Notes
In this episode James and Frank dive into the practical realities of using AI in everyday development—arguing that AI shines in brownfield (existing) code because it respects your architecture, while greenfield work rewards iterative prompting. They unpack model quirks: context-window limits, hallucinations, and why trying different models matters. The heart of the show is Frank’s nerdy delight: feeding a 64KB EEPROM through a disassembler and having Sonnet decompile it into readable C, exposing a PID autopilot and hardware checks—proof that AI can accelerate reverse engineering and embedded work. Along the way they share hands-on tips (trim and clean context, use disassembly first, tweak prompts), and fun examples of AI-generated icons and AppleScript. A must-listen for devs curious how AI can supercharge real projects.
Follow Us
Frank: Twitter, Blog, GitHub
James: Twitter, Blog, GitHub
Merge Conflict: Twitter, Facebook, Website, Chat on Discord
Music : Amethyst Seer - Citrine by Adventureface
⭐⭐ Review Us ⭐⭐
Machine transcription available on http://mergeconflict.fm Support Merge Conflict Links: Episode 500 Question Submission
132: The Life & Times of Frank Krueger
More from Merge Conflict
Microsoft’s new Surface Laptop Ultra pairs an ARM chip with NVIDIA RTX graphics and unified memory, promising workstation-class power for creators and local AI—at a premium price. The conversation explores why CUDA support and Windows ML matter, how local and cloud models can work together, and how Microsoft’s new container-based isolation aims to keep autonomous coding agents safer. A look at ambitious hardware and the software ecosystem needed to make it useful.
This week we look at decision models, which have gone from a novelty to something every AI lab is now building. We start with a practical detour: where do you actually sell a high-end Mac mini these days? We compare local marketplaces and eBay, and the trust tradeoffs that come with each. Then we come back to decision models and explain why Jev got us interested in them again. We cover Microsoft's Decision One and what makes it notable: its benchmarks and its speed. We also walk through how decision models work in practice for games, robotics and structured control. Finally, we explain why small fine-tuned models matter for robustness, for running locally and for a future beyond chat. We wrap up with what all this means for local AI hardware and how we use OpenRouter in our workflows. Plus: a teaser for next week's Microsoft hardware discussion.
James and Frank explore Apple's next-gen Siri and iOS 27 updates with mixed results—the chatbot fell short of expectations despite hype. They dive into AI agents, smart home automation potential, and why Apple's scattered AI integration lags behind competitors like OpenAI and Microsoft. Plus, practical developer updates on Xcode, .NET, and automating your digital life.
Discover the emerging classifier revolution with Jev—a radical new take on LLMs that ditches generation for lightning-fast categorization. Plus, deep dives into the latest model releases (Luna, GPT-6 Sol, Claude Opus 5.5), practical strategies for iterative AI development, and why specialized models are reshaping how we work with AI.
Apple's new iPhone Duo promises a game-changing foldable experience, but developers face a minefield of technical challenges. James and Frank break down the critical app adaptation work required—from handling multiple screen permutations to managing safe area insets and keyboard behavior—plus why native UI controls matter more than ever.