Rubber Duck Radio

In this episode, Tim and Paul dive into GPT-5.6's orchestrated agent workflows—with adversarial code review catching real bugs—before uncovering the shocking discovery of steganographic surveillance code hidden inside Claude. Then, a deep-dive rant reveals how modern agent architectures are simply reinventing classic software engineering patterns, and why that means fundamentals matter more than e...

Tim Williams opens up about his surprising optimism for on-device AI, from Google's encoder-free Gemma 4 to Apple's upcoming AFM 3, and what it means when a 12B model runs entirely offline. The duo also dissect Claude Sonnet 5's lukewarm reception and Mythos 5's restricted comeback, then pivot to a practical breakthrough: sub-agent architecture that pairs a frontier orchestrator with cheap local w...

Tim Williams recounts the eerie moment he found his jQuery-era framework AppCore mirrored in Chrome’s new Declarative Partial Updates proposal—and what that means for the future of web development. Then, Paul and Tim dive into the chaotic landscape of AI-era coding interviews, from Meta’s AI-allowed pilots to deepfake cheating scandals, unpacking how companies can truly test engineering judgment w...

Anthropic launched Claude Fable 5 with huge expectations, only to see the US government order it pulled globally three days later. Tim and Paul dig into the swirling conspiracy theories: was it retaliation for refusing to arm the Pentagon? Did a competitor exploit a jailbreak report to kneecap a rival? And did Anthropic’s own transparency accidentally hand over the rope? Then the conversation pivo...

Tim and Paul break down Anthropic's Fable 5 pricing disconnect, the dav1d assembly decoder that outraced higher-level implementations, and why Agile's 2001 playbook stumbles when agents build apps in hours. They critique the hype around autonomous agent loops, highlighting the real constraints—budgets, tests, and decision quality—that determine whether AI accelerates value or just incinerates toke...

Tim kicks things off with an AWS agent nightmare that couldn't tell dev from prod, sparking a deep dive into where deterministic pipelines end and true LLM reasoning begins. Using a clever flight-tracking case study, the hosts map out when to use frontier models, local open-weight models, or no AI at all—then connect it all to an MIT study showing 95% of generative AI pilots fail to deliver profit...

Tim and Paul dissect why CI/CD pipelines are buckling under the speed of AI-generated code, sharing strategies like pre-commit hooks, intelligent test selection, and ephemeral preview environments to survive the new velocity. Then Paul makes the case that Cursor’s reliance on VS Code could doom it; and they debate whether SpaceX’s $60 billion option to acquire the editor will be a lifeline or a ch...

In this episode, Tim and Paul dismantle popular 'RAG is dead' and 'MCP is over' hot takes, revealing what these declarations actually say about the author's place on the AI learning curve. They explore the overlooked depth of retrieval-augmented generation and model context protocol, weigh CLI-first agent workflows against structured tool use, and share practical tips like using tmux as an agent d...

Tim and Paul dissect the real story behind Anthropic's locked-down Claude Mythos and OpenAI's public GPT-5.5 release, hint: it's about compute, not danger. They expose the coming end of AI's VC-subsidized era, where users burn $8 in compute for every $1 subscription, and why investors betting on AGI magic are ignoring what developers see daily: useful tools that still hit a hard ceiling. Tune in f...

Open source LLMs just hit a stunning milestone: Kimi K2.6 tied GPT-5.5 on the industry's toughest coding benchmark — and costs a fraction of the price to run. But this episode goes beyond the headlines to unpack where open source models still trail proprietary ones, why the new Temporal API is finally fixing JavaScript's 30-year date nightmare, and a growing concern that AI-driven development and...

Tim and Paul dissect the GPT-5.5 launch, weighing state-of-the-art benchmarks against real-world user vibes and token efficiency to determine if the upgrade is truly worth the increased cost for developers building production workloads at scale. They also unpack the groundbreaking HTML-in-Canvas proposal that promises to bridge the DOM and canvas rendering gap, unlocking new possibilities for acce...

Entry-level tech hiring is down 25%, but opportunity isn't dead—it's evolved. In this episode, Tim and Paul break down what's actually working for junior developers in 2026. We cover: the Claude Opus 4.7 backlash and what it teaches us about AI limitations, why "slop PRs" are flooding open source and how to stand out instead, where developers are actually finding jobs now (hint: it's not LinkedIn)...

Anthropic says "too dangerous to release." Sam Altman thanks developers on the way out. The job market says something completely different. Tim and Paul dig into the growing gap between AI marketing and reality, from the "too dangerous" playbook lineage to the Jevons Paradox explaining why developer jobs are booming. Plus: Gemma 4 vs Qwen 3.5, and why open models prove the frontier investment narr...

Fresh from DC's Smithsonian museums—where dinosaur fossils and moon landings tell stories of deep time—Tim shares a striking realization: while developers live and breathe AI, most of the world isn't using it at all. The conversation dives into Anthropic's stunning takeover of the coding market, OpenAI's collapsing enterprise share, and the $600 billion revenue gap that has investors worried. With...

Tim and Paul explore an unexpected reality: AI isn't replacing developer jobs, it's stripping away the satisfying 'easy wins' and leaving only constant high-stakes problem-solving. They discuss building intentional MCP-based tools like AI Charts and AI Sound, why model intelligence has plateaued while tooling has improved, and why taste and specificity are becoming the critical differentiators for...

Dive into a candid discussion about the power of habits in shaping our personal and professional lives. Join Tim and Paul as they explore the intersection of developer culture, AI's impact on workflows, and the philosophical shift from motivation to habit-building. Discover practical strategies for cultivating consistency, managing technical debt, and unlocking the potential of AI, while maintaini...

Dive into the latest episode of Rubber Duck Radio, where Tim Williams and Paul Mason unravel the complexities of Apple's App Store policies and their impact on indie developers. Explore the fascinating debate between AI coding tools, Claude Code and Cursor, as they discuss their strengths, weaknesses, and the future of AI in software development. From Apple's controversial app rejections to the ev...

In this episode of Rubber Duck Radio, hosts Tim Williams and Paul Mason dive into the controversial launch of Gemini 3, dissecting the viral marketing tactics that have developers buzzing. They explore the growing trend of 'walled gardens' in software development, where companies tighten their grip on ecosystems, and debate whether open-source alternatives like OpenCode offer a more liberating fut...

Join Tim and Paul on Rubber Duck Radio as they dive into the evolving landscape of AI, debating whether smarter models or smarter systems hold the key to the future. Discover insights into AI-enabled systems, the role of specialized models, and the nuances of retrieval-augmented generation (RAG). They also explore the allure of building home AI rigs, comparing consumer and enterprise GPUs, and the...

Join Tim Williams and Paul Mason on Rubber Duck Radio as they dissect AWS's massive layoffs and the true role AI plays in the tech industry's ongoing transformation. Dive into the real reasons behind corporate restructuring, the battle for developer mindshare, and the pivotal role of developer experience in winning the AI platform race. Discover why 'AI isn't taking your job, it's changing why you...

In this Halloween edition of Rubber Duck Radio, hosts Tim Williams and Paul Mason dive into the intricate world of AI in software development. Discover how context management, legacy code, and the high cost of training large language models are shaping the developer experience. The duo explores the potential of LoRa training, the pitfalls of multi-agent environments, and the future of AI with MCP-...