Facebook

Why MCP and ChatGPT Apps Use Double Iframes — Frédéric Barthelet, Alpic

Jun 15, 2026 · 20:11

Frédéric Barthelet, CTO of Alpic, explains why ChatGPT and other MCP hosts render third-party app UI inside a double iframe. He traces how simpler approaches fail: `srcdoc` shares the parent origin, letting CSP block scripts and risking data access; sandboxing removes origin storage; and `allow-same-origin` recreates the escape. The resulting double iframe—an outer iframe from a controlled subdomain loading app HTML via `srcdoc` into an inner frame—ensures isolation and prevents cross-app storage collisions. Barthelet warns developers must declare every external domain their view uses in MCP app metadata or face submission rejection, and demos Skybridge's CSP inspector that diffs declared domains against actual network calls.

AI changes *Nothing* — Dax Raad, OpenCode

Nov 23, 2025 · 16:39

Dax Raad, core contributor to SST and creator of OpenCode, argues that AI changes nothing when building a winning product. In this contrarian talk, he breaks down the three unchanging fundamentals: marketing requires creating things so cool people share them, which AI cannot do because it is too corny; the aha moment demands ruthlessly eliminating friction to get users to that singular moment of understanding, requiring deep taste not algorithmic optimization; retention hinges on building deep primitives first to support power users without sacrificing simplicity for newcomers, a design challenge AI cannot hallucinate. Raad uses examples from ChatGPT's instant aha moment—any input box that responds like a human—and Facebook's poke as a deniable flirting aha moment. He concludes that AI amplifies capabilities but does not save anyone from the hard, creative work of product success.

When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer

Jul 22, 2025 · 15:47

Sam Julien, Director of Developer Relations at Writer, explains how the company built a graph-based RAG system that achieved 86.31% accuracy on the RobustQA benchmark and sub-second response times, significantly outperforming vector search approaches for dense enterprise knowledge. The team moved from simple vector retrieval to a graph-based approach to handle concentrated data where similar terms appear frequently, solving problems like inaccurate chunking and failure with similar documents. They built a specialized model to convert data into graph structures, stored as JSON in a Lucene-based search engine, and incorporated Fusion-in-Decoder with knowledge graphs to lower hallucination rates. Key decisions included focusing on customer needs over hype, staying flexible based on team expertise, and letting research challenge assumptions, leading to features like multi-hop reasoning and complex data format handling.

Excalidraw: AI and Human Whiteboarding Partnership - Christopher Chedeau

Jul 21, 2025 · 16:59

Christopher Chedeau, creator of Excalidraw, explains how to integrate AI into whiteboarding by focusing on turning prompts into editable diagrams rather than static images. He argues that just adding any AI model harms the product, citing a failed attempt to generate realistic images because users don't draw realistically. The successful integration uses Mermaid.js to output Excalidraw files, letting humans modify the AI-generated diagram. He envisions a future of iterative human-AI collaboration, and demonstrates other practical features like auto-naming files, generating illustrations (coming soon), and challenges AI engineers to build a browser-based logo background remover. He concludes that the industry is in a physical-to-virtual transition for AI, and that LLMs work best when targeting a structured domain-specific language.

Fun stories from building OpenRouter and where all this is going - Alex Atallah, OpenRouter

Jun 25, 2025 · 18:47

Alex Atallah, founder of OpenRouter, tells the story of how he launched the LLM aggregator in early 2023 after observing the open-source race sparked by Meta's Llama 1 and Stanford's Alpaca distillation under $600. He argues the inference market is not winner-take-all, citing OpenRouter's data showing Google Gemini growing from 2-3% to 34-35% of tokens over 12 months. The platform evolved from a simple model collection into a marketplace with over 400 models and 60 providers, solving architecture challenges like 30-millisecond latency, cancelable streams, and a middleware plugin system for web search and PDF parsing. Atallah explains that OpenRouter grew 10-100% month-over-month for two years, and he predicts future additions like transfusion models that generate images and more powerful geographic routing for enterprise optimization.

The Adversarial Path to the Personal Assistant: Sumit Agarwal

Feb 15, 2025 · 18:46

Sumit Agarwal, founder of Ario AI, discusses building a personal AI assistant that uses adversarial ETL to extract users' data from services like Google, Amazon, and Doordash, enabling immediate personalization without manual input. He announces $16M in funding and demonstrates how the assistant generates data portraits, recommends travel and routines based on personal history, and manages schedules by detecting conflicts. Agarwal shares RAG insights: avoid LLMs for trivial math, use search and pre-processed profiles, and present the right data at the right time. Ario Boost, a browser extension, lets users download their data locally in developer mode without creating an account.

Open Questions for AI Engineering: Simon Willison

Nov 25, 2023 · 24:33

Simon Willison recaps the AI industry's past year—from ChatGPT's breakthrough to open-source local models—and poses key open questions for AI engineering. He argues that ChatGPT's chat interface, while popular, is a poor fit for advanced use, urging better UIs like his command-line tool LLM. He celebrates Meta's Llama release as a 'stable diffusion moment' for language models and highlights the rise of small, locally-run models such as Replit's 3B model, asking how small models can remain useful. On security, he warns that prompt injection remains unsolved after 13 months, limiting what can safely be built. He champions ChatGPT's Code Interpreter (which he dubs 'Coding Intern') as the most exciting tool, able to write and compile C code on a phone, and argues that LLMs flatten the learning curve, making programming accessible to more people. He concludes by urging the community to build tools that enable anyone to automate tedious tasks.