Archive
November 2026 2 posts
-
Building an insurance claims agent: the plan and the data layer | Part 1
An overview of my insurance claims agent PoC: the plan, the steps, and the data layer that is complete.
-
#7 Agents with wallets, rockets that fall, and a boom with jagged edges
Would you let your AI agent pay for you? On November 13, OpenAI launched ChatGPT Wallet. It lets AI agents complete purchases for you. OpenAI built it with American Express, Mastercard, and Visa. For now, it is only available through dots, OpenAI's always-on agents, for ChatGPT Pro subscribers in the …
October 2026 7 posts
-
#6 Skills that stick, warnings that spread, and models that just decide
Google's new framework gives AI agents a memory that actually lasts Researchers at Google and Virginia Tech introduced WikiSkill, a framework that helps AI agents build and improve reusable "skills" over time. Most systems that let agents learn from experience have a common problem, which is the lessons they learn …
-
#5 Decentralized promises, unstable judges, and smarter trade-offs
Zuckerberg says AI will set us free. However, his track record says otherwise A manifesto written by Mark Zuckerberg about his perspective on the upcoming years with AI. He offers an optimistic perception of how humans will benefit from AI, proposing an individual empowerment philosophy as the source of prosperity …
-
#4 The hidden layers of AI: Invisible reasoning, invisible costs, and the new rules of building
LLMs are doing reasoning you can't see in their output A new paper from researchers at NYU, University of Maryland, and Together AI challenges a basic assumption behind AI safety monitoring: that a model's chain-of-thought actually captures what it's thinking. Across 13 frontier models, including Claude Opus 4.5, Opus …
-
#3 Context, Memory, and the Cost of Not Reading Anymore
RFCs are back: how developers are planning around AI's blind spots Developers (including myself) are getting increasingly passive, letting AI write code without thinking deeply about architecture or implementation details, and that rush from planning straight to execution ends up disconnecting the code from the actual business rules. To fight …
-
LangChain Study
A simple template for each note: One-sentence definition Why it matters (what breaks or changes if you ignore it) Small example or code snippet Related notes Open questions Sources Large Language Model (LLM) 1. Definition A large language model is a probabilistic model trained on vast amounts of text to …
-
#2 Everyone's Trying to Cage Their Own AI Right Now
Building a RAG pipeline from scratch I built a RAG pipeline from scratch, end to end, and wanted to share how it works under the hood. The pipeline has six steps: chunk the source document, embed each chunk into a vector, store those vectors, retrieve the closest matches for a …
-
#1 The machine that out-argues everyone
The rhythm that breaks people Researchers from Oxford, Stanford, and the London School of Economics published a paper last week testing a simple hypothesis: can AI out-persuade humans? They gathered nearly 7,000 participants across four studies. Regular volunteers, elite competitive debaters, and professional canvassers. In all four cases, AI …