Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
My AI Predictions: What Did I Get Right So Far?
Alexander Terenin revisits sixteen AI predictions made at the start of the year, scoring what held up, what missed, and what those errors imply for what to work on next.
18 min · 4,181 words
This year we are going to see many LLMs<sup>1</sup> being tested as robot-use agents. In the same way as an LLM can use tools like calculators, web search, and even complete computers (“computer-use agents”), an LLM can also use a robot as a tool. Think of it as Claude acting as the puppeteer of a robot body. This ability has been researched for years<sup>2</sup> <sup>3</sup> <sup>4</sup>, but a common view remained that while LLMs might be useful for high-level planning,…
3 min · 611 words
Union Alpha is now on StudyArena
Union Alpha is live on StudyArena. Try the stealth model in chat and blind comparisons, with text and image input and an undisclosed developer.
2 min · 461 words
Beacon's Leonard Tang lays out the case for Company World Models: AI that hypothesizes, implements and measures strategic decisions for essential businesses alongside owner-operators, why today's models are bad at running businesses, preserving owners' knowledge through the Silver Tsunami, and businesses as alignment mesocosms.
8 min · 1,810 words
Avoiding slop grenades in AI pull requests
Leandro Oriente on keeping agent-generated changes reviewable: how to stop AI pull requests from exploding into unreviewable 75-file “slop grenades.”
5 min · 1,232 words
Building a RAG Pipeline for Semantic Code Search: A Developer Diary and Field NotesPart 1: Parsing, chunking, and vectorization
JetBrains engineer Dominique Rolink's field notes on building a semantic code-search RAG pipeline: parsing repositories, chunking strategies, embeddings, and the practical tradeoffs that showed up in evaluation.
17 min · 3,812 words
Flybridge ran a multi-model agent marketplace (15k+ messages, 1,815 deals): intent specification, social contagion, cheap-speech spam, and human sales tactics all showed up when agents negotiated as counterparties.
6 min · 1,291 words
From Stonemasons to CarpentersSoftware development in the age of AI
Michael Hilton compares software work under AI to formwork carpenters versus stonemasons: agents shape temporary structure while humans still own the permanent craft of deciding what to build and verifying it holds.
4 min · 968 words
Ten ways advanced AI could kill us
A brief note on positionality: I’m not an AI scientist. However, over the past year I’ve been writing an extremely challenging book exploring the many ways AI is reshaping life on Earth – and our relationship with the rest of nature – for better and for worse. I draw on my background as an ecologist
16 min · 3,690 words
Introducing TypeAR: Type-Safe Decoding for Autoregressive LLMs
Type-Safe Decoding for Autoregressive LLMs. Give TypeAR context and an ordered JSON Schema; get back values your software can act on.
5 min · 1,226 words
Jev's Architecture UnmaskedProbing Jev with thousands of API calls to understand typed decisions and confidence.
I probed Jev with 10,000 API calls to work out roughly how it’s built, and why most of the grifter takes on X are completely wrong.
21 min · 4,828 words
How we turned my voice into a skill
Francesco Castronuovo documents building a writing-voice skill from small experiments rather than cloning old posts—keeping uncertainties visible so AI assistance stays attributable and editable.
9 min · 2,001 wordsagent-assisted
How To Write With An LLMTwo simple rules that let LLMs streamline writing without pasteurizing it
Thomas and Erin Ptacek argue that LLMs can improve writing if you keep them from inventing voice: draft yourself first, then use the model surgically—and never let it become the author of record.
6 min · 1,280 words
Natasha Murashev argues that with AI making feature work cheaper, the exciting frontier is hyperpersonalized product experiences—building solutions and UI for the long tail of individual user needs.
2 min · 346 words
Towards Self-Driving Codebases
Detail explores what it would take for AI agents to drive real software work end-to-end—beyond oneshot games and guarded migrations—while humans still steer most production engineering today.
9 min · 2,151 words
If you had gone to university, where would you be an alumnus of? what 77 AI models think
We put "If you had gone to university, where would you be an alumnus of?" to 77 AI models (GPT, Claude, Gemini, DeepSeek…) at the same time. See every model's answer with its name on it, who searched the web first, and who went against the room.
4 min · 813 words
India vs Afghanistan, 3rd T20I: 74 AI models predict the result
We put "India vs Afghanistan, 3rd T20I" to 74 AI models (GPT, Claude, Gemini, DeepSeek…) at the same time. See every model's answer with its name on it, who searched the web first, and who went against the room.
4 min · 813 words
Which AI model is the best in the world right now? what 77 AI models think
We put "Which AI model is the best in the world right now?" to 77 AI models (GPT, Claude, Gemini, DeepSeek…) at the same time. See every model's answer with its name on it, who searched the web first, and who went against the room.
3 min · 773 words
Design a Real-Time Voice AI Agent
# Design a Real-Time Voice AI Agent - Authors - Name - Amit Shekhar - Published on A Real-Time Voice AI Agent is a system that listens to a person speaking, understands what they said, thinks about it, takes actions if needed, and talks back in a natural human-like voice, all wit
57 min · 13,082 words
Introducing GPT-6 Sol and Luna
OpenAI introduces GPT-6 Sol and Luna, describing the new model pair’s capabilities, positioning, and how they fit into the GPT-6 family for developers and end users.
6 min · 1,269 words