All Links
11/21
AI: Tool, Mind, Weapon (@arm1st1ce)
11/21
11/21
11/17
AI Will Not Make You RIch - "The way to invest in AI is to think through the implications of knowledge workers becoming more efficient, to imagine what markets this efficiency unlocks, and to invest in those." (Jerry Neumann)
10/17
Equipping agents for the real world with Agent Skills - I’m very excited about this, the untapped potential in Claude Code (et al) for non-coding tasks is huge (Anthropic)
10/17
Superpowers: How I'm using coding agents in October 2025 - ”Please read the book and pull out reusable skills that weren't obvious to you before you started reading” (Jesse Vincent)
10/16
OpenAI Apps SDK UI Guidelines (OpenAI)
10/11
Functional versions of the LEGO computer bricks (LOVE HULTÉN)
10/07
Building a private & personal cloud computer (Chase McCoy)
10/07
Vibe engineering - how software engineering practices amplify ai-assisted development (Simon Willison)
10/01
AI Isn't Replacing Radiologists - if AI is good at radiology why is demand for radiologists is higher than ever? Diff. btw. clinical and lab setting, legal hurdles, and diagnosis is only a fraction of the job (Deena Mousa)
10/01
Building Agents with the Claude Agent SDK (Anthropic)
10/01
Effective Context Engineering for AI Agents (Anthropic)
09/27
I trapped an AI model inside an art installation - I love stuff like this, it makes me want to learn electronics and basic fabrication skills (YouTube/rootkid)
09/27
Magical systems thinking - "A complex system that works is invariably found to have evolved from a simple system that worked." (Ed Bradon)
09/27
09/27
09/10
09/09
i ran Claude in a loop for three months, and it created a genz programming language called cursed - it's Ralph Wiggums all the way down (Geoffrey Huntley)
09/09
Software speed and the chat illusion - the chat ui is uniquely suited to the slow response speed of LLMs / "everything is slow before it's fast" (Robin Sloan)
09/03
09/01
08/29
AlignEval: Building an App to Make Evals Easy, Fun, and Automated - I haven't tried the tool yet, but I love how it's structured as a "game" (Eugene Yan)
08/29
Frequently Asked Questions (And Answers) About AI Evals - tons of helpful info in here (start with the "getting started" links ofc), I'm excited to try these ideas with Flavorful (Hamel Husain & Shreya Shankar)
08/29
Taco Bell rethinks AI drive-through after man orders 18,000 waters - I've been learning about how to do AI evals lately, I have some links for someone at Taco Bell to check out (BBC)
08/27
DXT Weekly is a newsletter that shares interesting MCP servers - Things-MCP was featured this week (Substack)
08/25
Theresa Torres on AI Evals - I like this "bottom up" approach to AI evals, and also relate to the level up she's experiencing with Claude Code (et al) as a non-software engineer (YouTube)
08/19
The GenAI Divide: State of AI in Business in 2025 (PDF) - massive individual AI adoption but only 5% of corporate pilots are successful (MIT Project NANDA)
08/08
08/04
I don't get it, we had all those meetings (The New Yorker)
08/01
Simple hook so Claude Code can tell you when it's waiting on you - I'd like to do something like this with a red/yellow/green "tower light" (ernesto-jimenez)
07/30
AI Model Pricing Comparison - One table for comparing model pricing and capabilities
07/28
AI UI metaphors: HUDs vs copilots (Geoffrey Litt)
07/28
07/28
07/28
Good demos are important - curiosity is the main force for how we pull ideas from the future into the present (Sharif Shameem (x))
07/28
07/28
07/28
07/02
07/02
07/02
07/02
07/02
Tired: Prompt Engineer, Wired: Context Engineer (x/karpathy)
07/02
How Long Contexts Fail and How to Fix Your Contexts (dbreunig.com)
07/02
07/02
Christoph Niemann grapples with AI and art (New York Times)
07/02
06/29
How AI might change the nature of jobs? - "there are three major areas where humans either are, or will soon be, more necessary than ever: trust, integration and taste" (New York Times)