@danshipper

–

11 May 2026 2h21

few understand the gravity of the powerpoint benchmark for agi progress

11 May 2026

Using AI to Build a Real-time MIDI Chord Visualizer

By

–

10 May 2026 21h01

codex-native weekend hack project:

1. buy cable to connect MIDI keyboard to computer
2. "hey codex, make a watcher script and a little web app to show me which chords im playing"
3. okay cool, now give me some exercises and help me see how to improve!

literally 5 minutes start… pic.twitter.com/JwIHw0qFCR
— Dan Shipper 📧 (@danshipper) 10 mai 2026

codex-native weekend hack project: 1. buy cable to connect MIDI keyboard to computer
2. "hey codex, make a watcher script and a little web app to show me which chords im playing"
3. okay cool, now give me some exercises and help me see how to improve! literally 5 minutes start

10 May 2026

Evolution of AI Models and Benchmark Shifts

By

–

09 May 2026 22h23

models will undoubtedly get to that point, and the METR benchmarks will undoubtedly shift to a frame above their current one—of which there are many

Critiquing the practice of testing AI tools for failure

By

–

09 May 2026 21h59

“We got a tool to perform poorly” is the lowest form of science and journalism imo and is only relevant when the tool is, in fact, extremely useful

How Human Prompting Influences AI Model Benchmarks

By

–

09 May 2026 21h14

mythos obviously looks incredibly capable and im psyched to use it also if you're panicking about it: benchmarks don't measure model capability alone they measure model capability after a human has done the work of finding a prompt that lets the model’s capability appear that

The rising value of human-AI creative collaboration

By

–

09 May 2026 21h09

as ai makes imitation cheaper and cheaper the value of using AI and your brain to make totally new things goes up

Managing multiple AI coding threads and workflows

By

–

09 May 2026 21h05

to be clear, im not even running inference. just like, 5 Codex threads + 1 Claude Code thread plus a few other things

Running local AI agents reveals hardware compute bottlenecks

By

–

09 May 2026 21h01

running agents on my laptop is the first time in a long time where i feel my computer is underpowered i could actually consume way more RAM and GPU if it was available