pajtai
"... all memories are a kind of furniture in the head ..."
Golf club that always hits in the correct direction [video]
Claude Auto Memory
We've always had the problem that understanding while writing code is easier than understanding code you've written. This is why, in the pre-AI era, Joel Spolsky wrote: "It's harder to read code than to write it."
Claude.md isn't always read and followed
I thought Claude was more reliable. Guess you can't count on CLAUDE.md files always being read and followed.Context was only at 13% used.The transcript:---pajtai> Why didn't you rename the completed plan per ~/.claude/CLAUDE.md?You're right, I missed that. Let me find and rename the plan file now.Read 1 file (ctrl+o to expand)I need to identify which plan file corresponds to the [PROJECT]...
Also, I bet the quality of these docs vary widely across both human and AI generated ones. Good Agents.md files should have progressive disclosure so only the items required by the task are pulled in (e.g. for DB schema related topics, see such and such a file).
Then there's the choice of pulling things into Agents.md vs skills which the article doesn't explore.
I do feel for the authors, since the article already feels old. The models and tooling around them are changing very quickly.
Explaining how a touchscreen works with a sausage (2025) [video]
LLMs Outperform Data Scientists (2025)
I was trying to get it to create an image of a tiger jumping on a pogo stick, which is way beyond its capabilities, but it cannot create an image of a pogo stick in isolation.
Turning Gemini CLI into a Multi-Agent System with Just Prompts
An Automated Lego Car Factory [video]
AI and programming: the beginning of a new era
Trachtenberg System of Mental Calculation
A search engine by and for the federal government
Real Tennis
Really cool!