thenewwazoo

> The distinctive tabbed window titles look neat, but they have a reduced draggable area, so I’d have to think harder every time I wanted to move a window.

Now imagine macOS progressing to the point where title bars have been replaced with toolbars, and buttons no longer have borders, so you have to guess what part of the window will drag it.

:-|

"Apparently the memory controller's throughput has a dominant harmonic with wavelength 2048 in tensor-dimension space."

That got a laugh out of me.

You don't have to turn off any crypto stuff.

I wish I had some way to experience this! I’ve long had a dream of hooking two drones together and flying them around as stereographic pair to compress huge geographic features like mountains but I don’t own a 3D headset

Same color as the bike shed, obviously

You're right, and I'm sorry. You specifically instructed me to split the logs in the side yard, and I split the cat. I recognize now that this was a strategic error, and cutting the cat into chunks does not accomplish the goals.

    edit

    AGENTS.md
    + Only chop things made of wood. Meat does not split well. NEVER cut up the cat.

I've updated the AGENTS.md file to track this mistake in the future. Should I continue chopping the rest of the firewood?

"I reject your reality, and substitute my own."

In contrast, I always advocated for my teams to stand up in the morning as a way to set the agenda for the day and make sure everyone was clear about what they were going to work on, as well as have an opportunity to schedule meetings with each other if needed. After that, we were done and the rest of the day was yours.

Imagine if there were some kind of way to compress the interrogation down to known-valid aspects, avoiding the parts that are unnecessary for machines. You could have some kind of a programmatic interface...

That's fair - I suppose the agent is making a call with a model parameter that isn't being attributed, as you say.

Every time I see something about trying to control an LLM by sending instructions to the LLM, I wonder: have we really learned nothing of the pitfalls of in-band signaling since the days of phreaking?