I use a Mac at work and a pc w/vanilla KDE at home. And... I don't feel anything is less good with KDE? If anything I prefer that over modern Mac

How is this different than bwrap or srt and others? Im using bwrap to achieve read only everywhere and and write on pwd. Also pi and other coding agents all have sandboxing that work in similar way

read-only everywhere and write only to the current directory is good if you want to prevent accidental damage, such as a coding agent could make if it hallucinated an invalid command, like `rm -rf ~`.

If you want to prevent a damage from a malicious dependency or a prompt injection, you need more robust protection (for example read-only everywhere exposes your ssh keys). You can build this on top of bwrap, but because it is a low level sandbox building block, you would likely end up creating some higher level abstraction on top of bwrap (for example srt and Flatpak are build on top of bwrap).

Drop is an attempt to create such a generic, high level sandboxing tool. I personally prefer to run agents already within a sandbox than to rely on a coding agent runtime to sandbox itself. Especially that by doing so, I can use the same sandboxing tool and config for installing other programs that need isolation, not just for running agents.

If there are no summaries then when context is full messages need to get evicted. If doing so one by one then it would indeed destroy the cache. Of course... maybe the implementation evicted 50% of messages at once, I didnt verify in code

In Jev you pass options in the input and its output just gives some probability for each. Oai structured output just follows a schema. The exact output is still generated and there is no probability

you can ask structured output for probabilities...not that they necessarily mean anything.

In theory Jev “calibrates” the probabilities, meaning a probability of 20% is optimized to happen near 20% of the time, which as you point out traditional models with schemas do NOT optimize for at all

this is for local apps

how do you decide to start a new agent, and when to kill? also... do you use some works-tealing style task board, or otherwise how would the agents get new tasks.

This is gonna be a hard name to google :)

"A n̈ew kind of AI"... yeah... join the pile :)

good skill. but why should all this repo e needed for a small MD file??

A public repo is the easiest way to share something like this.

Nah that would be a link to a gist

I suppose that’s also reasonable, though this particular repo also hosts evals and other content related to the skill. So a gist seems like it would be an addition, not a replacement.

If its on github, you can add it directly to your claude via the claude marketplace and manage updates within claude (or set it to auto-update)

How is this better than say using bubblewrap sandbox solutions. Is it safer, is that the advantage?