Where answers come from

Some pages can ask a language model questions. Set this up once; your choice is remembered in this browser for the whole site.

Model source
Use another source instead

Smallest-to-largest weight downloads. Qwen3.5 0.8B is our starting choice for page Q&A. GPU estimates are not total RAM: leave room for the browser, context and temporary buffers. Hardware changes speed and capacity; answers still need checking.

Session-only loading avoids saving model weights, uses extra RAM and downloads again after unloading. Turn it off to save downloads. Delete-data-on-exit or private browsing may impose a much smaller storage limit than the displayed estimate.

You sign in on OpenRouter; it gives this page a key for your account.

A free account does not make every model free. Choose a model with a listed :free variant; merely adding that suffix does not create one. Check free-model availability and pricing.

Chat

AI assistant, not Shawn Hartsock. It does not speak for him.

Inspect the page excerpt

Up to 4,800 characters, not the whole site. Recent conversation turns are retained within the model’s context limit.

Ask about this page, or just say hello.

Ready when you are.

Not saved or uploaded automatically. Closing keeps this conversation in this tab; changing pages starts a new one. Model replies can be wrong.

Behold the Power of Pipe!

Originally published .

This is a repost of an article on pipe I posted several years ago. Pipe is a very powerful tool, behold:


tar -czf - [list of dirs and files] | \

    ssh [user]@[server] "cd /path/to/place/files; tar -xzf -"

I learned this one from one of my bosses a few jobs back. There are a few unixy tricks in that command that took me a while to grasp. I’ve been using this trick for years now and I thought perhaps you would like to see it.

You create a tar archive and specify the file “-“ which is your standard out. Then you list the dirs and files you wish to grab. Since the compressed tar is being sent to stdout you can catch it with a pipe “ ” and send it to ssh (the “" is just a way of breaking a command between lines).

With ssh we log into a server as a given user. Then we ask ssh to run a command for us. Since the ssh session will login to the machine at the user’s home dir we ask the command session to change to a path, then run the tar command. This time we are extracting the tar archive we caught with pipe by specifying the file “-“ to the tar command.

The result is that the files get tarred, compressed, and shot over the network to a remote machine which then immediately untarrs decompresses and drops the files in place. We let tar do all the work of error handling and handling non-regular files, compression is optional, and there are no archives left over.

If, however, we wanted to create a remote archive without ever consuming storage on the local machine we could instead do this:


tar -czf - [list of dirs and files] | \

    ssh [user]@[server] "cat > /path/to/place/file.tar.gz"

If processing power was limited on the local machine then we could do this:


tar -cf - [list of dirs and files] | \

    ssh [user]@[server] "gzip -c > /path/to/place/file.tar.gz"

Explore the map · Browse by topic and date