Time-to-market favors chromium. It's also by far the most commonly used engine for headless browsing, creating lots of useful prior art.

Google's AI overview regularly hallucinates or gets the answer wrong. Obviously if you're going to run inference on every search from billions of users, it has to be a very cheap model.

I really like how Kagi does it - summary only appears if you finish your query with a question mark, or if you press "q" after loading the results

You can already do what you're looking for by reading the browser cache as new data is cached. This would allow you to see the site as it was loaded originally, instead of simply fetching an updated view from a URL. The data layout for the cache in Firefox and Chrome is available online.

Does the cache store the rendered DOM?

The unfortunate reality is that, depending on your personal preferences, "most modern games" require such a ring 0 anti-cheat. Any game that has a matchmaking mode with a competitive option requires a rootkit.

As an aside, I recently found Riot Games' Vanguard installed on my Linux ESP partition... after having installed the game on my windows partition. It rooted every OS it could find mounted. Incredible.

Modern games are not just shooting stuff in competitive mode.

There exist a gazillion of other games too, without anti-cheat.

GP said "depending on your personal preferences" and clearly didn't imply all "modern games" are competitive shooters.

Then depending on your personal preferences, all modern games are farming simulators.

How did you find out that you had a rootkit?

I've found the latency of /compact makes it unusable. Perhaps this is just the result of my waiting until I have 0% context remaining.

Fun fact, a large chunk of context is reserved for compaction. When you are shown that you have "0% context remaining," it's actually like 30% remaining that's reserved for compaction.

And yet, for some reason I feel like 50% of the time, compaction fails because it runs out of context or hits (non-rate) API limits.

Weirdly, I’ve found that when that happens I can close Claude and then run `claude --continue` and now it has room to compact. Makes no sense.

But I have no idea what state it will be in after compact, so it’s better to ask it to write a complete and thorough report including what source files to read. Lot more work but better than going off the rails.

The old rule of thumb is that when you compact, you've already lost.

I wonder how well a sentence or two in CLAUDE.md, saying to search the local project for examples of similar use cases or use of internal libraries, would work.

CC uses very little system resources.

The insert function is very unidiomatic. Instead of defining a cmp closure, you would typically implement Ord and friends.

TIL of `docker commit`. What is the use case for this command? Quick debugging or something, to share with a coworker?

Same as snapshotting a vm, or as an interactive version of "docker build". But rarely useful, since most workflows don't really need statefulness.

It seems like their whole platform depends on it though… to my read they’re providing their users with cloud devcontainers to connect to from their local VS Code, then deploying to production by snapshotting the container with docker commit. Those containers have SSH enabled to the internet, which is where all of the auth logs came from that wound up baked into the images.

The field is nascent. The bar is not static.