Maybe now people can stop blaming npm and realize none of these unreviewed package ecosystem are safe.

Could that be the explanation for the recently increased token use?

Slopilot

This seems nonsensical. Why would non-actions activity consume actions budget?

  > Last month, we shared how GitHub Copilot code review runs on […] GitHub Actions using GitHub-hosted runners.

They say that they’re now billing against their actual costs

Copilot Code Reviews are Actions workflows. Just privileged ones you can't edit the YAML for. They even litter your Actions tab list and Deployment environments.

My guess is that they're moving to a spot where they can pitch an LLM "doing something" as an action, and copilot is their first move. I don't see it as crazy to think of a "copilot code review" in a similar way to other build actions.

But also - enterprise accounts already have budget assigned to github actions, and this allows them to start billing right away without having to actually get (or allow) businesses to evaluate the return of having copilot do code reviews.

So seems like it's a mix of immediate incentives and long term architecture. I don't like it, though. If I were an enterprise my first response would be to turn it off.

> enterprise accounts already have budget assigned to github actions, and this allows them to start billing right away without having to actually get (or allow) businesses to evaluate the return of having copilot do code reviews

Hang on, I read this as copilot reviews with bill both actions minutes and AI credits. Did I miss something?

I'm assuming the running of the model is consuming the tokens, and the client coordinating and orchestrating the calls to the model to perform the review is happening in an action runner, thus using action minutes.

Agreed, especially weird since they just rolled out usage-based billing for Co-pilot. It would make a lot more sense to just re-use that usage instead IMHO

It does, read the article. This feature now consumes actions credits and AI credits.

Yeah my mistake, I wasn't very clear in my comment.

Though actually the more I think about it, I think this change actually does make more sense. In the case of the AI running on GitHub side, that does feel pretty equivalent to CI minutes. I would hope that the number of minutes they bill for is pretty minimal though, since the vast majority of that will be I/O waiting on the agent to return

Code review ostensibly takes place inside a container runtime just like tests or other actions would. It makes sense to me.

but consumes vastly more resources than most app's build process.

Done that way it obfuscates cost of the code review and I think that's on purpose

The cost of running a container (to github) is someone else not being able to run a container.

“F*ck you. Pay me.”

That’s why.

TLDR: It's a 6-9x price increase

yes...need to move to api usage, that a huge jump after getting everyone onboard

Use `background-color` in Firefox's `userContent.css`.

I love the idea of ending it for myself, but my users are still screwed?

how your users' browsers choose to render `about:blank` while waiting on your page to be delivered is outside of both your control and concern

on Gnome i've got system-wide dark mode turned on and idk, my Firefox is dark gray until it gets any content. so users have the power and should exercise it to tailor their experience as they wish

Still worth it imho for important code, but it shows that they are hitting a ceiling while trying to improve the model which they try to solve by making it more token-inefficient.

Slow is good thought, that's when you know it'll get it right.

Correctness does not necessitate slowness.

And why would I want a slower mode that gets it right when the faster model already got it right before?

If it can’t even do basic stuff anymore I’m not gonna use it for advanced tasks either.

Seems so silly that they won't support `effortLevel: "max"` while a env var is perfectly fine.

They do now. /effort command is on the latest Claude Code version; run `claude update` and `claude /effort`.

/effort is only per-session though, not persistent.

This needs to be supported on `git` level first imho, not by a forge vendor.

What would this being supported by git mean to you?