Month: May 2026

GitHub Copilot is moving to AI credits (after accidently burning billions?)

by

Last month I wrote a history of AI agentic coding, from my perspective, which heavily leaned on GitHub Copilot. One of the things that I have really appreciated over the years was the packaged cost of Copilot in comparison to the apparent cost of using per token prices APIs directly, or even the other packaged deals. However at the end of this month GitHub Copilot is moving to usage-based billing, and they now have a Copilot Billing Preview tool to allow you to compare what you have been paying vs what you will be paying in the future.

In my last post I took a look at my usage breakdown month by month, showing steady growth, and also shifts between the various models. All of that was mostly within the 10 USD per month plan (though this past month I have shifted to the 39 USD per month plan due to the new session and weekly token limits that people are complaining about online a fair bit (I haven’t actually seen a hint of these on the 39 USD per month plan)

However, next month this 39 USD is going to shoot up! And probably for good reason, as it looks like they might have been loosing a billion+ a month in recent months? (More on that below)

The tool is browser based, and just requires you to drop in a CSV file from the Premium request analytics of your account (which now has some additional fields). It then shows you various visualizations in the browser and extracts useful data from the more verbose report, including specifically some comparisons between your previous cost, and apparent future cost with AI credits instead.

Month comparisons

I went back and downloaded all of my new premium request usage report data for this year throughout which I slowly progressed from around 300 PRU per months (premium requests used) toward and past 600 PRU per month (largely due to the cloud agent usage increase. And in summary, this is what the difference between PRU based billing and AICS (AI Credit) billing looks like for me.

MonthPlanPRUsAICsCurrent billing (PRUs)Usage-based billing (AICs)
January 2026Pro (10 USD) 300 PRU293.141,059.761 AICs10 USD10 USD
Feburary 2026Pro (10 USD) 300 PRU318.032,306.47910.72 USD18.06 USD
March 2026Pro (10 USD) 300 PRU719.0939,728.39726.76 USD392.28 USD
April 2026Pro (10 USD) 300 PRU563.7439,911.73720.55 USD394.12 USD
1/2 of May 2026Pro (10 USD) 300 PRU354.6331,017.7611/2 39 USD310.18 USD
Projected May 2026Pro+ (39 USD), 1500 PRU70060,00039 USD620 USD

Read more

A first look at Docker AI Sandboxes for GitHub Copilot

by

With local AI agents increasingly writing and executing code autonomously, giving them unrestricted access to your machine is becoming a massive security risk. This is one of the primary reasons that agentic flows have so many flavors of approval that may need to happen throughout an agents course of action, though others include review points and being able to keep the agent on track.

I have been very much enjoying my increased use of GitHub Cloud Agents in my work and play, which is rather powerful if you can setup your entire stack (more or less accurately) in a remote environment using VMs and containers. On the project that I currently work the most I have a copilot-setup-steps.yaml file or 53 lines leveraging my existing docker compose based development environment setup of 41 services that only takes 2 minutes to “install” (multi repo clones, and dependency installation), then allowing agent to run various different development configurations depending on the tasks at hand, using a mixture of the services (or not).

However today is the first day I’ll be taking a very brief look at Docker AI Sandboxes, to try and do more of this locally and or on machines nearby…

Read more

Editing wikibase.world (a MediaWiki site), with Jules (an AI agent)

by

I recently decided to run an experiment on wikibase.world: what happens when you give an AI agent the keys to a live MediaWiki instance and ask it to do some targetting gardening, including edits to Wikibase?

Meet the Jules free tier, though i’m sure you could use any agent. Over the course of a few hours, I tasked Jules with editing wikibase.world, moving from simple API edits, querying SPARQL, browsing external websites, and even learning how to properly participate in MediaWiki talk pages, requesting for me to edit its knowledge / prompt on a protected wiki page.

Onboarding and Basic API Usage

Before Jules could do anything, it needed an account. I asked it to register itself as “Addagent” using the MediaWiki API and handle the CAPTCHA and token requirements.

The prompt was:

Can you register me an account on https://wikibase.world/ I guess via https://wikibase.world/w/index.php?title=Special:CreateAccount&returnto=Project%3AHome or the API And then tell me the password The username should be “Addagent”

It went ahead and did this first time, and now https://wikibase.world/wiki/User:Addagent exists. To create the account it seemingly used https://www.guerrillamail.com/ which I have since changed to an actual email address I control incase I need to reset the account password (which I also noted down).

One thing of note while using Jules, is that it really is optimized for coding, and it continually reports that it is “Running code review…” between steps, even though there is no code repo and nowhere to commit code to and no real code in this project either, and it continually referred to “pre-submit steps” even though there is not going to be any code submission.

It looks like Python was used by the agent to perform the account creation, and that script included completing whatever CPATCHA it was served as part of the wikibase.cloud hosting.

The screenshot to the right shows the various steps completed by the agent, as it broke down the task to be completed.

A first edit, adding a description

Read more