Forgot your password?
typodupeerror

Comment Re:sarcasm aside (Score 3, Interesting) 43

The way we are using it, and it can type way faster than I can

  1. The main agent, it doesn't do anything other than determine where the artifacts live, and coordinate sub-agents
  2. The research agent, it does the research and passes that back up
  3. The planning agent, it gets the research from the previous step and planes out the changes
  4. There is a hard stop here to review the plan, there may be some back and forth on the plan
  5. Once approved it goes to the implementation agent, which writes the code.
  6. The test agent writes tests, does Playwright QA if UI is involved.
  7. Conditional agent depending on blast radius, it will run an adversarial code review with 1-3 different models. (this does actually catch bugs)

Some of these agents use different models depending on what they do.

Comment Re:How were they billing before? (Score 3, Informative) 43

A Business plan gets you 300 "Premium Requests" for $19/month.

I'm not sure anyone outside of GitHub knows what qualifies as a "Premium Request", but once you pass 300 you get billed at $0.04 per. This model has no concept of tokens in or out.

As I understand the new model, you pay your $19/month and get $19 in token credits. This will almost certainly increase costs for anyone doing any heavy lifting

Comment Re:just bought at 2025 cx-50 (Score 1) 47

If you use CarPlay, the default settings won't let you touch the screen to do anything, so you have to bounce around the UI with the scroll wheel, and with the latest CarPlay the active item is gray, and the inactive items are green. I don't know who signed off on that, but they should be fired.

You can enable the touchscreen while the vehicle is in motion.

Slashdot Top Deals

The first rule of intelligent tinkering is to save all the parts. -- Paul Erlich

Working...