imagent

You can also do code reviews in pure git:

https://github.com/google/git-appraise

I used git bug before but found I missed being able to edit tickets with a Markdown editor. So I built this: https://github.com/LoumTechnologies/ticketry

No, we're in a vicious cycle where the police rarely do anything helpful about violent crime, so people have stopped reporting it.

You're hired

Better yet, detect mouse clicks and display a popup right where you clicked that says something you didn't want, and show a busy indicator to make sure the user understands that they just agreed to something important.

Keep in mind while this is the date they officially became part of SpaceX, they have already been collaborating on building models together. So don't expect a significant bump in performance on new Grok models due to the additional data from Cursor--that bump already happened with Grok 4.5[1] and now 4.6.

[1] https://cursor.com/blog/grok-4-5

> Nice semi-colon. Written by AI?

Damn I'm going to have to update my personal style again to stay ahead of the AI police

(My meta point is that people are altering their personal writing styles to avoid sounding like AI)

Architect your system to use the best tool for each problem. Doing a minimal data pipeline? Use Python. Building a backend? Use Go. Building a frontend? Use React / Typescript.

Building a stack that does all of these? Still use Python, Go, React/Typescript. Because by architecting it this way you make the AI less likely to accidentally refactor logic between layers. In other words, architecting with multiple languages helps create persistent boundaries that isolate different kinds of logic into their appropriate modules.

What is GS?

The cost of prototyping has dropped so much due to LLMs and coding agents that it basically always makes sense to prototype something to elicit feedback, just as part of the requirements gathering process. E.g. if you can spend $50 to understand something that will save you two weeks of effort, wouldn't you do that? That's the sort of dynamic I'm talking about.

A zen master asked a junior engineer to go get him a rock. The junior engineer asked what kind of rock he should get and the master replied by knocking him in the head with his cane. The junior thought for a minute, then asked, "would you like a round rock or a flat rock?" Again, the zen master rapped him on the head. The junior thought for a moment, then went to the creek and fetched a rock at random. He brought it to the zen master who inspected it and then said, "No, I want a flat piece of flint for starting a fire." The junior engineer was then enlightened.

Stakeholders will only give you requirements after they see the prototype. Thus, the spec and the prototype to elicit it are two sides to the same coin. Once the spec if correct and the prototype is starting to show its age, throw away the prototype and implement the spec with a fresh start.

Limiting the amount of Fable usage makes us reserve Fable for our hardest problems, which is probably a very important signal when it comes to how valuable the training data is.

In other words, I think they've found a way to manipulate their customers into labeling sessions as "high quality data" (Fable sessions) and "low quality data" (non-Fable sessions).