> By the time you see a bug, the AI has already committed it to main
If you have given your "AI" full control over your repo so that it can commit unreviewed code to the main branch, you have far greater problems than a 45 second video stream delay. Besides, you'd need superhuman abilities to spot a bug in hundreds of lines of generated code in under 45 seconds.
I know this example is rhetorical and likely produced by an LLM, but this entire project seems misguided. They're streaming video of a graphical text editor to a web browser client, instead of streaming text itself, or using a web-based editor. These are solved problems. This shouldn't be so complicated...
Yeah, that was my main head-shaking moment in that entire piece as well.
Tell me again about these grandiose efficiency gains from agentic coding assistants, which I'm apparently supposed to supervise in real time as they produce shittier code than I would've. And about what an excellent idea it is to have software developed this way by people who don't understand why an automated system being able to commit to a main branch might be problematic.
If you have given your "AI" full control over your repo so that it can commit unreviewed code to the main branch, you have far greater problems than a 45 second video stream delay. Besides, you'd need superhuman abilities to spot a bug in hundreds of lines of generated code in under 45 seconds.
I know this example is rhetorical and likely produced by an LLM, but this entire project seems misguided. They're streaming video of a graphical text editor to a web browser client, instead of streaming text itself, or using a web-based editor. These are solved problems. This shouldn't be so complicated...