Since not all asteroids are pulled to the gravity simultaneously, some kind of background starfield could make it clearer that the camera/viewport is moving.
> I sincerely don’t understand what the people who say they no longer read any code are doing
Welcome to the present.
Like many of us do not read the machine code generated by a C++ compiler, the code generated by an agent is similarly irrelevant and disposable, by now.
The machine code generated by a compiler is deterministic and reproducible (assuming using same chain/tool versions), which is why reading the human readable pre-compiled source is sufficient.
Reading a prompt but not reading the non-deterministic/non-reproducible LLM output is not comparable.
How do you know it does what you want it to do without reading it? Tests? How do you know what they test? Yes, clicking a button in a browser and getting the result you want satisfies most, but that only works on the most basic systems. Once a code base grows large enough, any one agent reading in its context wont understand the whole, and if no human does either, it becomes unworkable.
Yeah, tests. You need tests for everything and the tests + API needs to be carefully reviewed. Technically, the implementation need not be read at all. Just APIs, boundaries, and tests. You need unit tests, mutation tests (tests for your tests), integration tests, and end-to-end tests. You also need to design the system to be broken up into small submodules, which is how software should be written anyway. You push all side-effects right to the edge, and then test the core extensively.
Nobody needs to understand the whole. They only need to understand each submodule, which is easy. And then, how they interact, in which case you only care about the API and contract garauntees, not the implementation.
Realistically, this is how pre-AI software engineering worked, too. Or how it should generally work. Nobody can read or understand a 10 million line codebase. So to ensure you don’t break shit, you need the submodules, orchestration, and tests.
Correct, but I increasingly find that the version control is just a storage for code and a place to trigger CI/CD from.
Edit: ...and that the source code is useful in retaining enough context of the problem being solved. So, most people will not store the prompts, trusting that the source code provides context for the next iteration.
Is it though? I see this occurring every day in a number of projects I have visibility to.
Isn't this exactly why OS projects are over-burdened by the firehose of contributions? The maintainers will want to read the code contributions, while those up-to-date with the latest models/agents/tools already trust their output to be above the average developer's (whatever that means in practice).
How does handling support tickets/bugs work with such approach? If LLM sometimes can't handle it - do I have to beg it to keep trying, as humans are no longer an viable fallback?
The way I've seen it work is basically pointing an agent directly to the ticket, or via a proxy description.
There's a good chance that if the agent cannot handle it, a human wouldn't be figuring it out either, without additional context. That context would be the sort of only-Joe-knows-how-it-works, so perhaps something worth addressing in any case.
It's unfortunate LG screens are still the best in image quality, even though competition is getting closer. That said, the best way to use LG TVs is to immediately disconnect them from the internet and use an Apple TV 4K for streaming applications.
"Disconnect" is not enough. They will seek out open WiFi and other available LG TVs as relays. You need to remove the WiFi card or at least the antenna.
They basically twiddle with the distribution of used output tokens so that the pattern is recognizable by machine means. Nothing to do with special characters.
reply