I'd argue that the moral principles of the Levitical law (e.g. "adultery is wrong") are not inherently bound to the specific punishments (e.g. "adultery is a capital crime") prescribed for ancient Israel.
To defend against the accusation of cherrypicking: I don't actually think the original punishments were objectively morally wrong (even though they certainly feel harsh to my modern sensibilities)—sin is no joke. At the same time, I also don't believe that the punishments (or even all of the crimes, i.e. the liturgical ones) were intended to apply to all polities throughout history. Admittedly, my argument would be primarily theological in nature[1], so I don't expect it to be convincing... we may have to agree to disagree :-P
[1] Namely, "ancient Israel is the only divinely instituted theocracy in history, so many things just won't generalize to more 'normal' polities". And/or, see Jesus' treatment of the Mosaic Law in the gospels (and the New Testament more generally).
Yes, perhaps, and that is annoying for poster, it also happens that people tell me that and I am annoyed. But there are times when it is justified. I believe this to be such a time, but perhaps I'm wrong.
How much understanding is needed? If it works as specified (you did a complete spec and occasional check-ins to ensure things are on track and then tested the delivery, right?), then what more is needed?
Understanding is needed when something breaks and you need to fix it immediately. Otherwise you become a meat proxy and now you’ve added Anthropic’s uptime as a single point of failure to your application.
>Otherwise you become a meat proxy and now you’ve added Anthropic’s uptime as a single point of failure to your application.
Yes. We're all going to become meat proxies and we're all going to add LLM service uptime as a single point of failure to... every aspect of our technological civilization. But it's all worth it because Grok will let you force feminize Draco Malfoy into a anime girl and that's worth never understanding anything again.
> exactly how the unit and integration tests are made
There should be enough detail in the spec that it's pretty obvious. And unlike - many - human devs, agents don't shy away from writing tests. Add a coverage guardrail and tell them to use red/green TDD and you're already a good way there. The main thing is to ensure shared understanding, so they also know business expectations and write appropriate tests. And... nothing here is really specific to an agent, as a human dev also needs sufficient guidance (tailored to their experience level).
This is just pure vibe coding and trying to convince yourself it's quality work. AI can't be trusted to go from an English written spec to tests
Here[0] we have benchmarks for AI writing tests for code that already has the correct behavior. Best case scenario is that they're at 67% with Fable, and that's with the highest quality specification we could possibly have (code). English is far more ambiguous
Maybe you don't trust them to, but they can go from spec to tests; I've made them (even if it initially took extra prompting and scrutiny). And ultimately tests are just a proxy to checking that X works, written by devs for devs; actually trying X is something to be done by QA and/or project/product manager before shipping.
Noone understood the code to begin with. People understand the concepts, the primitives, the "theory" as Naur said, the basis upon which a project is built. Noone ever understood a codebase worth understanding to begin with.
Bjarne Stroustrup did, at some point at least. I have a $32 real check from him for finding an error in "The C++ Programming Language (Special Edition)".
Stealing my data bandwidth by sending me unsolicited ads is also unethical. Profiling my online behavior and monetizing it is also unethical. YouTube doesn't seem to be bothered with compensating me for that. Why should I care about them?
> The second thing is that using LLMs in a useful way is a skill in itself.
Not really. I don't even bother writing complete sentences as my prompts anymore. Once the LLM has enough context on my current issue, even incomplete sentences or phrases result in the same outcome quality in LLM's responses.
I routinely steal my wife's hairbands to tie various cables in my cable stash. You can never have enough USB cables of various types. But as Murphy dictates, the USB cable that I need now is one that I don't have in my stash.
reply