My suggestion is to try to describe the main thing it actually does in a single sentence. For example, “If the battery’s above 20% it leaves the light off while the battery charges.” I can understand that.
An organization can become fundamentally opposed to the purpose for which it was created. Organizations simply don't follow the same laws as the individuals inside it do. A company can be made of geniuses and be totally ineffective; it can be full of talented go-getters and be completely unable to fix problems.
These languages were developed for hypertext. Discord is hypertext. The question is why Rust or C++ or anything would be so suitable for developing chat rooms; it’s not even clear why JavaScript would necessarily be slower after being statically compiled.
Besides the obvious (it’s a web browser coevolution) it converts strings as needed, which is undeniably appropriate for the use case. Also indirect memory management and GC is appropriate for the use. It’s just more suited.
Yes, the first one is not required and shouldn’t be used, write your own leftpad then. The second is about as awful as getting NaN, which is to say not, and can be overridden in the prototype anyway if you want more casual logging.
But that still doesn't answer the question of why Claude passes the info to web sites. What if it finds your banking information in a personal file and uses it to achieve its goal, which is not different technically?
Some websites will return an error if you send a request to them without a User-Agent - for example, crates.io does this. Curl doesn't send a User-Agent by default.
Then, your agent invents a User-Agent and it sometimes invents one with your email in it.
It doesn't even require prompt injection or a failed request, it might be in the agent's pretraining knowledge that a given website requires a user-agent.
It's just doing what it's supposed to do, analyzing the statistical patterns of a natural language prompt and matching it to a likely response.
What's ridiculous is an assumption that it "it should never do something so ridiculous" as if an LLM is a person who understands what that word means in any context other than next-token prediction.
Asking a non-deterministic machine to act like it's deterministic is never a good idea.
Where Claude Code has supposed boundaries between deterministic and non-deterministic tasks and flags.. generally.. it's unclear how much privacy has been a part of that and what implication that could have.
Of course a few rural votes will be rejected, but rest assured plenty more of the urban votes will be rejected too, for a net gain of many rural votes!
Wait until the teen becomes an adult and finds out how much pointless, performative work it takes. Oops, wasn’t supposed to let that cat out of the bag yet!
reply