Because if both are at home working, well, you can have some couple time (also called "sex") during lunch break or at any given moment when there are no meetings etc.
Reading the piece I _hope_ they are trying to make a point and not really thinking they are not going to help novices become juniors. But who knows, nowadays...
> (Btw the general idea that there are animals that we don’t know about is not remotely far-fetched. A new possum genus was discovered like a month ago.)
I might be totally mistaken but I think most of the times when a new "species" is found is either a) some different genus which a non trained eye would not be able to distinguish from an existing one, or b) some species that lives only in a very difficult to reach place with some very specific conditions (i.e. underwater near volcanoes).
Something so different with so many "sightings" as a Bigfoot? Almost impossible.
This.
In my case I do write from time to time tickets with an LLM but it's always after a long exploratory session with Claude Code, when I go back and forth checking possibilities and gathering data, and then I tell it to create a ticket with the info gathered so far. But even in that case I tend to edit it because I don't like the style or add some useless data that I want to remove.
Don't discount the value in rubberducking with an AI.
They write shit code, but but can be prompted to highlight common failures in certain proposals.
For example, I am planning a gateway now, and the ChatGPT correctly pointed out many common vulnerabilities that occur in such a product, all of which I knew but may not have remembered while coding, like request smuggling.
It missed a few, but that's okay too, because I have a more comprehensive list written down than I would have had if I rubber ducked with an actual rubber duck.
If I finally write this product, my product spec has a list of warnings.
Not really, the exploratory phase is (probably) much faster with Claude Code that on my own. Writing a well specified ticket is very, very time consuming. With Claude Code for me it's way much easier to branch off and follow the "what if actually...?" and challenging some knowledge that - if I had to do it manually - I will just take for granted during ticket writing. Because if I'm "sure enough" that a fact is what I recall it to be, then I just don't check and trust my memory. When paired with an LLM, that threshold goes up, and if I'm not 101% sure about something, I will send Claude Code fetch that info in some internal artifact (i.e. code in a repository, actual state of the infra etc) and then take the next decision.
Grok in Tesla is utterly terrible, a rushed out product with a very bad UX.
As a simple example, it's the very first feature in Tesla's UI that does not come translated to the UI language set by the user but it's just available in English. Never happened before.
Yes, they do it with the paths inside the `Edit(path/to/file)` tool calls as well. But I have not seen any links using the capability to link to line numbers.
It's pretty clear. If you have your bank account with 2 owners, and with X on it, X/2 are yours and X/2 belong to the other owner, at any point in time.
Case in point, if one of the owners deceases, you can withdraw X/2 at most. The other half is blocked until the inheritance paperwork is completed and that half has a new legal owner(s).
If people lack sense of humor or satire, even if pathologically, well, too bad for them. Why should the rest be denied of that satire? It's not harming anyone at all.
Unfortunately it's not too bad for them, it's too bad for everyone they're around. They aren't the ones that lose out when we start dismantling open source communities.
Ask me how I know it...
reply