In the strongest interpretation of that it would offer only data which the user is allowed to access. Why do you assume that them implementing a feature to prevent PII being accessed that they then turn around and return data which the user is not supposed to access?
Looks like a clear divide in people‘s experiences based on how they use these new tools:
1) All-knowing oracle which is lightly prompted and develops whole applications from requirements specification to deployable artifacts. Superficial, little to no review of the code before running and committing.
2) An additional tool next to their already established toolset to be used inside or alongside their IDE. Each line gets read and reviewed. The tool needs to defend their choices and manual rework is common for anything from improving documentation to naming things all the way to architectural changes.
Obviously anything in between as well being viable. 1) seems like a crazy dead-end to me if you are looking to build a sustainable service or a fulfilling career.
"This guy 100% must be in Ukraine. It would be one of the few places in the world where you can feel relatively safe right now to not just design but build and launch and even better, publish documentation on the web of you doing such. Surely there is NO WAY person is in any other country."
looks at his githubsee's he is a US college student
What was the Apple Dev account needed for? Previously I remember it was only needed for submitting apps to the App Store, not running Dev builds locally.
> Like every year, I decided to travel to FOSDEM by car. It is not the most relaxed option, but it comes with one very important advantage: arriving early enough to secure a parking spot directly on campus. That also means the journey starts very early in the morning, long before the city fully wakes up.
Curiously backwards. That's one way of reframing a disadvantage as an advantage. The train connection seems to be 3h15m to 3h30m from Neuss train station to FOSDEM. A single connection for the long-distance train in Cologne, the rest is local public transport within Brussels.
How fair would you think if a potential employer assumed from your (hypothetical) incompetence in picking a suitable hairstyle and outfit for an interview that you were not fit for a non-customer facing role?
While it absolutely makes sense to keep your important data backed up, I know people who were great academics in their field and yet managed to delete all their PhD work (before services like Dropbox and OneDrive became common).
And here I was hoping OP was being sarcastic. Yet it‘s reasonable we‘re nearing an AI-fueled Homer drinking bird scenario.
Some concepts people try out using AI (for lack of a more specific word) are interesting. They will add to our collective understanding of when these tools, paired with meaningful methods can be used to effectively achieve what seemed out of reach before.
Unfortunately it comes with many rediscovering insights I thought we already had, badly. Others use tools without giving consideration to what they were looking to accomplish, and how they would know if they did.
You could make an attempts using a scratch remover, which are available for scratched screens. There is some chance that it gets you there, though it depends on too many unknown variables to know for sure.
They do have an export functionality, which I encourage everyone using Claude to use occasionally. This is unfortunately reality–most of us are using digital platforms and services which can be taken away. From vacuum robots to digital thermostats and email accounts and llm's conversation history.
Migrate to services you trust the most where it makes to you. Occasionally export data from all of them, more and less trusted, anyways.
That’s not too bad and mirrored some of the feedback in this thread. Tldr: interesting idea, more worthy of a blog post or a thread in one of your favourite online communities, rather than a paper.
