Moving all of astronomy to space based observations is entirely incompatible with the way that instruments are funded, built, and deployed. It is only valid for a set of highly specific and well funded observatories that take decades to get off the ground and can never be updated, improved, or modified to search new scientific directions.
I am aware of no orbital solutions for a catastrophic Kessler cascade in LEO. The only place you could engineer one is in GEO, because that’s a singular orbit, not a plane much less a volume.
Second, the situation is already so bad that current satellites in LEO already require active collision avoidance systems in order to avoid becoming sources of debris themselves. Starlink alone reports over 1,600 close encounters each week.
What I said applies to space, too, outside GEO, for the number of satellites anyone is currently talking about launching.
> the situation is already so bad that current satellites in LEO already require active collision avoidance systems in order to avoid becoming sources of debris themselves
They require collision avoidance to avoid being lost. There is no risk of a Kessler cascade in LEO right now and nobody who can do orbital mechanics is claiming as much.
We’d need millions more satellites than we have right now to start approaching the point where atmospheric clearance falls below the rate of new-debris production. And even then, you’re talking about a problem in specific orbits for months, maybe years. In the meantime, you get to allow nature to reclaim huge amounts of land from cell towers and conduit.
I just can't get behind this perspective, perhaps because I am a 'bad prompter', simply due to the lack of capability from current models. I end up rejecting them, asking them to implement again, they spew out tons of crap code instead of a 10 line fix, and on, and on.
Note that I'm not saying the agents are useless. They certainly write a lot of code and sometimes it is good. But I don't think you can get away without touching code yourself simply because at some level it is often the most concise way to get your idea across. I find it best to implement a core set of changes by-hand, and then ask the system to e.g. replicate them to other dependencies. I genuinely don't understand how anyone can work on a system with any complexity, and get the results they actually want, without touching code.
There seems to be a split. There are a substantial group of people like yourself who don't get what they want from LLMs. There are folks like me who get excellent idiomatic code almost every time. Both experiences are real and should be respected. I'm hoping that future investigations will find out why that is the case.
People write applications that work with the S3 API but may want to host their own storage for a variety of reasons. Personally I make use of S3-compatible services for pre-signed url access to data on disks I own. The distributed aspect is only one reason why someone might want an S3-like service.
Yeah, having your agent write 3x the code in exhaustive tests (I tried this recently and got 600 lines of tests for my 100 lines of code!) sure makes things look great, but when you actually look at the content of the tests they’re meaningless. Good tests validate the use of design patterns, ensure that dependencies hold, and are meaningful (e.g. shortcut debugging by setting up useful state) when they break.
Maybe I'm entirely out of the loop and a complete idiot, but I am really not sure at all what people mean when they talk about this stuff. I use AI agents every day, but people who say they spend 'most of my time writing agents and tools' must be living in an absolutely different world.
I don't understand how people are making anything that has any level of usefulness without a feedback loop with them at the center. My agents often can go off for a few minutes, maybe 10, and write some feature. Half of the time they will get it wrong, I realize I prompted wrong, and I will have to re-do it myself or re-do the prompt. A quarter of the time, they have no idea what they're doing, and I realize I can fix the issue that they're writing a thousand lines for with a single line change. The final quarter of the time I need to follow up and refine their solution either manually or through additional prompting.
That's also only a small portion of my time... The rest is curating data (which you've pretty much got to do manually), writing code by hand (gasp!), working on deployments, and discussing with actual people.
Maybe this is a limitation of the models, but I don't think so. To get to the vision in my head, there needs to be a feedback loop... Or are people just willing to abdicate that vision-making to the model? If you do that, how do you know you're solving the problem you actually want to?
Why don’t “we” just build more cell towers?