This is the crazy part with LLMs. It knows much more than you as a single user will ever realize, as it only shows the part that matches with what you put in.
I was building a tool to do exploratory data analysis. The data is manufacturing stuff (data from 10s of factories, having low level sensor data, human enrichments, all the way up to pre-agregated OEE performance KPIs). I didn't even have to give it any documentation on how the factories work - it just knew from the data what it was dealing with and it is very accurate to the extent I can evaluate. People who actually know the domain are raving about it.
You could build (code, if you really want) tools to ease the review. Of course we already have many tools to do this, but with LLMs you can use their stochastic behavior to discover unexpected problems (something a deterministic solution never can). The author also talks about this when talking about the security review (something I rarely did in the past, but also do now and it has really improved the security posture of my systems).
You can also setup way more elaborate verification systems. Don't just do a static analyis of the code, but actually deploy it and let the LLM hammer at it with all kinds of creative paths. Then let it debug why it's broken. It's relentless at debugging - I've found issues in external tools I normally would've let go (maybe created an issue for), that I can now debug and even propose a fix for, without much effort from my side.
So yeah, I agree that the boring part has become the more important part right now (speccing well and letting it build what you want is pretty much solved), but let's then automate that. Because if anything, that's what I love about this job: I get to automate work, so that my users (often myself) can be lazy and focus on stuff that's more valuable/enjoyable/satisfying.
I think my sweetspot is having one (30min+) features a day. And then after spend synchronous time iterating on it to fix edgecases or tweak stuff.
The rest of my time goes to prepping those big features (designing, speccing, talking, thinking, walking).
Going to see how big a feature can be before the quality suffers too much and it becomes unmaintainable. This highly depends on how good I spec it out and how good I orchestrate the agentic workflow.
ASML has a near monopoly on the most advanced chip machines. They maintain that by 'just' being the most advanced and having lots of patents.
They haven't branched off into making chips themselves. They keep their focus on selling the factories.
I think they haven't, because ASML itself doesn't have production lines. Every machine is one off. It even gets delivered with a team of engineers to keep it running.
The same probably holds true for software factories: the best ones are assembled by the smartest people (wielding AI in ways most of us don't). They are not in the business to produce software at scale, they are in the business to ensure others can do that using increasingly advanced software factories.
This relies on the premise that such a factory cannot produce a more advanced factory without significant human intervention (e.g. high ingenuity and/or lots of elbow grease). If this doesn't hold true, then we are in for some interesting times x100.
So far in my career I have always had more requests coming in than implementations going out. If I can go 3 or 10 times faster, than I will still have plenty of work. Especially for the slew of ideas that are never even considered to put towards a dev, because it's already considered to be too low value to have it even be considered to be build. Or the ideas that are so far fetched they were never considered feasible. I am not worried work will dry up.
What I believe is going to be interesting is what happens when non-engineers adopt building with agentic AI. Maybe 70 or 80% of their needs will be met without anyone else directly involved. My suspicion is that it will just create more work: making those generated apps work in a trustworthy manner, giving the agents more access to build context and make decisions, turning those one off generated apps into something maintainable, etc.
Our public transportation infrastructure is so badly managed that many jobs will ask you if you have reliable transportation and fire you if you find yourself without it. If your car breaks here it's often not really a option to save up for a bit first.
The US is considered to be a flawed democracy for about 10 years now[1]. Europe, especially the powerful west, has the most healthy democracies.
It's absolutely not a given that the European democracies will survive, people here need to step up in strengthening it against illiberal forces as well, but it's in a much better starting position.
Example: in the Netherlands there was a government with an illiberal far right party (Wilder's PVV). They didn't achieve much, but there was a year of stagnation and the far right talking points have become even more normalized. Other democratic institutions, like judges had to be more on the defense. However, nothing fundamental is broken.
One flaw we have in Germany in particular is that the chancellor is allowed to stay in power indefinitely if people vote for that person, which potentially gives a lot of time to rebuild the society. It worked out with Merkel who is the anti-thesis of an authorization figure, but that might have been luck.
I don't know how resistant the German constitution and democracy is. I believe it's robust but that's also what people thought about the US with that "checks and balances" that turned out being fake for the most part.
General warrants (the sort of thing being done here) are explicitly listed as one of the things motivating independence from england in the declaration of independence.
I was building a tool to do exploratory data analysis. The data is manufacturing stuff (data from 10s of factories, having low level sensor data, human enrichments, all the way up to pre-agregated OEE performance KPIs). I didn't even have to give it any documentation on how the factories work - it just knew from the data what it was dealing with and it is very accurate to the extent I can evaluate. People who actually know the domain are raving about it.
reply