Probably, but if I squint a bit, I could also interpret it as "detailing" in the sense of cleaning (often a car) and addressing all the places which are often overlooked or require special tools.
> But that slow formation led to software that was durable rather than ephemeral, with a strong foundation that could be built upon.
People say that agentic development is great because you can churn out so much so fast. But that doesn't mean that any of it will be truly good and reliable.
The things that are truly insightful and solid end up being used exponentially more, which makes the linear cost of extra development time (asymptotically) insignificant in the cost/benefit equation.
The emphasis on quantity while neglecting quality calls to mind a passage from EWD1175[0]:
> My second warning remark is that I shall refuse to discuss the academic enterprise in financial terms. The first reason is that the habit of trying to understand, explain, or justify in financial terms is unhealthy: it creates the ethics of the best-seller society in which saleability is confused with quality. The other day we had to discuss the professional quality of one of our colleagues, in whose favour it was then mentioned that one of his Ph.D.s had earned lots and lots of money in the computer business, and few people seemed to notice how ridiculous a recommendation this was. We also know that the financial success of a product can be totally independent of its quality (as everyone who remembers for instance the commercially successful IBM360 should know). The second reason for my refusal is that the value of money is a very fuzzy notion, so fuzzy in fact, that efforts to understand in financial terms always lead to greater confusion. [Remember this, for it is quite likely that this afternoon will give you the opportunity to observe the phenomenon. Note that money need not be mentioned explicitly for the nonsense to emerge, a reference to "the taxpayer" can do the job. The role of "the taxpayer" then invariably leads to the conclusion that of State Universities at least the undergraduate curriculum has to be second- or third-rate.] The final reason for my refusal is that the habit appeals to the quantitative mind and I come from a culture in which the primarily quantitative mind does not evoke admiration. [A major reason that we considered Roman Catholics to belong to a lower class was precisely their quantitative bent: they always counted, number of faithful, number of days in purgatory, you name it.....]
Everyone I know who used the 360 has a lot of nostalgia for it.
It was well thought through. I mean, the 360 architecture is still with us because it avoided the traps that killed the PDP-11, VAX and the 68k -- as much as I loved the PDP-11. It's true when it came out that nobody had any idea what a general-purpose operating system looked like and it took a decade for them to productize VM so that you could run as many operating systems as you needed simultaneously.
The trade-off between quality and speed of development has always been a tenet of software engineering. Agentic coding changes the equation a lot, but the equation is still there.
> The trade-off between quality and speed of development has always been a tenet of software engineering. Agentic coding changes the equation a lot, but the equation is still there.
The quality and speed tradeoff doesn't matter if other incentives aren't aligned. In today's product-driven world, where usage stats are compiled in real-time, features are added and then pop-ups, nudges, etc are added to software to get product usage up. These features may or may not add quality, relevance, etc. But the "success" is measured in usage, forced or not. This is essentially Microsoft today (especially with copilot), but even after every major apple OS update, I get "what's new" pop ups for every Apple app (notes, reminders, mail, etc) on every platform (iPad/iPhone/Mac) that I own. I opened the email app to check my email, don't get in my way!
It may be so but the article does not claim that the strong foundation is the code, rather it seems to be product design, and design of other products, at that (the two predecessors, webapp and desktop app). No reason why you couldn't study existing products now and tell your agent to build something based on that.
This feels like a sleight of hand to me. The hard part of evolving Scribe and Web Scrapbook was discovering that a browser extension manipulating a local SQLite database was _the only_ architecture that could reconcile local offline persistence with live DOM scraping across arbitrary catalogs of academic data.
An agent can synthesize existing solutions but (because I see this failure mode at work constantly) it can't synthesize an architecture to resolve the sorts of tensions that the person prompting it doesn't yet understand (not that that is stopping anyone). You can't prompt it to build something if the operational primitives required to solve the problem haven't been mapped.
"Build a tool based on Scribe and Web Scrapbook" in 2003 would've made a fragile PHP wrapper because that's what the existing landscape looked like.
Yes, exactly. And this is why I don't think that the LLMs can make significant process beyond what humans have done and published.
"But the math proofs," people will say. A lot of those seem to be spam-solving things with a huge swath of existing lemmas, and a some of these are being debunked and retracted.
Just today I was quizzing ChatGPT about a basic grammar question for a language that has huge training data but for which the grammar was not well documented. It kept giving me confidently wrong answers until I drilled and drilled it and then finally it found/gave back an explanation that perfectly fit a pattern given in one particular grammar, citing that as a source. It doesn't appear to have been able to figure out the inner structure on it's own. It appears only able to pattern match and put things together from what humans have already discovered and written.
Right, there's a difference between statistical interpolation and semantic induction. The whole point is that LLMs can't reason from first principles to drive missing rules. It keeps confidently feeding you approximations until it collides with some source that already mapped it.
Interesting take, given that the whole reason LLMs are interesting is that they're the first system we have that can work in semantic space. Statistical interpolation, that we've solved long ago.
I think that's equivocating on the word semantic. Word embeddings map concepts like "king - man + woman = queen" or cluster synonyms together in high-dimensional vector space and the ML literature very loosely calls this "semantic space." But a high-dimensional topology of token co-occurrences isn't semantics in the sense of computation or formal semantics. It's still "just" measuring distributional similarity. Some vector that represents "thread deadlock" lives near tokens like "mutex" and "race condition" and "starvation," but the model itself has no concept of concurrency and contention.
Claiming we "solved" statistical interpolation long ago just means curve-fitting and basic regressions on structured data. Transformers are a truly impressive achievement, scaling all of this to unstructured high-dimensional text topologies, but it's fundamentally the same math operations on statistical proximity.
Like how do we explain hallucinations here? Tokens that are hallucinated are semantically "close" in that vector space but they're completely false in reality. If LLMs operated in a true semantic space they wouldn't hallucinate CLI flags that don't exist.
> Some vector that represents "thread deadlock" lives near tokens like "mutex" and "race condition" and "starvation," but the model itself has no concept of concurrency and contention.
I propose that concepts of "concurrency" and "contention" are themselves vector in latent space. All concepts are. Recall that we're talking about a 10^4 - 10^5 dimensional space. You can fit in pretty much any conceivable association as some direction in there.
And try to zoom in on any concept you know. If you do, it should quickly become apparent that there's never any concept you can give a closed definition for. We can only define concepts, and we can only learn them, through generalizing from examples. Which is conceptually (pun not intended) regression - finding a vector along which examples live.
Good stuff. I share this view fully. I've been working on a project, which I am happy I had no agentic help on for the first year. When you lay the architectural foundation you need to start with a vision, derive constraints and then map a solution to all of them. This takes a level of intentionality that agents don't have. Probabilistic models will work against anything that is unconventional, so they tend to favor low-value solutions that have already been seen.
Wrote up the longer version of my journey on that project here:
Paradoxically, AI enables workers to feel more connected to the fruits of their labor by reducing their need to specialize; they are now able to field adjacent tasks.
This kind of thing is awful if this is how engineering is going for user-facing apps, but disastrous if this is how it's going for infrastructure and libraries.
In another discussion I shared about how LLMs took my completely novel work on a human-language grammar and parrotted it back to me in chats, using the terms and concepts that I invented.
But there were two big problems:
1. It misunderstood things and didn't communicate the ideas properly, in essence making these helpful terms very misleading and confusing.
2. It refused to cite my work as the source of these terms and concepts. I prodded and prodded and it just kept citing other works that never mentioned the terms.
I am not worried about intellectual property theft. My work is free and out there for the public. What is deeply concerning is the inability to deterministically nail things back down to the source. Who created this and who said this, where can we get to the source and check if this is true? Good luck.
LLMs are using what would would be considered the most deplorable practices of plagiarism, lying, and mangling sources. Any student would fail doing this. But they are being pushed as the number one source of truth and progress.
This is part of how LLMs are hurting progress. People are moved away from things like StackOverflow or new projects where they pose and answer questions with real people, or create novel things, and pushed more and more to whatever answers or solutions the LLMs will spit out for them.
reply