This only solves part of the problem, the other half is: ok so you have 3 chats going, at some point you realize you have 3 >10k line CLs to review, on top of code your colleagues are asking you to review.
Every review I’ve ever done I’ve found overfitting and brittle solutions and things tacked on instead of integrated so I refuse to give up on code reviews, but those are my real bottleneck, and having three is so much worse than one because my context and understanding is diluted and a bit muddled.
I want to time how long it takes me to land code and I suspect going serial on one thing will be faster than going parallel on multiple things. Parallel feels faster but the code review takes longer.
I end up in similar situations, the codebase I work on demands a level of professionalism opus5.5 can't muster on the first pass. Code review remains the bottleneck. Usually I approach it like a code review, reading through and as I find things I markup the code, then afterwords I have the agent collate all the feedback and we discuss and it re-implements. Usually I can simplify and improve a lot in like 3 passes.
One thing that speeds up the reviews and improves my ability to find issues and provide guidance is having the agent work on better review guides (think an html page rendered locally, with object diagrams, decisions/assumptions, animations of data flow if it makes sense, whatever). Those in hand I can read the codebase faster and talk against that document too. I think the end result is better code than I could previously write by hand, in probably 5x the speed.
Usually I can't do more than two projects in parallel though.
By far the skill I use the most is one I wrote called "resolve-review" from back in the 4.6 days. Just uses gh CLI and graphql to get inline comments, which I key with standard tags like nit/fixit. So during review, I open vscode so I can have an lsp and jump around refs more easily (only reason I still have vscode installed; frozen at v1.110.1 with ai completely disabled and I haven't got around to getting the same setup in neovim), leave comments, send review, then resolve review. I'm sure one could have hooks or scheduled tasks listening for this but it's good enough for me. Working on a thing to build a pipeline of such work, which I describe in a top-level comment.
I do not have any pressure to deliver anything (amateur), so I can only imagine how much it must suck for anyone on that hamster wheel given how much it bothers me. If anyone wants to work on something like this, drop me a line; I miss working with people.
What models are you using? At this point I'd only use Opus 5.5 for any serious work where I care about the code, so I'm interested if you're still seeing brittle solutions with it
The models are great, but the experience resonates. It really depends on what you're doing, and ultimately, how much you care. A 10k LoC PR that feels “tacked on” should help you guess the size of the code base.
So do you care about getting 10k LoC to review, in a 1M LoC code base? How about 3 such PRs? How about reviewing another half a dozen, from colleagues? And doing that 2 or 3 times a week?
I don't know how you can expect a useful answer to that question without you and OP syncing up on what you're working on. The experiences of, say, a python network programmer vs a C/C++ GPU engineer are going to be worlds apart.
I think a lot of pointless arguments on HN stem from a failure to realize that "software" is too big of a field to generalize much of anything.
Functional code that is perhaps overly defensive or specific in ways that will require updating it in the future? All the time.
What many do not yet understand is that the maintenance burden is a fraction of the effort that it takes you to review the code, much less iterate on it.
I see people on here talk about a supposed eventual collapse of maintainability if they do not review or understand the code.
In reality this never happens. The latest models can salvage and refactor even the biggest mess; all you need to do is ask.
They could probably do it even if source code isn't available and you only have a binary to work with.
Brittle by building ever more increasing numbers of abstractions rather that take a coherent view of some things. So over time you have these "seams" that the code base ends up looking like a punk motor cycle jacket.
When it becomes trivial to create ad hoc solutions, I think the utility (and thus frequency) of behemoth code bases will decrease. Because you no longer need one giant monstrosity when you're only using 3% of its features when you can have a far more efficient and targeted solution that specifically caters to your 3%, and can be trivially expanded as desired.
In fact I think we're already at this scenario, but it hasn't had the predicted impact yet because the sort of people that realize we're here already overlaps perfectly with the sort already capable of developing their own software. When e.g. receptionists start tossing together their own productivity apps in a few minutes, then we will have entered into the next phase of the economy.
> When e.g. receptionists start tossing together their own productivity apps in a few minutes, then we will have entered into the next phase of the economy.
This isn't a matter of tooling through. Receptionists won't start making their own productivity apps because most people do not default to "I will make my own thing to solve this".
Maybe some receptionists will, but most won't, just like most people won't patch their own drywall even though the tools are available in every hardware store
Now imagine somebody could just describe some damage to their drywall in a text message to their computer, and it'd be magically patched away. Suffice to say, nobody would be calling in for drywall repair.
Before computers, there were computers. [1] It's obvious in hindsight, but all of these complex numerical calculations we take for granted were often not done by the same people applying them in various ways. They'd hire computers instead, which were human calculators whose job it was to do the math.
The reason these jobs no longer exist is because calculators/computers not only solved these tasks, but completely trivialized the process to do so. We're entering into a world where many cognitive tasks, including software development, are going to be trivialized in a similar fashion - describe the problem, get an answer.
And I think this is going to do similar things to what calculators and computers did (or widespread literacy for a more historical example). The ability to e.g. write a program will no longer be a valuable skill in and of itself, but simply an expectation of anybody in any role where it might be desirable to do so.
Perhaps, but I imagine that it would be difficult for the receptionist to spec such tools sufficiently such that they would want to use the tool. Also, how would this tool be distributed or accessed? Most people don't have package managers or even desktop environments that they can meaningfully modify. To use your example, the receptionist is likely running windows on a thin client that is maintained by an msp, so how would they install and use the tool?
People talk about AI solving coding, sure, to a large extent. The problems of design and ops completely confound the layperson. Just last year, a cousin mentioned they were using like lovable or something to build a webpage for their business idea. I offered to just throw it together for them, very simple crud. They gave me what they had on lovable, and they got no further than the landing page before they had no idea what to ask for, let alone how to ask for it. Prompts were literally "ok so now make the app" and the models like "well what about x y z"? You have to be technically inclined at the very least to get something remotely useful out of these things.
Edit to say that the best way such a person might use llms to make work easier is through whatever client they are provided, probably copilot, to do toil like data entry, scheduling, etc. but those lock you into that ecosystem and interface, and the solution:problem ratio is close to 1; one cannot extend or modularize such solutions because the concept isn't even in such a person's head. Perhaps this will be solved in time, but we are not there yet, and we're not close.
Deployment is only an issue because it's assumed to be unnecessary in a current environment. As that assumption changes, so will the default setups. Of course that introduces new vulnerabilities, but as LLMs also make a mess of everything security related (and future LLMs will likely make a mess current era 'LLM hardened' setups, onward) our approach towards security and the internet will change in ways that are difficult to predict today.
I agree that plenty of people are currently hesitant to use LLMs for technical purposes, but I don't think it's because they literally could not do it. LLMs will now code up entire workable apps from minimal/vague/contradictory descriptions. If somebody only got to a landing page it's because they only prompted for a landing page, possibly trying to mimic how a human developer might have previously built a site - and quickly getting lost. But if you just say 'make a website where people can order widgets, manage their orders, and do all related tasks' it'll get done, no technical knowledge needed.
So I think we're mostly in a transitory phase. As people realize how powerful these tools have become, adoption is simply unavoidable.
Granted, people would have to be able to accurately describe what they want to the computer
Many people cannot use a calculator to find the area of a triangle because they don't remember the formula for the area of a triangle, or figure out an angle because they don't remember trig
It's entirely possible that using AI to create software will run into the same problem. It won't be a rising tide lifting all boats, but only the top % of boats
That's still a pretty substantial problem if it is the case
Her interview with Arvo Pärt (composer) is amazing. She starts off being very Björk, and as a viewer I wondered where this would go. Turns out they live on the same planet, speaking the same language.
> partition different applications off from each other, and carefully control how they can communicate.
without
> provide access to hardware resources
That’s still definitely what an OS does. The application model is often very loosely coupled. See web browsers.
A difference between embedded systems and operating systems is the ability to provide access to hardware (in such a way as to isolate and dictate communication) _dynamically_ with a-prior unknown requests.
The guitar is also immaculate slowed down and that was her too. I always thought it was some hotshot Nashville session musician. One of the best guitar licks of all time.
Dolly wrote the lick herself, and when she was in the studio with the session players, they wanted her to show them how to play it [0].
She ended up having Chip Young lay it down on the record since her long fingernails made it difficult to nail consistently. This is also why if you watch videos of her playing guitar she plays in open tunings [1].
I still carry the rather 20th century idea that a performer of almost any kind also ought to have some sort of other talent in addition to their main one. The versatility of that sort of thing is one of the things that should separate a pro from the rest. I generally count "professional level musician" on more than one instrument as fulfilling that contract... perhaps one of the easier of the options, but it still carries that versatility advantage. Another example that I'm quite fond of is famous comedian Steve Martin performing Dueling Banjos with Kermit the Frog. The combo of two professional entertainers playing off of each other combined with the music skills creates the opportunity for a creative routine.
Vint took what could have been a prestige emeritus position at Google and turned it into a platform to champion accessibility and “Greyglers”. The man has more class than his suits.
reply