Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- read this to mean the construction material. was wrong.by effnorwood
- has anybody successfully shipped anything with htmx and llm ?
i tried it before with sonnet and the results weren't very good
went back to react
by zuzululu - I believe critical thinking, having a stance, an ethos, is the one thing LLMs can structurally never be good at.
Shameless plug: https://open.substack.com/pub/deimos28/p/the-friction-collap...
by deimos_28 - maybe slightly unrelated but the new htmx homepage (https://four.htmx.org/) feels a little ironic, seemingly written with tailwindcss and a full JS ecosystem Astro build system. It also has the ‘vibey’ ‘hypey’ landing page design that’s hard to describe but you’ll find on any web framework, rather than dropping you to docs like the old site.
Compared to the original simple HTML site it’s really surprising to see from the grugbrain.dev author!
by varun_ch - yeuch … should’ve used https://harcstack.org, like the new https://raku.foundation siteby librasteve
- :) i let a younger person on the core team create the new website for something different
it is using astro, we are scaling down the use of tailwind (I wanted to give it a try, but didn't really click with it.)
I don't mind someone doing something kind of fun with the website and trying something new out, I know some people don't like it but some people do. All good.
- > Technical debt, I assert without evidence1, grows exponentially, and therefpre it is very important to minimize it in your projects.
This actually seems like a really important idea absolutely deserving of its own blog post.
I'd have to think about the exact argument for why this feels so right, but the kernel would go something like this: whatever you build on those parts of the codebase where you have technical debt incurs new technical debt, because you're building on top of abstractions you'll remove later. The reason you have to remove the new abstractions, too, is that abstractions are like puzzle pieces: their structure determines which other abstractions they can connect with. So, as a rule (there are some exceptions), you can't take out one bad part, replace it with another, and leave everything around it untouched.
And, of course, it's easier to build on top of something creaky but currently serviceable than it would be to first rip that out and replace it, so that's what you do in most cases ... and the whole codebase gets more creaky and less serviceable; you increase the amount of abstractions you'd have to rip out and replace before building something new. The problem does, indeed, grow exponentially.
The argument is free to a good home -- I don't have the time for a full, meticulous elaboration, but I'd love to read one if someone is interested in making it.
- Ward Cunningham, who coined technical debt, describes it as having interest, which is exponential:
> Shipping first time code is like going into debt. A little debt speeds development so long as it is paid back promptly with a rewrite.... The danger occurs when the debt is not repaid. Every minute spent on not-quite-right code counts as interest on that debt. Entire engineering organizations can be brought to a stand-still under the debt load of an unconsolidated implementation, object-oriented or otherwise.
by rng-concern - I agree, it is an interesting thing to ponder. I often phrased it to myself that the cost of technical debt compounds the lower in the code stack you go.
Said another way, tech debt has a multiplicative factor the farther away from the end user you get. Tech debt in the database is worse than in the data layer. It is worse in the data layer than in the business logic. It is worse in the business logic than in the UI code. etc.
This is related to the fact that it gets exponentially more difficult to refactor code the farther away you get from the end user. Changing the database is usually more difficult and impacts more things than the data layer code. And on and on we go back up.
by Nemi - It's a good write up, but it's lacking some details, the most important one is: which Claude model was used?
The second issue is: what was tooling and the prompt approach?
(To be clear, I have no problem with the premise of the write up. But without some details like this, it's sort of like saying "I had a bad board on my deck, and my tape measure wasn't able to help me remove the nails. What a bad tape measure."
by wiremine - It's more like asking what editor and keyboard layout they use. Highly relevant to the user but you should simply assume someone describing work is using a setup for it they find productive. If you decide to dismiss their output it wouldn't be over these details.by giraffe_lady
- Opus 4.whatever (it was last week) via a command line interface in the IntelliJ Claude plugin.
The series of prompts weren't particularly interesting or innovative on my part: a paste in of the user report then a few back and forths on fixing it, me reviewing the changes and coming up with the final answer.
- I disagree with the trope -- (AI effects) "the slow dulling of our intellects". I am old enough to remember my career change, being a developer in the Apple ecosystem, confident with Objective-C and native system libraries in iOS and MacOS. I changed direction using a very different software stack in cloud services as a data engineer with deep utilization of Clojure. I have personal projects that I occasionally would return to in the former world -- often a decade or more later. I saw what I forgot immediately; but soon after, with engagement, I saw how quickly I was able to remember. Extended use of AI for me has exactly this footprint. Even "use it or lose it" is wrong -- "use it when you need to" is honestly more like it -- the brain is plastic. Some AI fears are warranted, this isn't one of them.by waffletower
- In all my side projects, instead of thinking about architecture or design decisions, I just ask it what I want the end effect to be. "I want this button to do a thing". You're saying this is good for my brain?by luisln
- do you propose its maybe closer to the idea that you can regain strength faster after having lost it (in the context of bodybuilding and extended time off)? Gaining something from scratch requires much effort and experimentation, regaining it less so?by hankbond
- > I saw what I forgot immediately; but soon after, with engagement, I saw how quickly I was able to remember.
We actually have pretty good models for how long it takes to forget things. It's the same basic math that powers Anki. To oversimplify, if you force yourself to remember something right before you would have otherwise forgetten it, you will remember it roughly 2.5 times as long before forgetting it again. (This changes at both the shortest time intervals and the longer ones, so treat it as a rough rule of thumb, not an exact formula.)
But this provides a handy bound! If you've been doing something professionally for 20 years, you should expect to remember it for another 50. At which point you're likely well into old-age, and memory performance may decrease for other reasons.
Where AI kills you is actually at the other end: initial learning. You are much less likely to need to recall something after 1 day, 2.5 days, 6.25 days, etc. And thanks to the lack of the "testing effect", memory formation will be much weaker.
In other words, I would naively expect AI to make long-used skills a bit rusty, but to drastically impede formation of new skills and knowledge.
by ekidd - Interesting read! Creating tests is highlighted as something Claude did well, but it strikes me that all the weaker rejected solutions could have been avoided if it were really good at designing intelligent tests for itself. For example, the first solution “was very specific to the reported bug and wouldn’t have fixed the general case” and the third suggestion “prevented the perfectly valid use of as conversion expressions in go commands as well”. I imagine both of these cases could have been noticed and avoided by the agent if it had planned out adequate tests ahead of time.by thorum
- As humans we have a concept of viscosity. That resistance, like being in quicksand or a swamp, is how you “easily” identify a code smell, something that needs to be refactored, etc. Part of it is human laziness, part of it some concept of elegance, an itch of being not quite tidy as it can be, etc.
LLM, being a tiresome little helper, will gladly output hundreds of lines, hacks, and what have you.
I don’t think any amount of tests, prompts, harnesses and other “my shaman is a better shaman” will help it to acquire this trait. Some other AI architecture someday maybe — just not today.
And that’s why it is good at what it is and really bad at stuff like code “design” (unless it is a well-known solution being baked in the training set)
by piskov - This is kind of what coding with LLMs feels like. Gradually increase guard rails "outside of it's context (automated)" to get the results you want out of it. Static typing, quick compilation, not having nulls, and lints are a great start (I would also argue for managed side effects and functional, but to each their own).
It gets pretty far to the solution on it's own and quickly, but then you spend time adjacent to the problem, building out it's cage while iterating through the remainder of the solution.
by rapind - hello all, this is an article I wrote up on my interaction with an agent, Claude, in fixing a bug in the hyperscript parser
it was a rather mundane bug, but i thought the interaction was interesting and worth analyzing to show where AI is very strong and where it is not as strong
- Always exciting to see a former professor on the front page and always an enjoyable read Mr. Gross!by hugeBirb
- I very much love your work Carson, it has always been and remain a fresh breath of air.
The example is mundane but to the point; and I very much enjoyed this article. It's a concrete example which is rare to read when it comes to using LLMs.
To the risk of being told that we "hold it wrong", it resonates with my experience of using LLMs.
by AloysB - Carson’s experience matches mine: AI is good at analysis and boilerplate, but not good at the kind of critical thinking necessary for good designs. If it were human, I would say that it jumps to solutions to quickly, rather than stepping back to consider the big picture and how everything should fit together to make a cohesive whole.
It’s not human, of course, and I think this problem actually relates to the fact that LLMs don’t have a world model. They don’t study and think through a design in the way that humans do. They don’t form a mental model of how everything fits together and how that design can be tweaked to most elegantly support a change.
I suspect that this is a fundamental limitation of LLMs, and that design will remain a weak point until some sort of bespoke design AI is bolted onto the side. In the meantime, we’ve got a lot of people producing a lot of code very quickly, and I think the debt in that code is going to be a millstone around our necks for a long time to come.
by jdlshore - It's just because not enough people had this very specific problem before.
This article will be part of the next model training set, and probably it will be able to solve it despite not understanding anything about world or not studying or thinking.
by vb-8448 - One partial mitigation is to ask it to use plan mode -- and then very carefully review the plan before allowing it to execute.by rst
- I don't think this problem is related to the fact that they don't have a world model, or because they don't form a mental model of how everything fits together, or a fundamental limitation of LLMs. These claims are often meaningless, and the boring answer is usually something like "software architecture is harder to verify than code/maths so RLing on it is harder, and it's harder writing good evals/benchmarks for it".by Zababa
- In my experience harness can do wonders to improve this.
Instead of asking it to generically to analyze and do X, you can use brainstorming skills like those from superpowers [1].
This makes it approach the problem better and keeps you in the loop.
Another step is then to have it review its plans by another LLM acting doing adversarial review. I have a claude skill [2] that calls codex to do it, and they chat among each other.
It's a tremendous boost in design quality.
[1] https://github.com/obra/Superpowers
[2] https://gist.github.com/enricopolanski/6c5038a8e20cc4098cd99...
by epolanski - Have to disagree with this as it's excellent at helping you wide and broad before converging. I suggest trying OpenSpec and use /ospx:explore to state your problem and go from there.by recroad
- I feel as though that world model strongly correlates with memory - the experience of having jumped to a conclusion early and full-steaming ahead, only to be bitten by constraints and problems later down the track.
Part of that is critical thinking and projecting forward / simulating potential issues, and part of that is that memory which in humans we probably would see as "wisdom".
I don't know if that's a fundamental limitation of LLMs, or, rather, that this can be solved moving forward with better memory systems, harnesses, and context windows.
by jacobedawson - Exactly, LLM is good at "code inpainting" : define clear structures and goals, and it will fill the boilerplate. But it doesn't work for reasoning and abstraction, so it fails to synthesise and propose novel views. But that's integral to the way it's designed and has been trained, to do a kind of "averaging" which limits it's capacity to explore novel designsby oulipo2