The idea that a 835-page spec "just exists" and we run an LLM to implement it is completely flawed. Specs do not appear out of nowhere, they co-evolve with the code. If you have the code, why do you want to generate it again?

Good software is made as a product of numerous feedback loops and LLMs let you operate those loops faster. They do not supplement the entire process though.

In the end, a good product is a barrel of distilled feedback.

1) The construction of the Empire State Building was particularly effective due to the depth of human-to-human collaboration.

2) Isn't it great that we can burn a bunch of dinosaur blood to convince ourselves that we don't need other humans?

And I don't really think this is true. Compilers are usually deterministic, and whilst we can find edge cases, it's nothing like an AI agent writing all the code for you.

I think you have two choices, given the Claude is a code generator and not a compiler: (a) you review most or all of code to make sure it makes sense, or (b) you trust but verify via a strong test suite, potentially also created by Claude.

The problem with (a) is that you lose a lot of the speed-up. The problem with (b) is that you have no human oversight and the code may be incomplete, badly designed, or plain wrong.

Currently we review all code because correctness is extremely important to what we do, but that comes at a cost.

I don't know what the answer is here, in general. Does trust build over time? Do the models just get so good we can trust them to make zero mistakes?

AI exists at the boundary of codification. When you understand something well enough to express it in a deterministic way, it is no longer worthwhile to keep asking AI for that thing over and over - you should codify it.

But wait, I hear you say? AI has knowledge! And we can rely on that knowledge and sprinkle on top some brief instructions and it'll get things right and work out the details itself!

That is spec driven development.

And this is great one single time. Except, knowledge shifts. You are outsourcing part of what you've codified to society as a whole, in the form of language model knowledge. You're also trusting current and future models to always produce something that meets the requirements, and never be quantized under you, and produce the same result next time despite being a probabilistic system with no memory, and and and.

Better to freeze everything in place in your codebase so you get predictable results - in other words, codify it! Let's store the desired state of that button in code in a very complicated thing that's existed for decades called a string, so it always says "Finish" and never says "Done" - even if we regenerate the app.

That's pretty unexciting and doesn't justify tens of billions of investment. Which means you won't hear it from anyone with tokens to sell. But it's what you have to do to make something people want.

The workflow I imagine is either deriving specs from the conversation or reverse engineering the code to spec, review and edit the spec which should be tighter and much more compressed, then deterministically compile to code. Of course we don't want to be spec-first only, that would be going back waterfall, but doing iterations back and forth.

Now, Claude is not a compiler because it is closed and non-deterministic (they do opaque processing on server, hiding reasoning tokens), but LLMs might be. We refer to a piece of code from npm/pip by name to get some code by downloading it. We then have lockfiles with hashes to ensure integrity. Currently we are vibing it, but in the future we could refer to a piece of code by prompt/spec and getting the code by inferring it. To ensure integrity, the lockfile would be hashes of open weights and inference code (and ironing out implementation details like non-determinism due to GPU scheduling, etc.).

> I’d say that, in all the ways that matter, I understand the code.

I think the dissonance here is really important, and not a bad thing at all. A lot of the decision _were_ handed off the the AI, but they weren't the decisions the author cared about. This is a big selling point of AI! If something is doable with a computer, it’ll figure it out. 30 minutes and 200m tokens later, it’ll take any idea and declare “the feature is fully implemented.”

The hard part is figuring out where to inject that friction, so you can see where it's making decisions for you that matter. The author approached this by incrementally building the thing, reviewing and poking and prodding at every step. A week of attention following a bunch of design discussions is fast, but that's still not trivially cheap.

I want to see us talk more about the decision exhaust of agents, because the better the models get, the more decisions we'll want them to make.

I wrote a bit more here: https://tern.sh/blog/compiler-never-says-no/

This sentiment kind of saddens me. I'm all for burning tokens to write throwaway code just to prototype a solution, but I don't get not reading (or at least familiarizing yourself with) the code that you will deploy to prod.

To my (limited) understanding, this is not a good idea, and is an unfixable problem from the server side. Companies, VPNs or ISPs or routers, often use their own DNS servers, and those can have caching logic, which means it doesn't matter how fast your own DNS implementation is, as the users lookup request wont hit your DNS server, it'll hit an intermediate cache.

Tools like Claude are great at building algorithms, then tests to verify them. The algorithms they build aren't just compilers, but any software that can be verified. Even though Claude may not be a compiler, it has the potential to (at least if it improves) create production-grade software that can be verified, like other compilers. But maybe not good UX without human input (expanded to any subjective experience, like video games).

* Not a "source language to target language" deductive algorithm. Technically Claude is an algorithm to predict the next token, but acting as a compiler or anything else it's an inductive heuristic, because it guesses (https://stackoverflow.com/q/2334225)

Anyone using claude can see it misses steps that an engineer wouldnt, it can make bad choices that a sysadmin wouldnt, it can pick the wrong order a project manager wouldnt, it can pick wrong cost models that a bean counter wouldnt, etc etc etc

But, I'm pretending it is and living with those mistakes.

There are lots of places in computer science that determinism isn't necessarily the best.

- UDP video calls let packets vanish or arrive corrupted, because waiting for retransmissions would freeze the picture.

- Stochastic gradient descent picks a random mini-batch of training data and treats it as the whole dataset, because computing the true gradient on every step would make training infeasible.

- Speculative execution in modern CPUs guesses which branch a program will take and rolls back when wrong, because waiting for the real answer would leave half the silicon idle.

What we want is something like a Las Vegas algorithm, a probabilistic machine with a cheap verifier.

[0] https://en.wikipedia.org/wiki/Probabilistic_Turing_machine

Famous last words, but point is taken.

The non deterministic nature of an llm breaks the metaphor that they are like a compiler.

However, it’s not foreign to compilers to receive feedback from the running program (PGOs), so there are still parallels to the feedback we provide LLMs that guide their “optimization”.

I think even calling LLMs a non-deterministic compiler isn’t accurate either so ultimately I agree the metaphor doesn’t quite work.

I do think LLMs are like compilers in terms of how they changed how we build programs from a historical context. But that’s about it.

> But our VMs start fast, so fast that even if we created the DNS entries before creating the VM, our users still had to sit around waiting for DNS to propagate, which occasionally took minutes, not seconds.

> We did the obvious thing: We wrote our own DNS server, so that DNS always immediately matched the source of truth. And life was good.

> But latency matters, so we added regions. And just like that, DNS became the long pole again, because all DNS was served out of Oregon. Also, deployments caused tiny DNS outages. To fix this, all we needed now was a geographically distributed but fully consistent DNS server.

> We did what a sensible engineer does when faced with a hard problem: cheat. We vibe-engineered a distributed DNS server tuned to our specific needs.

I'm sure they have already considered this, but what problem does this solve that couldn't be solved by using dnsmasq, unbound or something like that? Why reinvent the wheel?

A compiler does a lot more than source code translation.

There are specifications that tell us the de jure specifications of the language, if there is one, and then we have to recognize the de facto implementations of said language. The often disagree and leave much on the table. Some times on purpose, such as implementation details, and other times by omission.

Users of this compiler expect a deterministic compilation of the source text into the target code but it’s rarely 1:1. There are optimization passes, inlining, barriers, etc.

And then there are the run-time effects of executing a program!

I think the analogy gets a little weak because natural language is not a precise enough language to specify discrete systems.

What it sounds like the author is doing is bypassing decision points with other people and delaying making decisions themselves until the LLM agent forces them to? Which is a fine approach but I don’t think the analogy with a compiler is necessary.

People seem to have a hard enough time understanding branch prediction and thread barriers.

In my view, reasoning LLMs have learned a large number of close to true sentences of "logic" in natural language. These rules are not consistent (unlike typing rules of LH that allow creation of provably correct programs), but they work in practice better than LH. Essentially, they represent an unsound formal specification of natural language, together with many useful (almost)tautologies that helps solving constraint problems (just like LH does, but again unlike LLM, provably correctly).

LLMs proved that human language can be formalized reasonably close to soundness. I believe we can have a sound formalization of human language, and that kind of formal language will be once superior to LLMs.

It will also not be as complicated as LLMs and require only fraction of compute to use.

Waterfall is dead, long live waterfall!

It even has just-in-time compilation: it can directly follow a spec and generate small snippets live.

I'm pretty sure we'll soon see services (admittedly highly inefficient) built on Claude-as-a-backend.

If there's a serious learning curve to editing code then you don't understand the code. We used to call that 'on-boarding' when you brought a new engineer on the team as they got up to speed as to how the codebase worked.

So I made a distributed service for your distributed name service so you can distribute your names to the service that distributes them on the onternet