I was thinking that if you had a good enough verified mathematical model of your code using TLA+ or similar you could then use an LLM to generate your code in any language and be confident it is correct. This would be Declarative Programming. Instead of putting in a lot of work writing code that MIGHT do what you intend you put more work into creating the verified model and then the LLM generates code that will do what the model intends.
I read all of Cloudflare's Claude-generated commits
101–110 of 291 posts
Re: I read all of Cloudflare's Claude-generated commits
#102Earlier quoted context omitted.
Models are improving every day. People are figuring out thousands of different optimizations to training and to hardware efficiency. The idea that right now in early June 2025 is when improvement stops beggars belief. We might be approaching a limit, but that's going to be a sigmoid curve, not a sudden halt in advancement.
It is copium that it will suddenly stop and the world they knew before will return. ChatGPT came out in Nov 2022. Attention Was All There Was in 2017, we were already 5 years in the past. Or 5 years of research to catch up to, and then from 2022 to now ... papers and research have been increasing exponentially. Even in if SOTA models were frozen, we still have years of research to apply and optimize in various ways.
The copium is I think many people got comfortable post financial crisis with nothing much changing or happening. I think many people really liked a decade stretch with not much more than web framework updates and smart phone versioning.
We are just back on track.
I just read Oracular Programming: A Modular Foundation for Building LLM-Enabled Software the other day.
We don't even have a new paradigm yet. I would be shocked that in 10 years I don't look back at this time of writing a prompt into a chatbot and then pasting the code into an IDE as completely comical.
The most shocking thing to me is we are right back on track to what I would have expected in 2000 for 2025. In 2019 those expectations seemed like science fiction delusions after nothing happening for so long.
Re: I read all of Cloudflare's Claude-generated commits
#103> Treat prompts as version-controlled assets
This only works if the model and its context are immutable. None of us really control the models we use, so I'd be sceptical about reproducing the artifacts later.
Re: I read all of Cloudflare's Claude-generated commits
#104Earlier quoted context omitted.
Linting isn't verification of correctness, and yes, you can fool the compiler, linters, etc. Work with some human interns, they are great at it. Agents will do crazy things to get around linting errors, including removing functionality.
have you no tests?
Irrelevant, really. Tests establish a minimum threshold of acceptability, they don't (and can't) guarantee anything like overall correctness.
Re: I read all of Cloudflare's Claude-generated commits
#105> Reading through these commits sparked an idea: what if we treated prompts as the actual source code? Imagine version control systems where you commit the prompts used to generate features rather than the resulting implementation. Please god, no, never do this. For one thing, why would you not commit the generated source code when storage is essentially free? That seems insane for multiple reasons. > When models ine…
>> what if we treated prompts as the actual source code? You would not do this because: unlike programming languages, natural languages are ambiguous and thus inadequate to fully specify software.
Exactly!
> this assumes models can achieve strict prompt adherence
What does strict adherence to an ambiguous prompt even mean? It’s like those people asking Babbage if his machine would give the right answer when given the wrong figures. I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a proposition.
Re: I read all of Cloudflare's Claude-generated commits
#106If/when to commit prompts has been fascinating as we have been doing similarly to build Louie.ai. I now have several categories with different handling:
- Human reviewed: Code guidelines and prompt templates are essentially dev tool infra-as-code and need review
- Discarded: Individual prompt commands I write, and implementation plan progress files the AI write, both get trashed, and are even part of my .gitignore . They were kept by Cloudflare, but we don't keep these.
- Unreviewed: Claude Code does not do RAG in the usual sense, so it is on us to create guides for how we do things like use big frameworks. They are basically indexes for speeding up AI with less grepping + hallucinating across memory compactions. The AI reads and writes these, and we largely stay out of it.
There are weird cases I am still trying to figure out. Ex:
- feature impl might start with an AI coming up with the product spec, so having that maintained as the AI progresses and committed in is a potentially useful artifact
- how prompt templates get used is helpful for their automated maintenance.
Re: I read all of Cloudflare's Claude-generated commits
#107Earlier quoted context omitted.
Also: " This OAuth library represents something larger than a technical milestone—it's evidence of a new creative dynamic emerging " Em-dash baby.
Can we please stop using the em-dash as a metric to “detect” LLM writing? It’s lazy and wrong. Plenty of people use em-dashes, it’s a useful punctuation mark . If humans didn’t use them, they wouldn’t be in the LLM training data. There are better clues, like the kind of vague pretentious babble bad marketers use to make their products and ideas seem more profound than they are. It’s a type of bad writing which looks…
Very few people use n dashes in internet writing as opposed to dashes as they are not available on the default keyboard.
Re: I read all of Cloudflare's Claude-generated commits
#108> Reading through these commits sparked an idea: what if we treated prompts as the actual source code? Imagine version control systems where you commit the prompts used to generate features rather than the resulting implementation. Please god, no, never do this. For one thing, why would you not commit the generated source code when storage is essentially free? That seems insane for multiple reasons. > When models ine…
I'd say commit a comprehensive testing system with the prompts.
Prompts are in a sense what higher level programming languages were to assembly. Sure there is a crucial difference which is reproducibility. I could try and write down my thoughts why I think in the long run it won't be so problematic. I could be wrong of course.
I run https://pollinations.ai which servers over 4 million monthly active users quite reliably. It is mostly coded with AI. Since about a year there was no significant human commit. You can check the codebase. It's messy but not more messy than my codebases were pre-LLMs.
I think prompts + tests in code will be the medium-term solution. Humans will be spending more time testing different architecture ideas and be involved in reviewing and larger changes that involve significant changes to the tests.
Re: I read all of Cloudflare's Claude-generated commits
#109> Reading through these commits sparked an idea: what if we treated prompts as the actual source code? Imagine version control systems where you commit the prompts used to generate features rather than the resulting implementation. Please god, no, never do this. For one thing, why would you not commit the generated source code when storage is essentially free? That seems insane for multiple reasons. > When models ine…
I think the author is saying you commit the prompt with the resulting code. You said it yourself, storage is free, so comment the prompt along with the output (don’t comment that out that if I’m not being clear); it would show the developers(?) intent, and to some degree, almost always contribute to the documentation process.
Re: I read all of Cloudflare's Claude-generated commits
#110Earlier quoted context omitted.
> One of the things we learned very quickly was that having generated source code in the same repository as actual source code was not sustainable. Keeping a repository with the prompts, or other commands separate is fine, but not committing the generated code at all I find questionable at best.
I feel like using a compiler is in a sense a code generator where you don't commit the actual output
> I feel like using a compiler is in a sense a code generator where you don't commit the actual output
Compilers are deterministic. Given the same input you always get the same output so there's no reason to store the output. If you don't get the same output we call it a compiler bug!
LLMs do not work this way.
(Aside: Am I the only one who feels that the entire AI industry is predicated on replacing only development positions? we're looking at, what, 100bn invested, with almost no reduce in customer's operating costs other than if the customer has developers).