I read all of Cloudflare's Claude-generated commits • Hacker News Board

Re: I read all of Cloudflare's Claude-generated commits

#11

Post by rectang » Sat, Jun 07, 2025, 1:59 AM UTC

SrslyJosh wrote: post #5

> 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.

Re: I read all of Cloudflare's Claude-generated commits

#12

Post by deadbabe » Sat, Jun 07, 2025, 2:01 AM UTC

Dylan16807 wrote: post #6

SupremumLimit wrote: post #4

It's an interesting review but I really dislike this type of techno-utopian determinism: "When models inevitably improve..." Says who? How is it inevitable? What if they've actually reached their limits by now?

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.

5 years ago a person would be blown away by today’s LLMs. But people today will merely say “cool” at whatever LLMs are in use 5 years from now. Or maybe not even that.

Re: I read all of Cloudflare's Claude-generated commits

#13

Post by dingnuts » Sat, Jun 07, 2025, 2:07 AM UTC

deadbabe wrote: post #12

Dylan16807 wrote: post #6

Earlier 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.

5 years ago a person would be blown away by today’s LLMs. But people today will merely say “cool” at whatever LLMs are in use 5 years from now. Or maybe not even that.

5 years ago GPT2 was already outputting largely coherent speech, there's been progress but it's not all that shocking

Re: I read all of Cloudflare's Claude-generated commits

#14

Post by js2 » Sat, Jun 07, 2025, 2:10 AM UTC

Discussion from 4 days ago when the code was announced (846 points, 519 comments):

https://news.ycombinator.com/item?id=44159166

Re: I read all of Cloudflare's Claude-generated commits

#15

Post by roywiggins » Sat, Jun 07, 2025, 2:21 AM UTC

minimaxir wrote: post #9

Sevii wrote: post #7

Earlier quoted context omitted.

There are lots of reasons not to do it. But if LLMs get good enough that it works consistently people will do it anyway.

What will people call it when coders rely on vibes even more than vibe coding?

Haruspicy?

Re: I read all of Cloudflare's Claude-generated commits

#16

Post by viraptor » Sat, Jun 07, 2025, 2:33 AM UTC

The documentation angle is really good. I've noticed it with the mdc files and llm.txt semi-standard. Documentation is often treated as just extra cost and a chore. Now, good description of the project structure and good examples suddenly becomes something devs want ahead of time. Even if the reason is not perfect, I appreciate this shift we'll all benefit from.

Re: I read all of Cloudflare's Claude-generated commits

#17

Post by brookst » Sat, Jun 07, 2025, 2:45 AM UTC

minimaxir wrote: post #9

Sevii wrote: post #7

Earlier quoted context omitted.

There are lots of reasons not to do it. But if LLMs get good enough that it works consistently people will do it anyway.

What will people call it when coders rely on vibes even more than vibe coding?

Writing specs

Re: I read all of Cloudflare's Claude-generated commits

#18

Post by IncreasePosts » Sat, Jun 07, 2025, 2:46 AM UTC

I asked this in the other thread (no response, but I was a bit late)

How does anyone using AI like this have confidence that they aren't unintentionally plagiarizing code and violating the terms of whatever license it was released under?

For random personal projects I don't see it mattering that much. But if a large corp is releasing code like this, one would hope they've done some due diligence that they have to just stolen the code from some similar repo on GitHub, laundered through a LLM.

The only section in the readme doesn't mention checking similar projects or libraries for common code:

> Every line was thoroughly reviewed and cross-referenced with relevant RFCs, by security experts with previous experience with those RFCs.

Re: I read all of Cloudflare's Claude-generated commits

#19

Post by sitkack » Sat, Jun 07, 2025, 2:51 AM UTC

Dylan16807 wrote: post #6

SupremumLimit wrote: post #4

It's an interesting review but I really dislike this type of techno-utopian determinism: "When models inevitably improve..." Says who? How is it inevitable? What if they've actually reached their limits by now?

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.

Re: I read all of Cloudflare's Claude-generated commits

#20

Post by drodgers » Sat, Jun 07, 2025, 2:52 AM UTC

> Prompts as Source Code

Another way to phrase this is LLM-as-compiler and Python (or whatever) as an intermediate compiler artefact.

Finally, a true 6th generation programming language!

I've considered building a toy of this with really aggressive modularisation of the output code (eg. python) and a query-based caching system so that each module of code output only changes when the relevant part of the prompt or upsteam modules change (the generated code would be committed to source control like a lockfile).

I think that (+ some sort of WASM encapsulated execution environment) would one of the best ways to write one off things like scripts which don't need to incrementally get better and more robust over time in the way that ordinary code does.