261–270 of 321 posts
Earlier quoted context omitted.
It's still possible to make CRUD apps in assembly with an AI agent but it would be a research project.
By "research project" you you mean by people who understand assembly? Because then we're back to where we started.
Earlier quoted context omitted.
Claude is perfectly capable of writing assembly. Here's a working (basic) Prolog interpreter that Claude Fable 5 wrote in WebAssembly in 61 minutes for $16.75 in token costs: https://github.com/emk/fable-wasm-prolog/blob/main/prolog.wa... WebAssembly is slightly easier than real assembly, but here Fable used WASM GC extensions, which are poorly documented and not yet super common. Fable didn't even need to debug it;…
I have a personal game framework that I have LLMs write games in, which is in AssemblyScript. AssemblyScript is certainly closer to TypeScript than it is to WebAssembly, but it's still this thing where the host shares some big chunk of memory with the script and you pick some memory locations to read and write as your means of exposing APIs, and there's not a lot of training data on games written in AssemblyScript an…
Earlier quoted context omitted.
I have a personal game framework that I have LLMs write games in, which is in AssemblyScript. AssemblyScript is certainly closer to TypeScript than it is to WebAssembly, but it's still this thing where the host shares some big chunk of memory with the script and you pick some memory locations to read and write as your means of exposing APIs, and there's not a lot of training data on games written in AssemblyScript an…
This is for games that run purely in the browser?
Earlier quoted context omitted.
I don't understand this. A skill critical to software engineering is learning how to learn. Just download Claude Code (or open alternative) and try to make things. See how it fails or succeeds. Look at the supported features, try them out, think about how you might use them in your workflow. Before you know it, you'll be proficient. You have to learn how to self-teach.
I agree with you - but I’m the one with an anxiety disorder here.
Doesn't have to be stressful. Plan to throw away whatever happens. Do it in a VM if your nerves demand it. No reason it can't be fun.
Earlier quoted context omitted.
Claude is perfectly capable of writing assembly. Here's a working (basic) Prolog interpreter that Claude Fable 5 wrote in WebAssembly in 61 minutes for $16.75 in token costs: https://github.com/emk/fable-wasm-prolog/blob/main/prolog.wa... WebAssembly is slightly easier than real assembly, but here Fable used WASM GC extensions, which are poorly documented and not yet super common. Fable didn't even need to debug it;…
> Fable didn't even need to debug it; I believe essentially all the assembly worked correctly on the first try. so you don't know if it works properly or not
I am honestly not happy about the way that models can now just take what should have be a fun multi-weekend project and knock out in a couple of hours. But I'm not going to pretend that Fable is stupid, or that it did a bad job on any of the test projects I gave it. It struggles more on big, messy real-world code bases, absolutely.
Earlier quoted context omitted.
I agree with you - but I’m the one with an anxiety disorder here.
Make a copy of your codebase. Go to town on it. Have fun. Doesn't have to be stressful. Plan to throw away whatever happens. Do it in a VM if your nerves demand it. No reason it can't be fun.
...so I've been avoidant of the whole thing ever since 2023, burying my head in the sand to avoid those feelings of anxiety and uncertainty-about-the-future, and it now makes it difficult for me to engage with the topic head-on.
Earlier quoted context omitted.
> Apparently it's not obvious to everyone, but if you can't write code, you can't review it. There's more to it than that: writing is thinking. If you stop writing code, you aren't thinking anymore. Many argue that they're now thinking at a higher level (maybe they weren't before?), but, guess what, that high-level design can be done better by the LLM than by you anyway. It's only temporary.
I think writing is summarizing your thoughts outside of thinking. Thinking happens at least for me before I write. I know what I want to do before I write, and writing is just one medium to get it out there. If there was a faster way, to get my thoughts there I would use that.
A lot of people observe that their thoughts get better when they do the work to write them out. It's not just a straightforward encoding process (as maybe a software engineer would conceive of it).
Earlier quoted context omitted.
Claude is perfectly capable of writing assembly. Here's a working (basic) Prolog interpreter that Claude Fable 5 wrote in WebAssembly in 61 minutes for $16.75 in token costs: https://github.com/emk/fable-wasm-prolog/blob/main/prolog.wa... WebAssembly is slightly easier than real assembly, but here Fable used WASM GC extensions, which are poorly documented and not yet super common. Fable didn't even need to debug it;…
WebAssembly has as much to do with assembly as JavaScript has with Java. I highly doubt the "slightly easier" and my attempts with LLM's and assembly so far were largely disappointing, but I also think there is no compelling reason this has to be the case.
But it's not that much simpler. And once you add the WASM GC stuff, WebAssembly gets weird. It's a Harvard architecture with separate value memory, linear memory, GC memory and "tables", all accessible in completely different ways, with a weird mandatory type system (especially for the GC stuff). And the docs are often terrible. And yes, I've also written WebAssembly by hand.
So yes, I would, overall, classify WebAssembly as "slightly easier". But not dramatically so. And the training data for actually writing non-trivial things by hand isn't that great, not compared to something like Intel assembly.
(Don't talk to me about TI320C40 assembly. If Fable can one-shot a Prolog interpreter written using that without finding a reference manual, it's time to hang up my hat and learn to make goat cheese.)
Earlier quoted context omitted.
> I'm probably behind on using AI and need to get more up to speed Same. My difficulty is that for the past 8 years I've been working for (tiiiiny) SaaS business where I don't have anyone I can simply ask in-person "hey, can you show me how to 'do' all this newfangled AI agentic team coding?"; so my only direct-exposure is with the painful Copilot sidebar chat, which I now find myself allergic to. So let's see elsewh…
Burke Holland has a few good videos that helped me. For example this on agents[1]. He uses Copilot but the principles are similar for Claude Code, Codex, OpenCode and other harnesses: So far in the LLM coding revolution I still feel like it's software development. I just work with systems on the level of features and architecture instead of flow control statements. Some day we might lose that too, but I think it will…
That's kinda at the level I enjoy though - where I get to think-through things when figuring out exhaustiveness and correctness; introducing refinement-types into a codebase that's previously nothing but ints-and-strings; and trying out new and cutting-edge language-features directly.
I know I can prompt Claude etc into trying to do those things, but from what I've seen from other people doing it the result is somewhat of a mess - or just plain inelegant.
-----
May I ask how well Claude/Copilot/etc works with FP languages instead? So far - and back in early 2024 - I've only messed-around with asking ChatGPT to generate Haskell programs and the results were hallucinated gibberish.
Every time you work in a complex software project, you have all the context in your head about what you must take into consideration. LLMs don’t, you have to explain every little detail to them, but there’s no telling where it stops: do you have to explain X to it or is it in the training already?
When you try to shape how a LLM should behave and what it should know, you end up writing a Bible of relevant context that’s increasingly difficult to maintain as well, often with outdated or contradictory information, and it is still free to ignore things you have written and proceed however it wants.
That’s why so many people only feel comfortable giving the LLM some limited task to do, because you can judge if that specific task needs just enough context that it can handle by itself.