Notes on rolling out Cursor and Claude Code
182 points
21 hours ago
| 18 comments
| ghiculescu.substack.com
| HN
aerhardt
19 hours ago
[-]
> So far the biggest limiting factor is remembering to use it. Even people I consider power users (based on their Claude token usage) agree with the sentiment that sometimes you just forget to ask Claude to do a task for you, and end up doing it manually. Sometimes you only notice that Claude could have done it, once you are finished. This happens to me an embarrassing amount.

Yea, this happens to me too. Does it say something about the tool?

It's not like we are talking about luddites who refuse to adopt the technology, but rather a group who is very open to use it. And yet sometimes, we "forget".

I very rarely regret forgetting. I feel a combination of (a) it's good practice, I don't want my skills to wither and (b) I don't think the AI would've been that much faster, considering the cost of thinking the prompt and that I was probably in flow.

reply
emeraldd
17 hours ago
[-]
If you're forgetting to use the tool, is the tool really providing benefit in that case? I mean, if a tool truly made something easier or faster that was onerous to accomplish, you should be much less likely to forget there's a better way ...
reply
skydhash
17 hours ago
[-]
Yep! Most tools are there to handle the painful aspects of your tasks. It's not like you are consciously thinking about them, but just the fact on doing them without the tool will get a groan out of you.

A lot of current AI tools are toys. Fun to play around, but as soon as you have some real world tasks, you just do it your usual way that get the job done.

reply
jaapbadlands
17 hours ago
[-]
There's a balance to be calculated each time you're presented with the option. It's difficult to predict how much iteration the agent is going to require, how frustrating it might end up being, all the while you lose grip on the code being your own and your head-model of it, vs just going in and doing it and knowing exactly what's going on and simply asking it questions if any unknowns arise. Sometimes it's easier to just not even make the decision, so you disregard firing up the agent in a blink.
reply
nu11ptr
13 hours ago
[-]
> is the tool really providing benefit in that case?

Yes, much of the time and esp. for tests. I've been writing code for 35 years. It takes a while to break old habits!

reply
acedTrex
11 hours ago
[-]
Why would you want to break the habit? If you are not feeling a strong urge to use it...
reply
viraptor
13 hours ago
[-]
Our meat blobs forget things all the time. It's why the Todo apps and reminders even exist. Not using something every time doesn't mean it's not beneficial.
reply
dimitri-vs
15 hours ago
[-]
You never forgot your reusable grocery bag, umbrella, or sun glasses? You've never reassembled something and found a few "extra" screws?
reply
dgunay
15 hours ago
[-]
Many CLI tools that I love using now took some deliberate practice to establish a habit of using them.
reply
ghiculescu
13 hours ago
[-]
I resonate with your case (b). One reason why I intentionally don't use it is cases where I know exactly what code I want to write, and can thus write it quicker than I can explain it to Claude + have Claude write it.
reply
Trasmatta
16 hours ago
[-]
I really really hate this idea that you should have AI do anything it can do, and that there's no value in doing it manually.
reply
ErikBjare
7 hours ago
[-]
The value is in doing the thing, how it's done is just a matter of preference and efficiency.
reply
Trasmatta
33 minutes ago
[-]
This is a myopic and dehumanizing way to look at it.
reply
varispeed
17 hours ago
[-]
Some tasks are faster than cognitive load to create a prompt and then wait for execution.

Also if you like doing certain tasks, then it is like eating an ice cream vs telling someone to eat an ice cream.

reply
PetahNZ
16 hours ago
[-]
And the waiting is somewhat frustrating, what am I supposed to do while I wait? I could just sit and watch, or context switch to another task then forget the details on what I was originally doing.
reply
johnisgood
14 hours ago
[-]
I typically just think of more ideas, prompts, etc. while I wait.
reply
what
15 hours ago
[-]
I think you’re supposed to spin up another to do a different task. Then you’ll be occupied checking up on all of them, checking their output and prodding them along. At least that’s what Anthropic said you should do with Claude Code.
reply
dontlikeyoueith
14 hours ago
[-]
If I wanted to be an EM, I'd apply for that job.
reply
mikedelfino
15 hours ago
[-]
The thing is others will eat ice cream faster so very soon there'll be no ice cream for me.
reply
NitpickLawyer
19 hours ago
[-]
> The most common thing that makes agentic code ugly is the overuse of comments.

I've seen this complaint a lot, and I honestly don't get it. I have a feeling it helps LLMs write better code. And removing comments can be done in the reading pass, somewhat forcing you to go through the code line by line and "accept" the code that way. In the grand scheme of things, if this were the only downside to using LLM-based coding agents, I think we've come a long way.

reply
robben1234
11 hours ago
[-]
I work with python codebases and consider comments that answer "what?" instead of "why?" bad.

LLMs tend to write comments answering "what?", sometimes to a silly extent. What I found helping for using Claude 3.7 was to add this rule in cursor. The fake xml tag helped to decrease the number of times it strays from my instructions.

<mandatory_code_instruction>

YOU ARE FORBIDDEN FROM ADDING ANY COMMENTS OR DOCSTRINGS. The only code accepted will be self-documenting code.

</mandatory_code_instruction>

If there's a section of code where a comment answering "why?" is needed this rule doesn't seem to interfere when I explicitly ask it to add it there.

reply
meander_water
16 hours ago
[-]
I've noticed Gemini 2.5 pro does this a lot in Cursor. I'm not sure if it's because it doesn't work well with the system prompt or tools, but it's very annoying. There are comments for nearly every line and it's like it's thinking out loud in comments with lots of TODOS and placeholders.
reply
felipeerias
11 hours ago
[-]
That is because it is thinking out loud. Producing tokens is how it thinks.
reply
eschaton
10 hours ago
[-]
Producing tokens is all it does, it’s not thinking.
reply
NitpickLawyer
9 hours ago
[-]
Eh, you really have to take the "thinking" in quotes, in the LLM context "thinking" out loud is what makes the results better. I think (hah) their point stands.
reply
duxup
14 hours ago
[-]
I agree. I don’t always keep the comments, but I’m 100% ok with them.
reply
ellieh
17 hours ago
[-]
You can literally just ask it to not write too many comments, describe the kind of comments you want, and give a couple of examples. Save that in rules or whatever. And it's solved for the future :)
reply
dockercompost
16 hours ago
[-]
I tell them to write self-documenting code and to only leave comments when its essential for understanding, and that's worked out pretty well
reply
what
15 hours ago
[-]
They tend to add really bad comments though. I was looking at an LLM generated codebase recently and the comments are along the lines of “use our newly created Foo model”, which is pretty useless.
reply
manojlds
17 hours ago
[-]
Yeah that's what I do, remove the comments as I read through.
reply
beefnugs
7 hours ago
[-]
If it helps... shouldn't you be "not deleting them" for future feature additions?
reply
rossant
15 hours ago
[-]
I'm still having a hard time with coding agents. They are useful but also somehow immature hence dangerous. The other day I asked copilot with GPT4o to add docstrings to my functions in a long Python file. It did a good job on the first half. But when I looked carefully, I realized the second half of my file was gone. Just like that. Half of my file had been silently deleted, replaced by a single terrifying comment along the lines of "continue similarly with the rest of the file". I use Git of course so I could recover my deleted code. But I feel I still can't fully trust an AI assistant that will silently delete hundreds of lines of my codebase just because it is too lazy or something.
reply
duxup
14 hours ago
[-]
I’ve also seen catastrophic failures where the code returned completely fails for numerous “obvious” problems, including but not limited to missing code.

I tend to have to limit the code I share and ask more pointed / targeted questions in order to lead the AI to a non catastrophic result.

reply
asadm
15 hours ago
[-]
these models have hard time modifying LARGE files and then returning them back to you. That's inefficient too.

What you want is to ask for list of changes and then apply them. That's what aider, codex, etc. all do.

I made a tool to apply human-readable changes back to files, which you might find useful: https://github.com/asadm/vibemode

aider has this feature too.

reply
weird-eye-issue
15 hours ago
[-]
Your first mistake was using Copilot. Your second mistake was using GPT 4o
reply
asdev
12 hours ago
[-]
>Our head of product is a reformed lawyer who taught himself to code while working here. He’s shipped 150 PRs in the last 12 months.

>The product manager he sits next to has shipped 130 PRs in the last 12 months.

In a serious organization, non technical people should not be shipping any sort of code. They should be doing the highest leverage things possible to help the business, and if that seems to be coding, there are grave issues in the company.

reply
n_ary
7 hours ago
[-]
I see a fraudulent benefit in this case. When these non-tech people go into public talks or anything, they can suddenly claim “oh, I use AI to write 80% of my code” and voila! No one will ask whether their responsibility is to write code or do any engineering, simply being able to give some surface level claims makes them credible enough and feed the hype while appearing cool.

It also gives investors more confidence to shower them with money when needed, as non-tech people are also doing AI coding and they are super agile!

When Msft CEO claims that 80% code written by AI, there is a 50% doubt, but when someone adds that, yeah so I have done 150 PRs, now it feels more concrete and real.

reply
ghiculescu
6 hours ago
[-]
Author here. We don't have (or want) any investors. I encourage PMs to code because it's good for the business. Otherwise I wouldn't do it.

I wrote about this years before we started doing AI-backed-coding: https://ghiculescu.substack.com/p/opening-the-codebase-up-to..., so some of the details are no longer correct, but the philosophy is the same.

reply
CraigJPerry
6 hours ago
[-]
>> In a serious organization, non technical people should not be shipping any sort of code

Just as you want developers building domain knowledge for all the benefits it brings, you want a role like product owner to be developing their understanding of delivering software.

Sometimes the highest leverage thing to be done is making teams of people work better together. One aspect of achieving that can be better understanding of what each role does.

reply
ghiculescu
12 hours ago
[-]
How do credibly define "non technical people" when everyone's code is written by an LLM?

Serious organisations sound awful.

reply
asdev
11 hours ago
[-]
non technical people are people who are not hired for an engineering role
reply
wheelerwj
11 hours ago
[-]
This sounds like a disaster waiting to happen
reply
teekert
16 hours ago
[-]
I have a confession. I don’t really get what Claude Code is… It’s not a model, it’s not an editor with AI integrated… So what is it? It bugs me on the website, I click on it, read, still don’t get it.

I have a Claude console account, if you can call it that? It always takes me 3 times to get the correct email address because it does not work with passkeys or anything that lets me store credentials. I just added the api key to OpenWebUI. It’s nice and cheaper than a subscription for me even though I use it all day.

But I’m still confused. I just now clicked on “build with Claude”, it takes me to that page where I put in the wrong email address 3 times. And then you can buy credits.

reply
bognition
16 hours ago
[-]
Have you installed the Claude cli tool?

Think of it as an LLM that automagically pulls in context from your working directory and can directly make changes to files.

So rather than pasting code and a prompt into ChatGPT and then copy and pasting the results back into your editor, you tell Claude what you want and it does it for you.

It’s a convenient, powerful, and expensive wrapper

reply
srvmshr
12 hours ago
[-]
Not the OP but in a similar boat. Curious to understand how do you make sure that Claude code cli tool does not break existing code functionality?

My hesitation to adopt stems from the events where Claude.ai WebUI ignorantly breaks the code, but since I can visibly verify it - I iterate it until it seems reasonable syntactically & logically, and then paste it back.

With the autonomous changing of the code lines, I'm slightly nervous it would/could break too many parts concurrently -- hence my hesitation to use it. Any best practices would be insightful

reply
theonething
11 hours ago
[-]
By default, it shows you a diff of what it plans to do and ask you for permission before making the change.
reply
adastra22
11 hours ago
[-]
So it's like Cursor/Windsurf, minus the GUI?
reply
mdrachuk
15 hours ago
[-]
> You can see this in practice when you use Claude Code, which is pay-per-token. Our heaviest users are using $50/month of tokens. That’s a lot of tokens.

How is your usage so low! Every time i do anything with claude code i spend couple of bucks, for a day of coding it's about $20. Is there a way to save on tokens on a mid-sized Python project or people are just using it less?

reply
gen220
15 hours ago
[-]
It's because by default it'll try to solve most problems agentically / by "thinking", even if your prompt is fairly prescriptive.

I use aider.chat with Claude 3.5 haiku / 3.7 sonnet, cram the context window, and my typical day is under $5.

One thing that can help for lengthy conversations is caching your prompts (which aider supports, but I'm sure Claude Code does, too?)

Obviously, Anthropic has an incentive to get people to use more tokens (i.e. by encouraging you to use tokens on "thinking"). It's one reason to prefer a vendor-neutral solution like aider.

reply
jdance
8 hours ago
[-]
This is my experience too, I can burn $20 on a big refactoring in a few hours no problem

A lot of the time (when it works) I think its easily worth the money, but I would quickly break their $100 a month budget

reply
bn-l
12 hours ago
[-]
How though? Are you putting a massive code base into context each time?
reply
joshuanapoli
3 hours ago
[-]
With Aider, you typically select only that part of the codebase that you want to work on. You can do this manually, or let the agent find files itself. It tends to break down if you need more than 20 files or so in the context.
reply
itoprocess
9 hours ago
[-]
Yeah, I think you need to do task in more discrete chunks, so you aren't' sending so many tokens each request by the end.
reply
ghiculescu
13 hours ago
[-]
That seems really high to me. Maybe you write a lot more code than anyone else around. How big is the codebase? I have a feeling that (+ the stack) has a big impact.
reply
ollien
17 hours ago
[-]
> The product manager he sits next to has shipped 130 PRs in the last 12 months. When we look for easy wins and small tasks for new starters, it’s harder now, because he’s always got an agent chewing through those in the background.

I'd be curious to hear more about this, whether from the author or from someone who does something similar. When the author says "background", does that literally mean JIRA tickets are being assigned to the agent, and it's spitting back full PRs? Is this setup practical?

reply
ghiculescu
6 hours ago
[-]
No, not so literally. I just meant that whenever a small throwaway task comes across his desk, he does it instead of making a ticket. Lots of "small tweak" PRs.

(Also, your life will get better when you delete Jira!)

reply
SafeDusk
12 hours ago
[-]
Changing my old coding behavior aside, biggest limiting factor for me is understanding how and why the coding agent is doing this a certain way, so that I have the confidence to continually sharpen my tools.

I want something simple that I have full control on, if not just to understand how they work. So I made a minimal coding agent (with edit capability) that is fully functional using only seven tools: read, write, diff, browse, command, ask, and think.

As an example, I can just disable `ask` tool to have it easily go full autonomous on certain tasks. Or, ask it to `think` for refactoring.

Have a look at https://github.com/aperoc/toolkami to see if it might be useful for you.

reply
eschaton
10 hours ago
[-]
It’s producing statically likely next tokens based on its training corpus and prompts. That’s what it’s doing. It’s not analyzing your code, it’s not considering approaches, it’s not theorizing about behavior, it’s just producing statistically likely tokens.

This is why I don’t touch the shit—it’s fucking snake oil.

reply
datadrivenangel
19 hours ago
[-]
"Making it easy to run tests with a single command. We used to do development & run tests via docker over ssh. It was a good idea at the time. But fixing a few things so that we could run tests locally meant we could ask the agent to run (and fix!) tests after writing code."

Good devops practices make AI coding easier!

reply
skydhash
17 hours ago
[-]
> Good devops practices make AI coding easier!

Good devops practices make coding easier!

reply
tptacek
18 hours ago
[-]
This is one of the most exciting things about coding agents: they make a lot of tooling that was so tedious to use it was impractical now ultra relevant. I wrote a short post about this a few weeks ago, the idea that things like "Semgrep" are now super valuable where they were kind of marginal before agents.
reply
kasey_junk
18 hours ago
[-]
And also the payoff for “minor” improvements to be bigger.

We’ve started more aggressively linting our code because a) it makes the ai better and b) we made the ai do the tedious work of fixing our existing lint violations.

reply
jaredsohn
17 hours ago
[-]
It can automate a lot of the tediousness for static typing, too
reply
viraptor
13 hours ago
[-]
The fact that you have to describe things in text suddenly made a few companies also publish API documentation as llm.txt and the content is what I wish they published for people instead.
reply
hallh
18 hours ago
[-]
Having linting/prettifying and fast test runs in Cursor is absolutely necessary. On a new-ish React Typescript project, all the frontier models insist on using outdated React patterns which consistently need to be corrected after every generation.

Now I only wish for an Product Manager model that can render the code and provide feedback on the UI issues. Using Cursor and Gemini, we were able to get a impressively polished UI, but it needed a lot of guidance.

> I haven’t yet come across an agent that can write beautiful code.

Yes, the AI don't mind hundreds of lines of if statements, as long as it works it's happy. It's another thing that needs several rounds of feedback and adjustments to make it human-friendly. I guess you could argue that human-friendly code is soon a thing of the past, so maybe there's no point fixing that part.

I think improving the feedback loops and reducing the frequency of "obvious" issues would do a lot to increase the one-shot quality and raise the productivity gains even further.

reply
kubav027
17 hours ago
[-]
Unless you are prototyping human-friendly code is a must. It is easy to write huge amounts of low quality code without AI. Hard part is long term maintenance. I have not seen any AI tool helping with that.
reply
conradkay
12 hours ago
[-]
I find that there's an very high correlation between code I'd expect to confuse humans and code which confuses/breaks LLMs

When you let them pump out code without any intervention, there becomes a point where they start introducing bugs faster than they get fixed and things don't get better

reply
jbellis
20 hours ago
[-]
Good to see experiences from people rolling out AI code assistance at scale. For me the part that resonates the most is the ambition unlock. Using Brokk to build Brokk (a new kind of code assistant focused on supervising AI rather than autocompletes, https://brokk.ai/) I'm seriously considering writing my own type inference engine for dynamic languages which would have been unthinkable even a year ago. (But for now, Brokk is using Joern with a side helping of tree-sitter.)
reply
swyx
17 hours ago
[-]
> You can see this in practice when you use Claude Code, which is pay-per-token. Our heaviest users are using $50/month of tokens. That’s a lot of tokens. I asked our CFO and he said he’d be happy to spend $100/dev/month on agents. To get 20% more productive that’s a bargain.

fwiw we interviewd the Claude Code team (https://www.latent.space/p/claude-code) and they said that even within Anthropic (where Claude is free, we got into this a bit), the usage is $6/day so about $200/month. not bad! especially because it goes down when you under-use.

reply
ghiculescu
6 hours ago
[-]
Thanks for sharing, looks like a great interview. Tell them I'm a big fan!
reply
ghiculescu
13 hours ago
[-]
Author here. Ask me anything!

Since writing this a tangentially related thing we've added, is a github action that runs on any PR that includes a (Rails) database migration, and reviews it, comparing it to our docs for how to write good migrations.

Claude helped write the action so it was super easy to set up.

reply
vianarafael
13 hours ago
[-]
You mentioned using Claude to help set up a GitHub Action for reviewing Rails migrations. How do you see agentic tools like Claude evolving in their ability to reason about big-picture concerns—not just boilerplate generation, but things like validating database changes, architectural decisions, or spotting long-term risks that aren’t immediately visible?
reply
ghiculescu
13 hours ago
[-]
They are really good if you give them guidance and tight scope. For example for the database migrations review bot, we give it our Cursor rules file on database migrations (which is about 200 lines) and tell it to review the PR based on that.

It works particularly well for migrations because all the context is in the PR. We haven't had as much luck with reviewing general PRs where the reason for a change being good or bad could be outside the diff, and where there aren't as clearly defined rules for what should be avoided.

reply
eschaton
10 hours ago
[-]
How do you square this with the fact that LLM-based tools aren’t actually doing any analysis whatsoever, but are just pachinko machines that produce statistically likely output tokens when given input tokens?
reply
nu11ptr
13 hours ago
[-]
Have you noticed people more productive, in general, using Claude Code or Cursor? Obviously it varies, but curious if one or the other is the clear productivity champion at this point.
reply
ghiculescu
13 hours ago
[-]
I wouldn't say there's an obvious winner yet. I do think it depends on the person and how they like to work / how they reason about problems.

For Claude specifically, people who take more time to write long detailed prompts tend to get much better outcomes. Including me, since I made the effort to get better at prompt writing.

reply
christophilus
17 hours ago
[-]
As someone who really dislikes using Cursor, what does the HN hivemind think of alternatives? Is there a good CLI like Claude Code but for Gemini / other models? Is there a good Neovim plugin that gets the contextual agent mode right?
reply
M4v3R
16 hours ago
[-]
Have you tried Aider? They're making a CLI coding agent for quite some time and have gained quite a bit of traction.

[0] https://aider.chat/

reply
gen220
15 hours ago
[-]
Seconding aider, which was recommended to me months ago on HN. They don't integrate with vim directly per-se, but I'm a heavy vim user and I like the workflow of `aider --vim`, `ctrl-z`, `vim`.

They also have a mode (--watch-files) that allows you to talk to a running aider instance from inside vim, but I haven't used it much yet.

reply
tcoff91
10 hours ago
[-]
The file watch mode is great. Also nvim-aider is a great plugin which makes it really easy to manage context from within nvim and add diagnostics to chat
reply
ericmcer
16 hours ago
[-]
Sweet spot for me was cursor for autocomplete/editing and manually using Claude for more deep dive questions.

I cant go back to a regular IDE after being able to tab my way through most boilerplate changes, but anytime I have Cursor do something relatively complex it generates a bunch of stuff I don't want. If I use Claude chat the barrier of manually auditing anything that gets copied over stays in place.

I also have pretty low faith in a fully useful version of Cursor anytime soon.

reply
polskibus
16 hours ago
[-]
Jetbrains tools have MCP plugin and can work with Claude.
reply
danenania
15 hours ago
[-]
> Is there a good CLI like Claude Code but for Gemini / other models

I built an open source CLI coding agent that is essentially this[1]. It combines Claude/Gemini/OpenAI models in a single agent, using the best/most cost effective model for different steps in the workflow and different context sizes. The models are configurable so you can try out different combinations.

It uses OpenRouter for the API layer to simplify use of APIs from multiple providers, though I'm also working on direct integration of model provider API keys.

It doesn't have a Neovim plugin, but I'd imagine it would be one of the easier IDEs to integrate with given that it's also terminal-based. I will look into it—also would be happy to accept a PR if someone wants to take a crack at it.

1 - https://github.com/plandex-ai/plandex

reply
chw9e
16 hours ago
[-]
> I haven’t yet come across an agent that can write beautiful code.

o3 in codex is pretty close sometimes. I prefer to use it for planning/review but it far exceeds my expectations (and sometimes my own abilities) quite regularly.

reply
DGAP
16 hours ago
[-]
Even if you don't think AI will replace the job of software developer completely, there's no way compensation is going to stay at the current level when anyone can ship code.
reply
scudsworth
17 hours ago
[-]
>Our head of product is a reformed lawyer who taught himself to code while working here. He’s shipped 150 PRs in the last 12 months.

>The product manager he sits next to has shipped 130 PRs in the last 12 months.

this is actually horrifying, lol. i haven't even considered product guys going ham on the codebase

reply
AtlasBarfed
16 minutes ago
[-]
Mwahahaha

Noncoders are about to learn about the code maintenance cycle

reply
fishtoaster
17 hours ago
[-]
Honestly, it's been pretty great at my tiny startup. The designer has a list of tweaks he wants that I could do pretty quickly... once I'm done with my current thing in a day or two. Or he can just throw claude at it. We've got CI, we've got visual diff testing, and I'll review his simple `margin-left: 12px;`->`margin-left: 16px;`.

But we're unlocking:

A) more dev capacity by having non-devs do simple tasks

B) a much tighter feedback loop between "designer wants a thing" and "thing exists in product"

C) more time for devs like me to focus on deeper, more involved work

reply
dgunay
15 hours ago
[-]
Code review makes this a lot less scary. Honestly it seems like mostly a win. A while ago at my day job, a moderately technical manager on another team attempted to contribute a relatively simple feature to my team's codebase. It took many rounds of review feedback for his PR to converge on something close to our general design guidelines. I imagine it would have been way less frustrating and time consuming for him if he could have just told an AI agent what to do and then have it respond to review feedback for him.
reply
snoman
17 hours ago
[-]
Ostensibly the PRs are getting reviewed so it’s, maybe, not that bad but I had a similar reaction: I can slap together something with some wood, hammer, nails and call it a chair. Should I be manufacturing furniture?
reply
11217mackem
13 hours ago
[-]
Sure, if it's good, it works, it's reliable and people like it.
reply
11217mackem
13 hours ago
[-]
It is definitely scary if the good PMs who are solid at authoring requirements are able to just make it happen. Not worried for the most part tho.
reply
asadm
15 hours ago
[-]
that's actually great! win-win for everybody. Although not fun reviewing those early PRs.
reply
AtlasBarfed
13 hours ago
[-]
I'm wondering how much better llms are at "untyped"/loosely typed scripters like Ruby for large scale coding and error avoidance.

Presumably an llm can actually maintain better contextual awareness of code and variables than, say cold loaded syntax highlights.

reply
sensanaty
6 hours ago
[-]
As a hobby rubyist, pretty terrible compared to Typescript. I suspect it's also that there's less Ruby in the training sata, but Ruby being so dynamic and ducktypable means it produces some truly nightmarish shit from time to time
reply
viraptor
13 hours ago
[-]
They likely aren't. I'm getting occasional issues caught by type checks in the LLM output. They would be weird crashes instead in other languages.
reply
11217mackem
13 hours ago
[-]
ultimately, it comes down to training data and character count

llms can be better than most humans at applescript

just need a fuck ton in context

reply