Comment by SeanAnderson | Hacker News Reader

Comment by SeanAnderson | Hacker News Reader

I'm a staff software engineer doing a mix of front-end and back-end with emphasis on front-end.

I use both Cursor on Claude 3.7 and ChatGPT on 4o/o3. Cursor seems kind of "dumb" compared to 4o, but it's a good workhorse.

I let Cursor handle the basics - basically acting as a glorified multi-file autocomplete. I think through common problems with 4o, tough problems with o3, I copy all of Svelte's docs into 4o (https://svelte-llm.khromov.se/) to get good Svelte 5-focused feedback, I have 4o code-review what Cursor writes from time to time, I have 4o, sometimes o3, generate "precise" prompts that I'll give to Cursor when me talking off-the-cuff to Cursor doesn't get good results after a few attempts.

I don't consider myself an expert in these areas yet so I might be misusing Cursor, or not making enough use of its rules system, or something. I feel like I get good value for my ChatGPT subscription. I don't feel like I get good value for my Cursor subscription, but I also still feel like keeping it because $20 to type a lot less is still pretty nice. I would be upset if I only had a Cursor subscription and no access to ChatGPT. I am pretty hesitant to pay for AI à la carte. I feel much better about working within the limitations of a known subscription cost.

>I let Cursor handle the basics - basically acting as a glorified multi-file autocomplete.

Same experience. I'm in no need to let the AI write large, real working code. But it's amazing for fast refactoring, function signatures, boilerplate, etc. The real boring parts. I only wish it wouldn't be so eager to try to dump a 50 lines of bullshit code every time. But for small changes, super cool.

I honestly believe they do this BS shit so you waste tokens and pay more.

Engagement, after all.

When you say fast refactoring, etc. can I ask if you've used visual studio?(and I assume the Java equivalents)

As they have had for over a decade fast refactoring (extract method, boilerplate generation, change function signatures everywhere, suggested code refactoring due to language improvements, one click refactoring based on linting suggestions, etc.).

Without AI.

I'm just confused as the stuff you've mentioned already existed and doesn't need an AI to do it.

So can it do something more or are you using AI tokens to do something most decent IDEs can already do without AI?

same experience. Editor agents with basic level tasks and boilerplate. Problem solving and decomposition of it in the chat apps seems to be better. What I've noticed is the agent modes of these editors use the embeddings API of ChatGPT and how the LLM model maps the context of the codebase. Often what has happened is the LLM's in Agent mode ignore the default setup of the codebase example package managers and use the package managers which would be popular throughout their training data.

To summarise the Agent Mode editors don't try to fill in their context gaps and be aware of the environment they operate it unless explicitly specified by the prompter to first review the codebase, understand it's structure and then proceed with implementing features.

Can you please elaborate on how you're copying Svelte's docs into 4o?

I just download the Svelte + SvelteKit (Recommended - LLM Distilled) file from the link mentioned in my original comment and drag-and-drop upload it into the chat context when I'm talking to 4o about coding. Nothing magical. It takes a second to read through the document, but then the LLM works significantly better. It stops suggesting invalid Svelte 4 syntax and prioritizes using Runes.

> Cursor seems kind of "dumb" compared to 4o

What do you mean by that? You can use 4o model in Cursor?

Cursor lists a large number of models out of the box, and you can select which one you want it to use. https://docs.cursor.com/settings/models

Cursor tries to save more money on context than ChatGPT. So when both are targeting GPT 4o, the ChatGPT App will incorporate more context history and memories than Cursor.

I think part of the reason is, ChatGPT has additional system prompt in chat, API doesn't have.

even if both companies use same model (OpenAI and Cursor), system prompt has a huge impact on results

Reply on news.ycombinator.com