I am a new developer from it pro.
I use chatgpt with custom gpt and cursor with Claude at the same time on 2 screens.
Why? Because cursor with Claude limits my query number to 500.
So I only use Claude when I know exactly what I am solving.
Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
131–140 of 140 posts
Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
#132Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
#133I'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:…
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.
Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
#134I'm SO surprised to not see aider-chat everywhere mentionned. I've been using it for about a year and it's incredible. My take is that most people did not invest the little time necessary to get acustomed to its workflow. My advices for aider are: - familiarize yourself with the chat modes (architect, code, ask) - familiarize yourself with the edit modes (diff, whole, etc) and know which to use for a given model. Ind…
Agree,
I think aider chat forces the prompter to develop good habits in the prompting process, like providing the proper context, problem decomposition and utilizing the LLM capabilities properly.
The Aider interface and additional setup required in the process makes it more productive over time.
Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
#135Earlier quoted context omitted.
You get the same experience inside VS Code with Copilot these days, as long as you select agent mode. Yesterday I even asked it to read documentation off a URL and it asked me permission to fetch the page, summarized it, and applied the API changes needed.
Not really. This is an example of something that Claude Code handles very easily and for Github Copilot, is not even an starter (because can't read SQLite files) >Read the Sqlite file in this directory and create an UX that would visualize and manage the data. The application should be responsive (so it can be use on mobiles) and should have some graphs when appropiate.
Actually, it can. I've just gone and checked. Agent Mode executed sqlite on the terminal, got the schema, and issued the relevant changes.
Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
#136I've been trying out Windsurf for the past two weeks with VS Code and I find it (and Copilot) very helpful, but also very annoying. Occasionally, the windsurf command overlays (explain, accept, etc...) will get stuck and make it impossible to see the code until I restart VS Code. But the biggest problem that I have is with automatic auto-complete. With both Windsurf and copilot, I have trouble figuring out when / if…
Windsurf user here too. Same issue with autocomplete being tough to target / control, and often the weak style difference between my code, diffs, and suggested makes my files unreadable in ws. It is straight up BUGGED on console command auto run too —even on Turbo mode, if a console command requires any interaction or takes a few seconds to run, sometimes the status of that command hangs forever. That said, the tool is as good as the rest as far as generating, maybe cleaner in terms of conversation and action flow tracking / versioning. Conflicted.
Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
#137I'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:…
>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.
Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
#138agentic ides are better for vibe coding because every time prompted it has the context of the whole codebase and it can edit multiple files and even run console commands or write docs, its easier to vibe debug too, so its much better than copypasting file by file with something like google ai studio. though agentic ides usually come with an elevated price tag.
Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
#139I'm curious if anyone has experience with continue.dev using agent mode and how it performs relative to copilot or cline.
Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
#140I'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:…
>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.
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?