Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

news.ycombinator.com

Post reply on HN
Print view View original

121–130 of 140 posts

Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

#121

Post by Ey7NFZ3P0nzAe »

extralarge wrote: post #113
Ey7NFZ3P0nzAe wrote: post #56

I'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…

Do you find that the time you spend splitting a feature up into small chunks and explaining each small chunk to the LLM takes longer than just writing the code yourself? I've used aider but found just pounding out some code in neovim to be faster. Perhaps I'm not using aider correctly.

I do think that it can take maybe a little more time with aider but this time investment pays itself off as soon as there is some complexification or issue that LLMs can't fix.

See, if you have no idea of what kind of architecture was used for the passed 150 commits, it will take more time to debug or see if a given new featufe you have in mind is doable without major refactoring for example.

This will probably matter less as LLMs grow more powerful I admit

Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

#124

Post by Imanari »

Ey7NFZ3P0nzAe wrote: post #56

I'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…

Same here, I'd even say you made the learning curve sound worse than it is, no offence :)

This is my workflow for 90% of tasks:

1) /ask: I want to do X. / How would you do X? / What options do I have for X?

2) (optional) /ask>: make these adaptations / consider this / follow up question.

3) "go ahead" (this defaults to /code mode)

For a model I like the style of Sonnet3.7 best.

One caveat: I add my files manually. Knowing what you want and where you want it is 90% of the game and this is where LLMs usually get it wrong.

Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

#125

Post by gollum999 »

faustlast wrote: post #49
fhd2 wrote: post #40

I settled on gptel, which is an LLM package for Emacs. It's kind of a mix of both approaches: 1. You have chats right there in the editor, easy to copy/paste and manage context/history without switching to a browser. You can also quickly add files or portions of files to the context or remove them again. 2. You can choose which model you want to use for what, granted you have an API key. 3. You can quickly highlight…

have you tried aider? Using it with magit to see the changes is a good workflow. the aider integrations to emacs are also worth it, you can easily add/remove files and send highlighted parts of your buffer.

Do you use aidermacs or something else?

Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

#126

Post by starstripe »

SeanAnderson wrote: post #16

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:…

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

Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

#127

Post by SeanAnderson »

starstripe wrote: post #126
SeanAnderson wrote: post #16

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:…

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.

Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

#128

Post by flashgordon »

I'm the same boat. I came to Gemini after using curosr and Claude code. The latter are touted for their auto complete. But frankly the copy paste has not been the context-switch-nightmare I was worrying about. Best analogy I can think of is with Claude I am playing chess (doing local code completion) where as with Gemini I'm playing Go. Getting concept and large blocks of design patterns (and actually working at that) at time. So since I'm thinking at a much higher level the copy paste is hardly an issue (for me).

Oh frequent checkpointing etc are still key.

Re: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

#130

Post by pmelendez »

rcarmo wrote: post #64
olalonde wrote: post #10

I use Claude Code (cli tool) and it's on another level. Not even comparable to code autocomplete à la Copilot or copy/pasting into a LLM chat app. It knows about your whole code base, can use external tools, read documentation, run tests, etc. Even as an experienced developer, it's been a huge productivity boost. The main downside is that it can quickly get expensive.

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.

Post reply on HN