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

Canvas is a new way to write and code with ChatGPT

openai.com

Post reply on HN
Print view View original

191–200 of 701 posts

Re: Canvas is a new way to write and code with ChatGPT

#191

Post by vessenes »

whalesalad wrote: post #171

I want to take an existing Python application (which is 100% a 'sufficiently complicated concurrent program in another language contains an ad hoc informally-specified bug-ridden slow implementation of half of Erlang.'[0]) and port it to Elixir. Retaining the core business logic, but re-homing it inside of idiomatic elixir with a supervision tree. At the end of the day it is just orchestrating comms between PSQL, RMQ…

How big is this codebase? gpto-preview and claude sonnet are both fairly capable. Claude has longer context windows and is a little less lazy. aider.chat is working on an architect / coder model right now that's verrrry effective. Essentially - paste your whole codebase into 4o-preview, ask it to rearchitect to spec, and output a design document and list of tasks suitable for a senior dev. Dump that plus your tarball into claude as two separate pastes, and be like "Do task 1".

Re: Canvas is a new way to write and code with ChatGPT

#192

Post by danielmarkbruce »

dartos wrote: post #186
JumpCrisscross wrote: post #167

Earlier quoted context omitted.

> wonder how Paul Graham thinks of Sam Altman basically copying Cursor If OpenAI can copy Cursor, so can everyone else.

Yup. Prompts have no moat.

It depends on who the moat is supposed to keep out. A reasonable case from an antitrust regulator would be that if a provider of models/apis gleans the prompts from the users of the apis to build competing products... they are in trouble.

Good prompts may actually have a moat - a complex agent system is basically just a lot of prompts and infra to co-ordinate the outputs/inputs.

Re: Canvas is a new way to write and code with ChatGPT

#193

Post by scellus »

aeze wrote: post #149
j0hnyl wrote: post #139

Earlier quoted context omitted.

As much as I want to like Claude, it sucks in comparison to ChatGPT in every way I've tested, and I'm going to use the better product. As a consumer, the governance model only results in an inferior product that produces way more refusals for basic tasks.

Agreed on the principle (using the better product) but interestingly I've had the opposite experience when comparing Claude 3.5 Sonnet vs GPT 4o. Claude's been far and away superior on coding tasks. What have you been testing for?

I generate or modify R and Python, and slightly prefer Claude currently. I haven't tested the o1 models properly though. By looking at evals, o1-mini should be the best coding model available. On the other hand most (but not all) of my use is close to googling, so not worth using a reasoning model.

Re: Canvas is a new way to write and code with ChatGPT

#194

Post by UncleMeat »

meowface wrote: post #91
danielovichdk wrote: post #38

No thank you. As with anything else that is helpful, there is a balancing act to be aware of. This is too much for my taste. Just like github copilot is too much. It's too dumb like this. But chatgpt is insanely helpful in a context where I really need to learn something I am deep diving into or where I need an extra layer of direction. I do not use the tool for coding up front. I use them for iterations on narrow su…

I think you should try to give tools like this another chance. If Andrej Karpathy can say AI-assisted programming is a productivity boost for him ( https://x.com/karpathy/status/1827143768459637073 ), it can be a productivity boost for probably any programmer.

Andrej is a great communicator. I've never seen evidence that he is an especially exceptional programmer.

Re: Canvas is a new way to write and code with ChatGPT

#195

Post by Spivak »

meiraleal wrote: post #97
throwgfgfd25 wrote: post #27

Earlier quoted context omitted.

Well, I've just read back through some of your comments and I say that ain't so! Write honestly. Write the way you write. Use your own flow, make your own grammatical wobbles, whatever they are. Express yourself authentically. Don't let an AI do this to you.

Person A: Me try make this code work but it always crash! maybe the server hate or i miss thing. any help? Person A with AI: I've been trying to get this code to work, but it keeps crashing. I'm not sure if I missed something or if there's an issue with the server. Any tips would be appreciated! For a non-native English speaker, it's much better professionally to use AI before sending a message than to appear authent…

It's pretty good for native English speakers at work who need/want a reverse anger translator.

Me: This is the most garbage code I've ever seen. It's bad and you should feel. It's not even wrong. I can't even fathom the conceptual misunderstandings that led to this. I'm going to have to rewrite the entire thing at this rate, honestly you should just try again from scratch.

With AI: I've had some time to review the code you submitted and I appreciate the effort and work that went into it. I think we might have to refine some parts so that it aligns more closely with our coding standards. There are certain areas that are in need of restructuring to make sure the logic is more consistent and the flow wouldn't lead to potential issues down the road.

I sympathize with the sibling comment about AI responses being overly-verbose but it's not that hard to get your model of choice to have a somewhat consistent voice. And I don't even see it as a crutch, this is just automated secretary / personal assistant for people not important enough to be worth a human. I think a lot of us on HN have had the experience of the stark contrast between comms from the CEO vs CEO as paraphrased by their assistant.

Re: Canvas is a new way to write and code with ChatGPT

#196

Post by moonmagick »

Yawn. I don't use Claude because the interface is good. I use it because Opus 3 is the best model anyone has ever created for long context coding, writing and retrieval. Give me a model that doesn't have polluted dataset to game MMLU scores, something that tangibly gives good results, and maybe I'll care again.

For now I only keep ChatGPT because it's better Google.

Re: Canvas is a new way to write and code with ChatGPT

#198

Post by AndyKelley »

atomic128 wrote: post #185
AndyKelley wrote: post #157

Earlier quoted context omitted.

Counterpoint: don't try to own people like farm animals. Have pride in humanity, faith in your fellow man, and resist toxic cynicism.

Fortunes are made owning companies that sell harmful products. Domino's Pizza, Monster Energy Drink, etc. Fortunes will be made selling electricity to people who develop serious cognitive dependence on LLMs. There is no need for you to participate in the profits. I respect your life choices and I wish you well.

I don't respect your life choices and I wish you failure.

Re: Canvas is a new way to write and code with ChatGPT

#199

Post by throwgfgfd25 »

gloflo wrote: post #177
meiraleal wrote: post #97

Earlier quoted context omitted.

Person A: Me try make this code work but it always crash! maybe the server hate or i miss thing. any help? Person A with AI: I've been trying to get this code to work, but it keeps crashing. I'm not sure if I missed something or if there's an issue with the server. Any tips would be appreciated! For a non-native English speaker, it's much better professionally to use AI before sending a message than to appear authent…

Person A with AI: In the bustling world of software development, where lines of code intertwine to create the intricate tapestry of our digital lives, I find myself facing a challenge that has proven to be both perplexing and frustrating. I’ve spent over a decade honing my skills as a developer. Known for my analytical mind and commitment to excellence, I’ve navigated various programming languages, frameworks, and pr…

:-)

Re: Canvas is a new way to write and code with ChatGPT

#200

Post by throwgfgfd25 »

RigelKentaurus wrote: post #61
throwgfgfd25 wrote: post #7

Do they not understand that the example text they are using in the first image is so laughably banal that it makes an entire segment of its potential audience not want to engage at all? Shoot me in the face if my own writing is ever that bad. ETA: just to be clear... I am not a great writer. Or a bad one. But this is a particular kind of bad . The kind we should all try to avoid.

The text i supposed to be banal, so that ChatGPT can make it better. It's like the before picture in an exercise course.

It's not, is it? It's meant to be the draft it created from the notes.
Post reply on HN