Live data from Hacker News

Canvas is a new way to write and code with ChatGPT

openai.com

231–240 of 701 posts

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

#231

Earlier quoted context omitted.

Canvas is closer to Cursor ( https://www.cursor.com ) than Claude. I wonder how Paul Graham thinks of Sam Altman basically copying Cursor and potentially every upstream AI company out of YC, maybe as soon as they launch on demo day. Is it a retribution arc?

It's just a company that promised AGI would somehow come from developing LLM-based products, rapidly scrambling to keep up with other LLM-based products, to distract from the fact that it's becoming increasingly apparent that AGI is not coming anytime soon.

Yeah I completely agree with this, it makes me sad that OpenAI are spending time on this when they should be pushing the foundation models ahead.

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

#232
post #155

Earlier quoted context omitted.

I do a lot of cybersecurity and cyber adjacent work, and Claud will refuse quite a lot for even benign tasks just based on me referencing or using tools that has any sort of cyber context associated with it. It's like negotiating with a stubborn toddler.

This is surprising to me as I have the exact opposite experience. I work in offensive security and chatgpt will add a paragraph on considering the ethical and legal aspects on every reply. Just a today I was researching attacks on key systems and ChatGPT refused to answer while Claude gave me a high level overview of how the attack works with code.

Really odd. ChatGPT literally does what I ask without protest every time. It's possible that these platforms have such large user bases that they're probably split testing who gets what guardrails all the time.

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

#233
post #146

Earlier quoted context omitted.

I'm with you. I feel like I'm losing my mind. Everyone around me is talking about the looming AGI, death of the knowledge worker and how "everything" has changed. But every time I try to use these text generators I get nothing useful from them. It's like the whole world has bought into a mass hallucination.

It makes more sense when you realize that while sure, there might be slight variation in output, generally speaking the people tripping over themselves in how [current version] is so amazing aren't being totally honest about why they think it's amazing. For them, the ability to generate so much trash is the good part. They might not even be fully aware that it's trash, but their general goal is to output more trash b…

Its a tool, like any other tool a software developer would use. In areas where I have a lot of repetition or need to pour through verbose (but simple) documentation, its such a game changer. I can spend 5 minutes thinking about what I want the machine to do, give it some samples of what I expect the output to be and wala, it generates it, often times 100% correct if I've got the prompt put in properly, sometimes its good enough with a bit of refinement. This is something I would normally have delegated to a junior team member or sub-contractor, but now I'm saving in time and money.

Occasionally I sink 1-2 hours into a tweaking something I thought was 90% correct but was in reality garbage. I had that happen a lot more with earlier models, but its becoming increasingly rare. Perhaps I'm recognizing the limitations of the tool, or the systems indeed are getting better.

This is all anecdotal, but I'm shipping and building faster than I was previously and its definitely not all trash.

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

#235

OpenAI is so far ahead of the competition. They're able to implement anything they like from competitors, and then some. Claude really needs a sandbox to execute code. If Anthropic would be smart about it, they'd offer developers ("advanced users") containers which implement sandboxes, which they can pull to their local machines, which then connect to Claude so that it can execute code on the user's machine (inside t…

This is an odd comment, because you mention Claude and Google, both of which already have similar/adjacent features. For a while. OpenAI is actually defensive/behind. 1. Claude has “artifacts” which are documents or interactive widgets that live next to a chat. 2. Claude also has the ability to run code and animated stuff in Artifacts already. It runs in a browser sandbox locally too. 3. Gemini/Google has a ton of fe…

I mean the following:

`use matplotlib to generate an image with 3 bars of values 3, 6, 1`

followed by

`execute it`

https://chatgpt.com/share/66fefc66-13d8-800e-8428-815d9a07ae...

(apparently the shared link does not show the executed content, which was an image)

https://imgur.com/a/PkJCnKO

Which has interesting consequences, because I saw it self-execute code it generated for me and fix the errors contained in that code by itself two times until it gave me a working solution.

(Note that I am no longer a Plus user)

---

Claude: I apologize, but I don't have the ability to execute code or generate images directly. I'm an AI language model designed to provide information and assist with code writing, but I can't run programs or create actual files on a computer.

---

Gemini: Unfortunately, I cannot directly execute Python code within this text-based environment. However, I can guide you on how to execute it yourself.

---

> 4. Also you can use takeout

I just checked and wasn't able to takeout Gemini interactions. There are some irrelevant things like "start timer 5 minutes" which I triggered with my phone, absolutely unrelated to my Gemini chats. takeout.google.com has no Gemini section.

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

#236
post #14

I'm really happy to see ChatGPT doing this. The idea of a canvas made me really enjoy using Claude as I felt it to be the (so far) most "appropriate interface" to AI Chatbots as you are often doing two unique things in an AI chat: - holding in your mind a "thing" (i.e. some code) - talking about a "thing" (i.e. walking through the code) The same applies to non-code tasks as well. The ability to segregate the actual "…

Have you used it?

Why do you ask? I did use "4o with canvas" shortly after writing the above. To be clear, my original comment was not about the actual OpenAI implementation of a "canvas style chatbot", but rather that I have found the canvas-chat-UX to be the most effective way to interact with a chatbot. I am basing this on many hours with both ChatGPT (non-canvas until today) and Claude/Anthropic (who has had this feature). As of this writing, I prefer Claude both because of (a) the content of its output and (b) the canvas style, which allows my brain to easily parse what is the topic vs. discussion about the topic.

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

#237
post #221

The issue I continue to have with many AI coding tools is they want me to use their own editor ("native", aka VSCode fork, or in the browser like this). I have zero intention of moving away from IDEA and nothing I've seen so far is good enough to make me want to switch. I really with there was more of "bringing AI into your existing tools/workflows" instead of "here is a new tool with AI baked in".

Have you considered this one: https://github.com/continuedev/continue

I tried it a while back and had a lot of trouble getting it to work, it's on my list to try again. I also tried Sourcegraph's Cody and just constant errors even after paying for the Pro plan so now I'm back on Copilot.

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

#238
post #221

The issue I continue to have with many AI coding tools is they want me to use their own editor ("native", aka VSCode fork, or in the browser like this). I have zero intention of moving away from IDEA and nothing I've seen so far is good enough to make me want to switch. I really with there was more of "bringing AI into your existing tools/workflows" instead of "here is a new tool with AI baked in".

Have you considered this one: https://github.com/continuedev/continue

I didn't realise Continue had a Jetbrains IDE plugin. Neat! Going to give it a go.

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

#239
post #149
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 have a friend who has ZERO background in coding and he's basically built a SaaS app from the ground up using Replit and it's integration with Claude.

Backend is Supabase, auth done with Firebase, and includes Stripe integration and he's live with actual paying customers in maybe 2 weeks time.

He showed me his workflow and the prompts he uses and it's pretty amazing how much he's been able to do with very little technical background. He'll get an initial prompt to generate components, run the code, ask for adjustments, give Claude any errors and ask Claude to fix it, etc.

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

#240
post #54

Earlier quoted context omitted.

You are entitled to interpret the word "programming" in multiple different ways depending on the context of the conversation. What you propose here as "programming" is valid but not comprehensive of what everyone may think of when considering the "programming" process. By many definitions of "programming", these AI tools are indeed programming. In the same way, many definitions of "reasoning, ..." may include the AI…

These AI tools are able to do a small subset of what a professional human is able to do, with greatly reduced flexibility, e.g. tasks like leetcode where there is an abundance of concentrated training data. I would bet that the current paradigm in ChatGPT will never be able to replace a minimally competent human at real world programming - the kind of programs people actually pay for. Let’s see.

> I would bet that the current paradigm in ChatGPT will never be able to replace a minimally competent human at real world programming - the kind of programs people actually pay for. Let’s see.

Depends on definition of "minimally competent". There WILL be over-engineered enterprise solutions that employ 10x more AI-enabled code monkeys than is strictly required. Think about it: we can create a "fully automated AI coder" and then hire another FTE (or team) to handhold and clean up after it. It will be done. It must be done.

Post reply on HN