I’ve found Claude and ChatGPT to be the best coding tools for me.
I often throw the results from one into the other and ping pong them to get a different opinion.
Canvas is a new way to write and code with ChatGPT
311–320 of 701 posts
Re: Canvas is a new way to write and code with ChatGPT
#312This is cool, but I wish it were integrated into tools already used for coding and writing rather than having it be a separate app. This also demonstrates the type of things Google could do with Gemini integrated into Google Docs if they step up their game a bit. Honestly I’m scratching my head on OpenAI’s desire to double down on building out their consumer B2C use cases rather than truly focussing on being the infr…
> but I wish it were integrated into tools already used for coding Unless I'm missing something about Canvas, gh CoPilot Chat (which is basically ChatGPT?) integrates inline into IntelliJ. Start a chat from line numbers and it provides a diff before applying or refining.
> which is basically ChatGPT?
Yea, I'm wondering the same. Is there any good resource to look up whether copilot follows the ChatGPT updates? I would be renewing my subscription, but it does not feel like it has improved similarly to how the new models have...
Re: Canvas is a new way to write and code with ChatGPT
#313Earlier quoted context omitted.
What harsh punishment are we talking about here? Let's be specific: we should collectively call for him to step down from his role in OpenAI. That is not harsh. OpenAI is extremely influential on our society, and he is probably not a well balanced person.
Who aligns the aligners? Taking Sam Altman's statements about AGI power and timelines seriously (for the sake of discussion), his position as CEO directs more power than all presidents and kings combined. Even if he was widely regarded as being amazing and nobody had a word to say against him right now, the USA has term limits on presidents. Taking him seriously, he should also. -- On this specific claim however, req…
It's not about proving he did it. This isn't a court of law, it's the court of public opinion. This isn't just deciding whether someone goes to prison, this is deciding who gets to control a big chunk of humanity's future. It's not some random naysayer claiming he did it, it's his own sister. It's very likely he did it, so he should step down. Simple as that.
Re: Canvas is a new way to write and code with ChatGPT
#314Earlier quoted context omitted.
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.
The idea of AGI is silly. It’s ludicrous. Who’s been counting on it to happen? OpenAI are in the money making business. They don’t care about no AGI. They’re experts who know where the limits are at the moment. We don’t have the tools for AGI any more than we do for time travel.
There's good reasons to expect time travel is physically impossible.
Your brain is an existential proof that general intelligence isn't impossible.
Figuring out the special sauce that makes a human brain able to learn so much so easily? Sure that's hard, but evolution did it blindly, and we can simulate evolution, so we've definitely got the tools to make AGI, we just don't have the tools to engineer it.
Re: Canvas is a new way to write and code with ChatGPT
#315I don't really don't understand the appeal iterating on code in the browser away from the rest of the code base outside of cool demos. You really need to give the model context about your data model, code conventions, library choices, etc and be able to exercise it with tests to get to an acceptable result.
I use ChatGPT/Claude in bed and when I otherwise don’t have a computer handy like going on walks. When developing isolated code it works just fine without having to specify a lot of detail. For example, I’m working on a Qt QML app backed by Rust but use the mobile interfaces to code up C++ components that are independent of the Rust logic and can be wired together from QML/Javascript. Since the LLMs already have lots of data on how that API works, I don’t need to feed it much info about my project. It actually helps enforce code boundaries.
Otherwise it’s mostly Cursor and Aider.
Re: Canvas is a new way to write and code with ChatGPT
#316Earlier quoted context omitted.
The whole thing is literally stapled together right now -- and he knows it, but he's got paying users and validated the problem. If he's at it for a year, it won't matter: it means he'll be making money and can either try to get funded or may be generating enough revenue to rebuild it.
Hiring people to maintain AI-generated dross is not easy. Try it.
You'd be surprised.
I worked at a YC startup two years back and the codebase at the time was terrible, completely unmaintainable. I thought I fixed a bug only to find that the same code was copy/pasted 10x.
They recently closed on a $30m B and they are killing it. The team simply refactored and rebuilt it as they scaled and brought on board more senior engineers.
Engineering type folks (me included) like to think that the code is the problem that needs to be solved. Actually, the job of a startup is to find the right business problem that people will pay you to solve. The cheaper and faster you can find that problem, the sooner you can determine if it's a real business.
Re: Canvas is a new way to write and code with ChatGPT
#317Earlier quoted context omitted.
Yeah I do. Playing with it right now. It's cool. https://i.imgur.com/R5PQQoi.png
How/where were you notified that you got it?
As another data point: I wasn't notified either. I didn't have it when I first read about Canvas here earlier but coming back to the topic now I do have the feature. This is for a Teams account, the post says Plus and Teams are the first to get it rolled out with Enterprise and other in a week.
The easiest way to check if you have access is it will appear as an explicit choice in the "Model" selector.
Re: Canvas is a new way to write and code with ChatGPT
#318Earlier quoted context omitted.
> Good prompts may actually have a moat - a complex agent system is basically just a lot of prompts. The second part of that statement (is wrong and) negates the first. Prompts aren’t a science. There’s no rationale behind them. They’re tricks and quirks that people find in current models to increase some success metric those people came up with. They may not work from one model to the next. They don’t vary that much…
That prompts aren't science means little. If anything it makes them more important because you can't systematically arrive at good ones. If one spends a lot of time building an application to achieve an actual goal they'll realize the prompts make a gigantic difference and it takes an enormous amount of fiddly, annoying work to improve. I do this (and I built an agent system, which was more straightforward to do...)…
> If anything it makes them more important because you can't systematically arrive at good ones
Important and easy to make are not the same
I never said prompts didn’t matter, just that they’re so easy to make and so similar to others that they aren’t a moat.
> I may be wrong - but I'll speculate you work on infra and have never had to build a (real) application that is trying to achieve a business outcome.
You’re very wrong. Don’t make assumptions like this. I’ve been a full stack (mostly backend) dev for about 15 years and started working with natural language processing back in 2017 around when word2vec was first published.
Prompts are not difficult, they are time consuming. It’s all trial and error. Data entry is also time consuming, but isn’t difficult and doesn’t provide any moat.
> that is hard to replicate.
Because there are so many factors at play _besides prompting. Prompting is the easiest thing to do in any agent or RAG pipeline. it’s all the other settings and infra that are difficult to tune to replicate a given result. (Good chunking of documents, ensuring only high quality data gets into the system in the first place, etc)
Not to mention needing to know the exact model and seed used.
Nothing on chatgpt is reproducible, for example, simply because they include the timestamp in their system prompt.
> Good prompts -> good output -> good training data -> good model.
This is not correct at all. I’m going to assume you made a mistake since this makes it look like you think that models are trained on their own output, but we know that synthetic datasets make for poor training data. I feel like you should know that.
A good model will give good output. Good output can be directed and refined with good prompting.
It’s not hard to make good prompts, just time consuming.
They provide no moat.
Re: Canvas is a new way to write and code with ChatGPT
#319The 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".
Tabnine has an IDEA plugin. It's not quite as good as Cursor, in my opinion, but it's better to have Tabnine and IDEA than Cursor and VSCode.
It started out as just predictive text, but now it has a chatbot window that you can access GPT, Claude, etc. from, as well as their own model which has better assurances about code privacy.
Re: Canvas is a new way to write and code with ChatGPT
#320Earlier quoted context omitted.
Who aligns the aligners? Taking Sam Altman's statements about AGI power and timelines seriously (for the sake of discussion), his position as CEO directs more power than all presidents and kings combined. Even if he was widely regarded as being amazing and nobody had a word to say against him right now, the USA has term limits on presidents. Taking him seriously, he should also. -- On this specific claim however, req…
It's not about proving he did it. This isn't a court of law, it's the court of public opinion. This isn't just deciding whether someone goes to prison, this is deciding who gets to control a big chunk of humanity's future. It's not some random naysayer claiming he did it, it's his own sister. It's very likely he did it, so he should step down. Simple as that.
Make the court of public opinion binding? Sounds like a way to force companies to become subject to democratic votes. Not sure how I feel about that for other reasons.