- Assume LLMs will be more intelligent and cheaper, and the cost of switching to a new LLM model is non-existent. How does improving the custom/heuristic compare in that future?
That's kind of what I was getting at in point 2, about "new use cases" opening up, but yeah you stated it more directly. It's hard to argue with. With a heuristic driven approach we know we will need expertise, dev hours, etc to improve the feature. With LLMs, well, some lab out there is basically doing all the hard work for us, all we need to do is sit back and wait for a year or two and then change one line of code, model="gpt-4o" to model="gpt-5o" or whatever.
$50/month in the subscription price in the personal tier (currently not accepting new users) includes 50 credits per month in it, and $500/month teams tier includes 250 credits per month in it. This is what I see with my current user and when I try to sign up as a new user respectively.
I'd like to see that $50/month tier reopened to subscribers, and a $0/month+credits tier added (1 concurrent active session only, constrained to small VM spec with immutable rootfs (regular devin VMs have writable rootfs), no automatic knowledge generation, no snapshots, though playbooks allowed).
> Even if that version is limited to only editing public Github repos
Not possible to constrain like that with the current Devin architecture.
Just like with other tools such as yt-dlp, the user is required to use it responsibly. As long as you don't copy text/images/svg, the only issue is going to be "trade dress" infringement since CSS styles are not copyrightable. (not a lawyer so this isn't legal advice)
Strange that this post made it to HN because I'm also releasing a Tailwind conversion this week. https://x.com/SnipCSS/status/1853586090164420639 I believe mine will be much better based on the blog post about this tool.
> . As long as you don't copy text/images/svg, the only issue is going to be "trade dress" infringement since CSS styles are not copyrightable. (not a lawyer so this isn't legal advice)
I am not lawyer as well, but this is highly unlikely true.
It is like saying that C syntax is not copyrightable so I can took their code.
What matters is the end result; what did you do with it? And particularly, is monetary gain involved? If you use tools like this to replicate innovative design, and you don't have permission to use it, it is much more complicated. Especially, if you use that in commercial setting.
This demo and the one I linked just seem so open about the AI GF use case its bizarre.
If you actually wanted a voice assistant AI, having a giggly, chatty computer acting like it has a huge crush on you is not remotely useful in day to day real world use. Unless that's exactly what you want.
That's extremely disappointing. They have time to build a Visual Studio Extension that competes with Cursor, but don't have time to release an API that would enable hundreds of new extensions/workflows.
Only reason I pay for ChatGPT Plus is because they have an API and I'm building products off of their API. I use Phind more for work, but I'm not going to pay anything unless they have an API.
My current SaaS is an extension that doesn't have much UI code https://www.snipcss.com, and my next SaaS will be a chatgpt powered web automation extension that has a good amount of UI. Both use jQuery.
Edit: I didn't say why I don't just use vanilla with querySelectorAll - majn reasons are I like how I can attach events (attaching to parent while targeting dynamically added subelements), chaining functions, and it's just less code than vanilla
I'm in Chicago - I pay for a personal office at a coworking space ($500 / mon)
To justify doing that I live in a dorm-type situation where I have shared bathroom and kitchen and only my large bedroom is private. ($800 / mon)
It's in Chinatown and because Chinese people generally keep to themselves, and I work 80 hour weeks (40 dayjob, 40 startup), it works out. When I was paying $1600 for a studio, I'd get annoyed when neighbors were regularly smoking weed. That's not a problem in Chinatown. No one smokes weed.
It's probably not for everyone - but doing both my dayjob and business from home wasn't working out. For a lot of people there's a mental switch if you have to travel and go to an office to do work. I'm one of those people. I just get more work done this way.
- Assume LLMs will be more intelligent and cheaper, and the cost of switching to a new LLM model is non-existent. How does improving the custom/heuristic compare in that future?