An image is worth a few lines of code ;)I have been trying to get something like this working in one form or another for close to a year. The latest image models finally make it possible.It's still early, but I'm really interested in this approach to AI UI - using image models before coding models for front end development. The challenges are; 1 - How do we get image models to generate decent...
I’m using AI tools heavily for coding, but I’m still figuring out the best way to incorporate product/UX design without it feeling bolted on. For those using AI in your dev workflow, how do you integrate design thinking, UI iteration, and usability checks? Do you use specific tools, prompts, or checkpoints? Would love to hear concrete workflows that have worked well.
https://github.com/just-every/code
Hey HN,Today we're launching Code, a community-driven, open-source coding agent for your terminal. It's a fork of OpenAI's codex with a focus on developer ergonomics and local control.Key features: - Browser integration – attach to your Chrome via CDP or use a built-in headless browser. You can browse pages, run the CLI in a browser session, and even take screenshots from the terminal. -...
Hey HN,After a decade building ChargeDesk, we've created something that finally bridges the gap between modern LLMs and practical customer engagement. Happy to Help observes visitor behavior with client-side encrypted monitoring and uses AI to intervene at critical moments.We actually prototyped this four years ago, but shelved it because the AI wasn't capable enough. With recent advancements...
Twitter recently stopped apps from offering any kind of bulk management services for Twitter accounts. We completely support Twitter trying to stop spam, but this action does nothing of the kind. Here's my full thoughts; http://blog.manageflitter.com/twitter-drowning-spam-why-thei...
Anyway the point of this service us just to point out how ridiculous the restrictions are. We will really be delivering it, however - the economics work. We're just finalising how we'll prove it's real people, most likely with a live stream going at all times.
Plenty of interesting ways that kind of bar could be included in a site.
One of the things I'm not so sure about is the local bindings for each language. I'm tempted to just use off-the-shelf HTTP clients or a very thin wrapper in each language and write code snippets based on them. I'm not sure I see the value in writing full client bindings - I've often found it harder to use in many cases when I use these 'opinionated' bindings in the past. You often end up with a choice of entirely following the libraries views on error handling or digging around and breaking upgrades by modifying these libraries directly. I've always preferred much thinner wrappers that have no knowledge of the underlying API calls. Would love more opinions!
The first barrier in social networks is people - getting enough people on your network to incentivize others to follow. Is the fact that app.net paid enough to draw people away from Twitter & Facebook? As a developer, perhaps, but as a user, I really doubt it.
A much better sales pitch would be just "you own your data". Give users amazing import/export tools from the get go. Allow third parties to fork your system and allow seamless user migration. Build a protocol, not a service.
With a business hat on, I also worry about the single silo of data in app.net. Say it does become successful, then they're a monopoly again. How can we be sure they'll fairly charge for their API usage when they realise how much it costs to hosts that much real time data? Can we be sure they won't change the playing field again?
Besides all that, I don't get why he wants $500,000 up front. If he wants to "align our financial incentives with members & developers", I would have thought he'd charge a set fee to allow revenue to scale with usage.
Also the language on the site is just so damn confusing. They have lots of ideas jammed in together. Most of the discussion about the idea has been people trying to figure out what they're on about. They need to figure out a sales pitch people can understand and stick to it.
Anyway, lots of huge holes in this implementation IMO. I doubt it'll even get funded.
It looks like it runs very similarly to our current server management systems, but the web UI is a huge plus.
I agree that open sourcing it to run on your own infrastructure would be a big benefit - people tend to be a bit protective of where they put their root ssh keys :)
I would never send an email that said "You fucking changed my CSS". It happens ALL the time to developers. In fact refactoring, telling each other what you think is wrong in the code and how to fix it is a core part of team software development. Nothing is ever perfect. You can't be that protective of any part of your product.
By the same token, I totally accept when the things I've spent hours pouring over get thrown out the door. We recently had a design review where someone said one of the elements I put hours into looked like a 3 year old had drawn it (they didn't know it was done by me, they thought it was outsourced). It was the kind of style I was going for, but that reaction made me realise it totally wasn't suitable for the site. I was a little hurt of-course, made a joke about it and brushed it off. We now have a completely new version of this page that's way better than my original vision.
Wrong response: “You fucking trimmed my copy.” “I don’t want to get mad but I sat there for FIVE HOURS crafting that yesterday, there’s a reason for every word.”
Right response: “I see you changed my copy. What improvements were you trying to make? I felt point x,y,z were important and you left them out. If you were trying to make it shorter, here's a shorter version that includes the more important points.“
Feedback, suggestions for improvement are very welcome :)