What % of cloudflare's protection can this provide? I've been looking at bunkerweb + anubis as alternative to cloudflare tunnel (im actually not sure if this provides WAF)
This isn't really comparable to any of the SaaS based products.
While this offers many of the same technical capabilities as Cloudflare, a lot of Cloudflare's value is in having high-level, aggregate insight into threats.
Prompt quality and knowing your domain is critical. One issue I had early on was experimenting with LLMs to generate a frontend application in a brand new framework I was unfamiliar with (Svelte at the time) which lead to situations where I would cruise along and get stuck in a loop. The other issue came from the increasing context size that led to more unpredictable behaviors (i would ask it to change the color of a button and it would completely change the entire page).
almost all the tools i've used to date for designing frontend framework, none really replaces using cursor and being able to dive deep, however cline does seem to have gotten significantly better.
the day where you can come back to a fully working web app with moderate complexity after cleaning the gutter is still some way off but thats the dream
How much of this is a cage we've built for ourselves? When I made my first website in 1998 even if we had had LLMs asking one how to change the color of a button would be ludicrous because I'd change an HTML attribute (did CSS exist back then? don't remember) either in a static file or in a perl script. That's it. And the modern "throw a hundred and seven frameworks at it" stack doesn't really do anything that simple CGI CRUD app couldn't do.
What has changed over the years is our expectations and requirements. Sure, you can skip "all the noise" and slap an attribute on your button, but then you'll have to track down another 20 buttons in your codebase that need a color update. You can be smart with your approaches, but at a certain project size and complexity, frameworks are unavoidable. The only choice you really have is to learn an established one or handcraft something new for every thing you make.
That’s the problem template languages solve. That button could be a partial, and you include it where you want a button. And with grep, you can track it down.
The problem with frameworks is with feature/need fit. Sometimes you need something simple and using a framework results in a big percentage of dead code. Or you extend it enough that there’s no longer any benefits.
Same experience with context size and prompt quality.
Some other things I picked up:
- If you formulate a good prompt with small (but sufficient) context and it still makes mistakes after one attempt to feed the error message back to it, it's probably not going to be able to ever get it, no matter how many iterations you do with it. It will get stuck in a rut forever. Better not to argue with it.
When I catch an agent falling into a “debug loop” I ask it to summarize its understanding of the error. Next, I ask it to shift its context to a higher level in the code and look for patterns across my files which would impact {summary of error).
It isn’t foolproof but it has a much better success rate for me than letting it spin.
Welcome to the agentic age, where prompting can be just barely automated, but tokens are so cheap it doesn’t matter. Fresh off the presses as of last week
forgot the name of the watch but it had an lcd display to save battery and a full touchscreen around 2017? i ended up using the lcd display mostly for HB and walk distance. it would be great if we had a completely e-ink based pebble watch with backlighting (lcd display was great but couldn't be viewed in the dark :/)
reply