Hacker News Reader

Comment by spankalee | Hacker News Reader

I think this view is really short-sighted. Low-code tools date back to the '80s, and the more likely outcome here is that low-code and agentic tools simply merge.

There's a lot of value in having direct manipulation and visual introspection of UIs, data, and logic. Those things allow less technical people to understand what the agents are creating, and ask for help with more specific areas.

The difficulty in the past has been 1) the amount of work it takes to build good direct manipulation tools - the level of detail you need to get to is overwhelming for most teams attempting it - but LLMs themselves make this a lot easier to build, and 2) what to do when users hit the inevitable gaps in your visual system. Now LLMs fill these gaps pretty spectacularly.

View on HN

This makes the most sense to me too. My feeling is so-called AI is going to deliver on a lot of the things we're used to having shoddy versions of -- good natural language interfaces, good WYSIWYG type tools, all of this could turn the wix/squarespace/wordpress/etc landscape into something pretty good, rather than just OK.

In my most hopeful of futures, we've figured out how to do lightweight inference, and if the models don't run locally at least they aren't harming the planet, and all this AI tooling hydrates all the automation projects of the last 40 years so that my favorite tiny local music label can have a super custom online shop that works exactly the way they need without having to sacrifice significant income to do it.

Why your tiny custom music shop can’t sacrifice part of their income for labor, but developers losing income is ok?

I agree. I think that once your LLM hits a baseline level of computer science / programming "understanding" it can pretty easily work with whatever language. Using narrow DSLs and low code platforms could be a great way to constraint an LLM and keep it on the happy path.

It's not just about the language. The good money for these low-code tools is larger organizations which have deployment/hosting/compliance/maintenance concerns that need to be accounted for. You can knock out as many apps in whatever platform you want, but they don't want these at the IT gatekeeper level.

They want a tool that makes this file share talk to this SharePoint site which updates this ERP tool over there. The LLM approach is great for the departmental person (if they can still host shadow IT) but falls down at the organizational level. The nature of this work is fundamentally different, crappier, and less interesting than what any person on HN wants to be doing which is a contributor to misunderstanding of the market.

EDIT: fixed grammar.

> There's a lot of value in having direct manipulation and visual introspection of UIs, data, and logic

Yes. In the GIS industry for example, nothing has fundamentally changed with the introduction of LLMs. They may make the same processes more efficient e.g. though automated building of workflows. AI has significantly improved classification work of course but it's still using the same principles (we've been doing ML longer than most industries). Geocoding will get cheaper and easier but it's still geocoding.

GIS software allowing standard visualisation, export and map production will bet a lot better because of LLMs. It's an area where the sheer complexity and number of formats was overwhelming, but now a GeoTiff parser can be built in a day or two.

The article was making a bit of a sweeping statement based on a single datapoint: they didn't need Retool anymore.

Mendix is nothing more than MS Access for the Web.

Ok funny anecdote: I once did a special assignment for the CEO of Mendix to build a convertor for MS Access apps to Mendix. So, yes, I can confirm that this is roughly true ;)

I wrote a short post about it on my blog: https://blog.waleson.com/2022/10/access2mendix.html

And long before that i built an ms-access UI on top of an Oracle 6 database, so yes, MS-Access was one of the client-server era low-code tools. Like powerbuilder, Oracle Forms, etc. (Hi jouke!)

Nice seeing you here Andrej!

Anything no-code or low code has a data model, and an agent can manipulate it in ways that are compatible with the system design. Letting an agent loose on a problem, without a good pilot, just leads to poor designs.

Agreed, the low code dream has been around a long time. Douglas Copeland, the novelist who named Generation X, wrote a book called Microserfs in 1995 about a startup building a low code platform.

> There's a lot of value in having direct manipulation and visual introspection of UIs, data, and logic. Those things allow less technical people to understand what the agents are creating, and ask for help with more specific areas.

A lot of value indeed, but not just for less technical people. Imagine ddd vs gdb. Usually some kind of visual debugging aid isn’t available in an environment because the ROI isn’t there, not because technical people love mental parsing or hate graphics. The LLM revolution is changing the calculus here: creating new tools and new visualizations is easier than ever. It would be unthinkable three years ago to create a visual debugging aid just to use it once, outside of truly gnarly and show-stopping bugs; now it could very well be feasible.

Reply on news.ycombinator.com