I have found good success with Claude Code/AgentOS. The real question - is Elixir the best language to develop with using AI code generators? It may be?

If the software is doing complicated integrations, that may be a barrier as said in the article.

And to be clear, this is people using teams of Claude Code agents (either Sonnet 4.5 or Sonnet 5 and 5.5 in the future). Reliability/scale can be mitigated with a combination of a senior engineer or two, AI Coding tools like the latest Claude Code and the right language and frameworks. (Depending on the scale of course) It no longer takes a team senior and mid-level engineers many months. The barriers even for that have been reduced.

Completely agree that using Lovable, Bolt, etc aren't going to compete except as part of noise, but that's not what this article is saying.

Sorry. This is totally not AI slop. AI-edited for grammar, but human-created.

What industry are you building in? And have you been building in it a while or is it a new startup?

I think this puts the onus in the wrong direction. I _love_ LLM coding and write probably 70% of my code that way. But having seen its (current) limits, and building a few toy apps myself, I'd love to see examples of successful, complex products that are mostly vibe coded. Until I see that, I'll continue to believe the current crop of LLM is best suited for building prototypes, helping get initial ideas shipped, and helping speed up very experienced developers working in well trodden ground (i.e. mostly CRUD in popular languages / frameworks), because that's what most peoples experience is (at best - many here wouldn't be nearly as generous as my takes).

Look at the AI visibility tools. They all integrate with multiple LLM models, include scheduling, management of multiple external processes, data parsing, site-scraping, graphs, as well as multiple database structures. They need retry and error logic, real-time displays and updates, and multiple flow UX's, and Stripe integration with webhooks, and subscription management.

Same thing with competitor monitoring. These tools require scraping multiple sites, checking X, Facebook, Jobs sites, Crunchbase, etc, aggregating data and displaying and making sense of changes. And the same multi-process management, queuing, and Stripe integrations.

A few years ago, these would both fit into businesses requiring many months of development to get it all running. Now we are seeing dozens of companies emerging in each of these categories each month as they take weeks to build. And if one finds a cool aha (a new integration or graph or UX flow or positioning) the others can quickly follow in a week or less of AI-agent coding.

There are dozens of other categories where this is happening too.

The hard part of figuring out the nuances of the APIs and integrations and retries and AWS integrations and Rabbit MQ configurations and corner cases can all be done by AI with the right context.

On a tangent, I sometimes avoid correcting typos and awkward expressions because it adds non-ai signal. I do t intentionally add any, but I let them be.

I like that this is a meta comment :)

Very timely with Google's new Flash image release today.

I wonder when ChatGPT is going to switch over to links or if they will keep hiding them so you continue to stay on the platform.

Also, when are the links just going to be pay to be linked?

LOL. AI is currently like a mid-level average to good engr who can write good code but ocassionally goes off the rails. Any engr on a team with those characteristics would be heavily vetted in reviews. Almost like a smart CS intern.

If AI was amazing senior level engr, it would be a different story.

Yeah right now that's certainly true.

But my belief is those companies will soon realize that some of the people who they thought were junior are pretty adept at AI management - more adept than the senior people. And that skill will suddenly be more in demand than how well you can code an optimized sorting algorithm.

Some will get there faster than others of course. But AI is changing things so quickly that it may happen faster than we think, given the state right now.

I don't mean right now, I mean going as far back as 2018 at least when I had to go through a brutal slog over many months to get my first gig as a new software dev. I eventually ended up in a midlevel role and had to grow into it (I still feel like I found a Willy Wonka golden ticket).

But it is infuriating to see people suggest that there is such a thing as junior level positions and that companies actually want to hire junior level people. That has been absolutely false for a very long time.

Totally fair. Sorry you had to go through that.

Yeah the joke is companies want to hire someone who is already an expert in that role who is curious and a fast learner, without realizing that if someone is already an expert who is curious and a fast learner, they probably want a different role to grow into.

I don't mean to shit on your article. I think the general gist of it is correct; what it means to be a software developer is going to radically change for all levels, not just we mere mortals without the magical word "Senior" in our titles. Being fluent in prompting and supervising AI agents are going to be more of the day to day than cranking out lines of code.

I'm just (I think justifiably) a little salty because not that long ago LEARN TO CODE!!! was the mantra for those who wanted to step up into a middle class life and now every executive and their mother is frothing at the mouth over shoehorning AI into anything and everything and pulling up what little of the career ladder exists while they're at it.

Yeah people still need to learn to code. Anyone frothing at the mouth needs to see a doctor.

I agree that AI does not replace the best people in those roles. It can do an average to good job. Maybe it can reach top 40% of the industry? If you need the best UI or best marketing, humans are still netter. Those top human jobs won't go away for a while.

With that in mind, if you just need average to good, AI can do a good job at a tiny fraction of the cost. So the average to good roles will start getting replaced.

As examples, the sites tellmel.ai, and rivalsee.com for example were created without needing a UI or frontend designer. In the past I would have needed to hire a UI employee or consultant to do either of those at a very large expense (especially for the really good ones).

Hitting the vibe ceiling is real. I know a bunch of non-devs who come to me asking for help after vibe coding and hitting the ceiling. Usually the best thing to do is to just re-start.

(Also hitting the vibe ceiling happens with developers too- best way to get around it is to revert all changes and start the feature over).