What does the future hold for Developers with Generative AI steaming ahead?

Advanced scaffolding, UI generators, generative developer agents. Will this lower the barrier to entry and destroy wages? Or will it simply raise the bar for current software developers?

The current limitations of generative AI tools like Claude, ChatGPT, GPT 4o/o1/o3 APIs, and various others are that to get the AI to produce you anything genuinely useful, you need to already have a pretty good idea of what you want, and roughly how you want to do it. The frameworks and libraries you use should also be decided before hand, and potentially even 3rd party dependencies. There is still a lot of hallucination, and poor choices outputted by language models when it comes to solving software development problems, but they are improving and techniques exist to improve results.

”Advanced Scaffolding” is basically taking what an experienced developer can do in their head, and giving that task to an autonomous AI agent to perform. Once the agent is finished the experienced developer can make any changes or tweaks, fix any problems, or realign the LLM so that the results are closer to the desired outcome.

Traditionally a small proof of concept project would probably have taken a day or more to complete in the “old fashioned” way; coding by hand directly into the IDE, manually troubleshooting and debugging any issues, and setting up the server to run it on. With the “advanced scaffolding” strategy this is now possible to complete in a matter of minutes, with maybe a few more minutes to change some styling, copy or images.

Tools like https://bolt.new/ an open-source generative javascript based AI agent type app are already automating most of this process. This includes the deployment, database connections, git repositories etc…

Vercel have their own product in development called v0 which will create modern and stylish UIs using some of the latest libraries.

I am also building something similar which I have presented previously. Work on this originally had to stop due to the context limit of openAI’s models at the time, and the poor state of their API. Almost all requests would time out and for anything remotely taxing it was completely unusable. The stability and health of the API is now much better and development this tool has been progressing well, and benefitting from the improvements to the models along the way. The addition of “tools” gives these modern LLMs an unfathomable amount of power compared trying to force a usable output from text-davinci-003 and hoping the formatting was consistent. The LLM can now be given a library of functions to choose from to enhance its result if it deems it relevant to the input. In theory, this library can be driven from a dynamic source, and the LLM could even be given the capability to create new tools for itself.

IDEs with LLM support natively included are also exploding in popularity like Cursor and Zed, highlighting the usefulness of AI in software development and the need to streamline the process. The next thing to streamline will be the organism having to read visual input on a screen and press physical buttons to create files, write code, and set up servers.

The current abilities of “Developer Agents”, the stability of the APIs at the moment and the ever increasing context limits are just confirming the prediction that things like this will be taking over a large portion of the low end of the software development job market, and who knows how far its capabilities will be able to be pushed.

It will need a few more years of innovation and refining models and connecting all the various services to make these developer agents truly useful and autonomous enough to be in a position to replace a human developer. There are still a lot of kinks to work out and these models are not perfect, but the progress that I have seen in the last couple of years has been absolutely astounding and everybody should be very very well prepared for what is to come.

It doesn’t take a rocket scientist to see where these developments are heading and what the potential long term implications are if this technology continues to progress at the rate it has been, and what the ceiling or limiting factor will be to its growth. GPUs? Power? Public opinion?

What do you think?