Totally agree on this. It has delivered a substantial value for me in my projects. The models are always going to give back results optimized for using minimal computing resources in the provider's infrastructure. To overcome this I see some using/suggesting, running the AI in self correction loops, the pro being least human intervention.
However, personally I have got very good results by taking the approach of using the AI with continuous interaction and also allowing implementation only after a good amount of time deliberating on design/architecture. I almost always append 'do not implement before we discuss and finalize the design' or 'clarify your assumptions, doubts or queries before implementation'.
When I asked Gemini to give a name for such an interaction it suggested 'Dialog Driven Development' also contrasted it against 'vide coding'. Transcript summary and AI disclaimer written by Gemini below
The models are mostly I believe capable of executing however as you rightly indicated 'lazy'. This 'laziness' I think is to conserve resource usage as much as possible as given the current state of AI market the infrastructure is being heavily subsidized for the user. This leads to perhaps the model being incentivized to produce an optimum result that satisfies the user by consuming the least amount of resources.
This is also why most 'vibe' coding projects fail as the model is always going to give this optimum ('lazy') result by default.
I decided to adopt AI assisted coding for a recent project. Not sure what defines 'vibe coding' but the process I ended up was a iterative interaction at a measured pace.
I used Gemini AI studio for this and I was very pleased at the result and decided to open source it. I have completely captured and documented the development transcript. Personally it has give me considerable productivity boost. My only irritation was the unnecessarily over politeness that AI adopts in My take is
AI yields good ROI when you know exactly what you want at the end of the process and when you want to compare and contrast decision choices during the process.
I have used it for all artifacts of the project:
- Core code base
- Test cases
- Build scripts
- Documentation
- Sample apps
- Utilities
Since AI code is inherently bound to face a critical review, we have kept the goal of security at the top. We have taken the following steps for it.
- 1. Code execution is sandboxed
- 2. Access to all built in modules of NodeJS is prevented, with option to whitelist using the server configuration
- 3. Platform APIs which access system (within the sandbox) also need to be whitelisted with explicit permission grants
Yes, we would like to make it ever more secure, with the help of the community and feedback from our customers. Like with any code human or ai there is bound to be bugs, the issue list of even the most popular, major projects out there is a testament to it. We intend to ever make it better for ourselves and for our customers.
Back in the peak years of ERP (90s), as a fresh graduate i started my career in a company called BaaN. It was one of the big two SAP (Germany) & BaaN (Netherlands). To give a sense of its capability, it is the product that Boeing chose as its ERP, Boeing being the most complex challenge for any ERP!
BaaN were pioneers in this kind of 4GL thinking and made some revolutionary stuff!
The product since then is sadly now a living a zombie life with its existing customer base. The link below gives a sense of what they provided.
However, personally I have got very good results by taking the approach of using the AI with continuous interaction and also allowing implementation only after a good amount of time deliberating on design/architecture. I almost always append 'do not implement before we discuss and finalize the design' or 'clarify your assumptions, doubts or queries before implementation'.
When I asked Gemini to give a name for such an interaction it suggested 'Dialog Driven Development' also contrasted it against 'vide coding'. Transcript summary and AI disclaimer written by Gemini below
https://gingerhome.github.io/gingee-docs/docs/ai-disclaimer.... https://gingerhome.github.io/gingee-docs/docs/ai-transcript/...