Everyone’s talking about AI. What do we here at Visual Assist expect? It’s clear it’s incredibly relevant – debate on that ship has sailed – but it’s hyped. We take a brief non-hyped look at where we think things will go.
An AI-generated image built at simplified.com with the prompt ‘A laptop with an AI onscreen’. Impressive it’s possible, but equally it has a long way to go. Images and movies are harder than text. Are they harder than code?
Today’s AI
- Runs on remote servers / the cloud
- Shares knowledge (unless you pay 10x as much) which makes it inappropriate for confidential data like source code
- Is computationally very expensive: the hardware required is expensive and you need a lot of it
- May not be relevant: it’s trained on wide data, but you may have something more specific, such as your own libraries and source
However:
- There’s a lot of work being done reducing the computation cost: for example, Facebook’s Llama and related models have a large number of tweaks that bring it down to single-computer levels at reasonable speeds
- Once it can run locally, accidentally shared knowledge is not an issue (at the same order of magnitude of cost, you could also have an affordable in-house server, shared only with employees)
- Once it can run locally, it can be used any time, not just with a net connection
- It may be much more relevant: if it’s trained on your data, it will be able to suggest domain-specific solutions
What’s key?
For commercial software development, three things are key:
- Keeping your source code confidential when getting AI input
- Low cost
- Giving domain-specific, your-app-specific useful results
We see local and private AI trained on your own codebase becoming a relevant reality quite soon. Compared to a remote cloud-based ChatGPT (for example) instance, that seems far, far more useful, practical, low cost, and safe.
Visual Assist
Tools like Copilot or ChatGPT, which are cool but legally risky for the owners and potentially dangerous for you if your source is added to their knowledgebase, are not the way forward. Plus, an AI that knows your tech is far more useful than an AI that knows generic programming. Local, private, trained-on-your-code AI is where we see industry relevance.
AI for Software Development FAQs: Privacy, Coding Assistants, and the Future of AI
What is AI-assisted software development?
AI-assisted software development refers to the use of artificial intelligence tools to help developers write, review, debug, document and optimize code. These tools can boost productivity by automating repetitive tasks and offering smart code suggestions.
Can AI write production-ready code?
AI can produce code snippets, boilerplate code, and even entire functions, but human review is still necessary. Developers should check AI-generated code for correctness, security, performance and maintainability before deploying the code to production.
Is it safe to share source code with AI tools?
It depends on the tool and how it is deployed. Code can be processed in the cloud with AI services running on external servers or on-premises with local AI solutions that allow organizations to maintain more control over proprietary code and sensitive data.
What are the benefits of running AI locally for software development?
Local AI solutions can improve code privacy, reduce dependency on internet connectivity, lower long-term operating costs, and provide more relevant suggestions when trained on internal codebases and development practices.
How can AI improve developer productivity?
AI can assist with code completion, debugging, documentation generation, code explanations, refactoring recommendations, and test creation, allowing developers to spend more time solving complex business problems.
Will AI replace software developers?
AI will probably complement developers rather than replace them. AI can automate routine coding, but developers are still needed to make architectural decisions, solve problems, design systems, conduct security reviews and understand business requirements.
What is the difference between local AI and cloud-based AI coding tools?
Cloud-based AI tools rely on remote servers to process requests, while local AI models run on a developer’s machine or private infrastructure. Local AI often offers stronger privacy controls, whereas cloud-based tools typically provide access to larger models and broader datasets.
Can AI be trained on a company’s internal codebase?
Yes, organizations can tailor AI models with their own code repos, documentation, and development standards to deliver more accurate, context-aware recommendations for their projects.
What should developers look for in an AI coding assistant?
Key factors include code privacy, accuracy, support for programming languages, integration with development tools, performance, customizability, and understanding of the context of the project.
How is AI changing the future of software development?
AI is changing software development, making it faster to code, improving code quality, making it easier to share knowledge and helping teams work more effectively. AI is expected to play a big role in the whole software development lifecycle with models becoming more specialized.
The above is our view on where AI will go for development. As for what this means for Visual Assist, none of this can be taken as a statement of product direction. It’s best to say that we are interested in the topic. VA already provides industry leading refactorings and other tooling powered by a unique code understanding engine, a tool developed to be non-compiler-like and more programmer-like. AI’s potential for features based on code understanding syncs very well with what we provide. Without hype, and moving carefully, we may see movement in this direction. If we do, as always it will be with the Visual Assist ethos: an eye towards true usefulness, not headlines; great performance; and the features we choose will be designed by devs, for devs.