[David Bloomfield] wanted to make some tweaks to an embedded system, but didn’t quite have the requisite skills. He decided to see if vibe coding could help.

[David]’s goal was simple. To take the VESC Telemetry Display created by [Lukas Janky] and add some tweaks of his own. He wanted to add more colors to the display, while changing the format of the displayed data and tweaking how it gets saved to EEPROM. The only problem was that [David] wasn’t experienced in coding at all, let alone for embedded systems like the Arduino Nano. His solution? Hand over the reigns to a large language model. [David] used Gemini 2.5 Pro to make the changes, and by and large, got the tweaks made that he was looking for.

There are risks here, of course. If you’re working on an embedded system, whatever you’re doing could have real world consequences. Meanwhile, if you’re relying on the AI to generate the code and you don’t fully understand it yourself… well, the possibilities are obvious. It pays to know what you’re doing at the end of the day. In this case, it’s hard to imagine much going wrong with a simple telemetry display, but it bears considering the risks whatever you’re doing.

We’ve talked about the advent of vibe coding before, too, with [Jenny List] exploring this nascent phenomenon. Expect it to remain a topic of controversy in coding circles for some time. Video after the break.

This week, the hackerverse was full of “vibe coding”. If you’re not caught up on your AI buzzwords, this is the catchy name coined by [Andrej Karpathy] that refers to basically just YOLOing it with AI coding assistants. It’s the AI-fueled version of typing in what you want to StackOverflow and picking the top answers. Only, with the current state of LLMs, it’ll probably work after a while of iterating back and forth with the machine.

It’s a tempting vision, and it probably works for a lot of simple applications, in popular languages, or generally where the ground is already well trodden. And where the stakes are low, as [Al Williams] pointed out while we were talking about vibing on the podcast. Can you imagine vibe-coded ATM software that probably gives you the right amount of money? Vibe-coding automotive ECU software?

While vibe coding seems very liberating and hands-off, it really just changes the burden of doing the coding yourself into making sure that the LLM is giving you what you want, and when it doesn’t, refining your prompts until it does. It’s more like editing and auditing code than authoring it. And while we have no doubt that a stellar programmer like [Karpathy] can verify that he’s getting what he wants, write the correct unit tests, and so on, we’re not sure it’s the panacea that is being proclaimed for folks who don’t already know how to code.

Vibe coding should probably be reserved for people who already are expert coders, and for trivial projects. Just the way you wouldn’t let grade-school kids use calculators until they’ve mastered the basics of math by themselves, you shouldn’t let junior programmers vibe code: It simultaneously demands too much knowledge to corral the LLM, while side-stepping any of the learning that would come from doing it yourself.

And then there’s the security side of vibe coding, which opens up a whole attack surface. If the LLM isn’t up to industry standards on simple things like input sanitization, your vibed code probably shouldn’t be anywhere near the Internet.

So should you be vibing? Sure! If you feel competent overseeing what [Dan] described as “the worst summer intern ever”, and the states are low, then it’s absolutely a fun way to kick the tires and see what the tools are capable of. Just go into it all with reasonable expectations.

Neverinstall AI is a personal AI computer assistant based in the cloud. It can perform a number of tasks and can instantly download and install apps on your cloud computer to match your needs. Just tell it what you want to do, like “I’m a designer and want to learn Figma.” It will instantly set […]

Source

CodiumAI is an AI code testing tool that supports Python, JavaScript, and TypeScript in VScode & JetBrains IDEs, and can tackle big and complicated code. It generates non-trivial tests (and trivial, too!) that help you understand how your code behaves and find edge cases and suspicious behaviors. It also provides explanations of the tests generated, […]

Source

Airplane Autopilot is an AI coding assistant that helps developers build internal tools faster. It acts like a pair programmer, generating code, explaining concepts, and providing debugging help. The tool is embedded right in Airplane’s development studio for seamless usage. Update: As of January 2024, the Airplane Autopilot service has been shut down. For similar […]

Source

MutableAI is an AI-accelerated software development tool to quickly create high-quality code with ease. It has an autocomplete feature which saves time on boilerplate and reduces reliance on Stack Overflow. Refactor, document and add types with one click. Simply give instructions to the AI to modify your code, there is also an upcoming test generation […]

Source

Amazon CodeWhisperer is an ML-powered AI coding assistant that helps developers build applications faster by providing real-time code recommendations in their integrated development environment (IDE). It can generate entire functions and logical code blocks, and offers recommendations for AWS APIs across popular services like EC2, Lambda, and S3. CodeWhisperer can also assist with unit test […]

Source

Sketch is an AI code-writing assistant for pandas users that is available on GitHub. It understands the context of your data, and can greatly improve the relevance of suggestions. It uses efficient algorithms to quickly summarize your data and feed it into language models. Sketch is usable in seconds and doesn’t require adding a plugin […]

Source

Zed is an AI code editor that integrates the AI capabilities of LLMs into your programming experience. Developed in collaboration with Anthropic, this coding tool offers a unique interface for AI-assisted coding directly within the editor. You can interact with AI models through an Assistant panel, slash commands, and inline assistance to generate, transform, and […]

Source

Buildt is an AI coding assistant currently in Alpha stage of development. The tool allows you to search for code snippets fast and easily. Just ask the AI what you’re looking for within the code (for example: what happens after a user logs in?“) and it will show you the exact code snippet where the […]

Source

Sweep is an open-source AI tool that works like your own junior developer. It’s designed to help with bug fixes, small features, and refactors in your codebase. Sweep works by reading your code, planning the changes, and then using that to generate a pull request with code. This lets you transform bug reports and feature […]

Source

JetBrains AI Assistant is an AI coding companion that supercharges your favorite IDEs like IntelliJ IDEA, PyCharm, and more. It allows you to chat with an AI assistant right inside your IDE to get help with coding tasks, without ever leaving your workflow. It automatically supplements your requests with details from your open project context, […]

Source

GitLab’s Code Suggestions is an AI tool that helps developers code faster and more efficiently. It can suggest complete lines of code, functions, tests, and boilerplate code as you type, letting you auto-complete code with a single keystroke. Code Suggestions keeps your source code secure, doesn’t retain or train on your code, and supports 13 […]

Source

OverflowAI is a new set of AI-powered products and features being added to Stack Overflow’s public platform and Stack Overflow for Teams. The goal is to leverage AI like semantic search and natural language processing to enhance the developer experience, while still keeping the Stack Overflow community at the center. OverflowAI is expected to be […]

Source